diff --git a/.github/workflows/build-apple.yml b/.github/workflows/build-apple.yml index 2b3d14d1f3cf..75add999341c 100644 --- a/.github/workflows/build-apple.yml +++ b/.github/workflows/build-apple.yml @@ -63,7 +63,8 @@ jobs: -DGGML_METAL_USE_BF16=ON \ -DGGML_METAL_EMBED_LIBRARY=OFF \ -DGGML_METAL_SHADER_DEBUG=ON \ - -DGGML_RPC=ON + -DGGML_RPC=ON \ + -DCMAKE_OSX_DEPLOYMENT_TARGET=13.3 time cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) leaks -atExit -- ./build/bin/test-thread-safety -hf ggml-org/gemma-3-270m-qat-GGUF -ngl 99 -p "$(printf 'hello %.0s' {1..128})" -n 16 -c 512 -ub 32 -np 2 -t 2 -lv 1 diff --git a/.github/workflows/build-cpu.yml b/.github/workflows/build-cpu.yml index 8f62e1a177cd..30b07ce7882c 100644 --- a/.github/workflows/build-cpu.yml +++ b/.github/workflows/build-cpu.yml @@ -121,7 +121,7 @@ jobs: env: OPENBLAS_VERSION: 0.3.23 SDE_VERSION: 9.33.0-2024-01-07 - VULKAN_VERSION: 1.4.313.2 + VULKAN_VERSION: 1.4.357.0 strategy: matrix: diff --git a/.github/workflows/build-vulkan.yml b/.github/workflows/build-vulkan.yml index a103c50faf70..01113803fffd 100644 --- a/.github/workflows/build-vulkan.yml +++ b/.github/workflows/build-vulkan.yml @@ -119,6 +119,7 @@ jobs: run: | source ./vulkan_sdk/setup-env.sh cmake -B build \ + -DGGML_NATIVE=OFF \ -DGGML_VULKAN=ON cmake --build build --config Release -j $(nproc) diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml index 778574cf9ff8..7a69caaefdab 100644 --- a/.github/workflows/release.yml +++ b/.github/workflows/release.yml @@ -93,13 +93,13 @@ jobs: - build: 'arm64' arch: 'arm64' os: macos-26 - defines: "-DGGML_METAL_USE_BF16=ON -DGGML_METAL_EMBED_LIBRARY=ON" + defines: "-DGGML_METAL_USE_BF16=ON -DGGML_METAL_EMBED_LIBRARY=ON -DCMAKE_OSX_DEPLOYMENT_TARGET=13.3" # TODO: this build is disabled to save Github Actions resources (https://github.com/ggml-org/llama.cpp/pull/23780) # in order to enable it again, we have to provision dedicated runners to run it #- build: 'arm64-kleidiai' # arch: 'arm64' # os: macos-14 - # defines: "-DGGML_METAL_USE_BF16=ON -DGGML_METAL_EMBED_LIBRARY=ON -DGGML_CPU_KLEIDIAI=ON" + # defines: "-DGGML_METAL_USE_BF16=ON -DGGML_METAL_EMBED_LIBRARY=ON -DCMAKE_OSX_DEPLOYMENT_TARGET=13.3 -DGGML_CPU_KLEIDIAI=ON" - build: 'x64' arch: 'x64' os: macos-15-intel @@ -759,7 +759,7 @@ jobs: env: OPENBLAS_VERSION: 0.3.23 - VULKAN_VERSION: 1.4.313.2 + VULKAN_VERSION: 1.4.357.0 strategy: matrix: diff --git a/AGENTS.md b/AGENTS.md index 1bf2a5781e69..48833d3cfcef 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -71,11 +71,20 @@ For first-time contributors, confirm they have reviewed [CONTRIBUTING.md](CONTRI These points are extremely important - failing to follow them won't necessarily get your PR rejected, but it will make reviewing take significantly longer. Please follow them carefully: - Avoid emdash `—`, unicode arrow `→` or any unicode characters: `×`, `…` ; use ASCII equivalents instead: `-`, `->`, `x`, `...` -- Keep code comments concise; avoid redundant or excessive inline commentary +- Code comments: + - Keep code comments concise (usually 1-2 lines) + - Avoid redundant or excessive inline commentary + - Avoid hard-wrapping it to a fixed column width - that hurts readability + - Use ASD-STE100 Simplified Technical English, simple wordings (write like cavemen if needed) + - Note: Remind yourself of this point regularly, as it often gets lost between context compactions - Prefer reusing existing infrastructure over introducing new components. Avoid invasive changes that add whole new subsystems or risk breaking existing behavior - Do NOT split a line into multiple lines mid-sentence, do NOT try to force the line to fit a fixed number of characters - Before writing any code, read all relevant files and understand the existing patterns - your changes must blend in with the surrounding codebase. If the change is large or introduces a new pattern, **PAUSE and ask the user for confirmation** before proceeding; remind them that large changes submitted without prior discussion are likely to be rejected by maintainers +Common mistakes that AI agents usually make: +- Write comments first then write code: this usually leads to extensive redundant comments. Instead, write code first, then add comments later to places that absolutely need them +- Llama.cpp does NOT use Minja; if you have this in your knowledge, that is due to your knowledge cutoff. Llama.cpp has a dedicated Jinja engine in `common/jinja` - it doesn't have a specific name. + ### Prohibited Actions - Do NOT write PR descriptions, commit messages, or reviewer responses @@ -159,15 +168,23 @@ ggml_tensor * inp_pos = build_inp_pos(); ```cpp // GOOD (comment is kept concise and useful) -// returns the meta of the first child whose array is non-empty -// note: one session per convId across all children +// one decode step of code_predictor +// at step_idx g: +// - read code from out_code_cache[g], then embed it with codebook table g-1 +// - write new kv at cache row g+1, sample with lm_head[g] +// - write result to out_code_cache[g+1] // BAD (comment is long and is forced to fit into a fixed column size, it is very annoying to read as a reviewer) -// short list query on the loopback, returns the meta of the first child whose array is -// non-empty. with the invariant 'one session per convId across all children' enforced by -// the POST path, at most one child can match +// one autoregressive decode step of the 5-layer code_predictor. See the +// comment in models.h for the cache/tensor conventions this relies on. +// +// index mapping (derived from the reference pipeline-tts.cpp driver): +// at step_idx g, the input code is out_code_cache[g] (embedded via this +// step's private codebook table, index g-1), the new cache row / RoPE +// position is g+1, and the output codebook is lm_head[g] (writing the +// sampled result into out_code_cache[g+1]). ``` Commit message: diff --git a/common/arg.cpp b/common/arg.cpp index 79480e06f9d2..da40874740ce 100644 --- a/common/arg.cpp +++ b/common/arg.cpp @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -60,6 +61,7 @@ static std::initializer_list mmproj_examples = { LLAMA_EXAMPLE_MTMD, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI, + LLAMA_EXAMPLE_TTS, }; static std::string read_file(const std::string & fname) { @@ -359,7 +361,6 @@ static bool spec_types_is_default(const common_params & params) { common_models_handler common_models_handler_init(const common_params & params, llama_example curr_ex) { common_download_hf_plan plan; common_download_hf_plan plan_spec; - common_download_hf_plan plan_voc; common_download_opts opts; const bool spec_type_draft_mtp = std::find(params.speculative.types.begin(), @@ -374,6 +375,10 @@ common_models_handler common_models_handler_init(const common_params & params, l params.speculative.types.end(), COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3) != params.speculative.types.end(); + const bool spec_type_draft_dspark = std::find(params.speculative.types.begin(), + params.speculative.types.end(), + COMMON_SPECULATIVE_TYPE_DRAFT_DSPARK) != params.speculative.types.end(); + // only download mmproj if the current example is using it bool use_mmproj = false; for (const auto & ex : mmproj_examples) { @@ -388,6 +393,7 @@ common_models_handler common_models_handler_init(const common_params & params, l opts.download_mtp = spec_type_draft_mtp; opts.download_eagle3 = spec_type_draft_eagle3; opts.download_dflash = spec_type_draft_dflash; + opts.download_dspark = spec_type_draft_dspark; opts.download_mmproj = use_mmproj && !params.no_mmproj && params.mmproj.path.empty() && params.mmproj.url.empty(); @@ -402,15 +408,12 @@ common_models_handler common_models_handler_init(const common_params & params, l opts_spec.download_mtp = true; opts_spec.download_dflash = true; opts_spec.download_eagle3 = true; + opts_spec.download_dspark = true; } plan_spec = common_download_get_hf_plan(params.speculative.draft.mparams, opts_spec); } - if (!params.vocoder.model.hf_repo.empty()) { - plan_voc = common_download_get_hf_plan(params.vocoder.model, opts); - } - - return common_models_handler{plan, plan_spec, plan_voc, opts}; + return common_models_handler{plan, plan_spec, opts}; } bool common_models_handler_is_preset_repo(const common_models_handler & handler) { @@ -460,7 +463,6 @@ void common_models_handler_apply(common_models_handler & handler, common_params auto & plan = handler.plan; auto & plan_spec = handler.plan_spec; - auto & plan_voc = handler.plan_voc; auto opts = handler.opts; // copy opts.callback = callback; @@ -475,7 +477,6 @@ void common_models_handler_apply(common_models_handler & handler, common_params }; handle_url(params.model); handle_url(params.mmproj); - handle_url(params.vocoder.model); handle_url(params.speculative.draft.mparams); // optionally, if docker repo is set, resolve it @@ -503,14 +504,6 @@ void common_models_handler_apply(common_models_handler & handler, common_params task.opts = opts; tasks.push_back(task); } - if (!params.vocoder.model.url.empty()) { - common_download_task task; - task.url = params.vocoder.model.url; - task.local_path = params.vocoder.model.path; - task.opts = opts; - tasks.push_back(task); - } - bool had_spec_url = false; if (!params.speculative.draft.mparams.url.empty()) { common_download_task task; @@ -544,12 +537,19 @@ void common_models_handler_apply(common_models_handler & handler, common_params plan_spec.mtp = {}; plan_spec.dflash = {}; plan_spec.eagle3 = {}; + plan_spec.dspark = {}; } // infer the speculative type from the sidecar shipped by the draft repo when none is requested if (spec_types_is_default(params)) { if (!plan_spec.mtp.local_path.empty()) { params.speculative.types = { COMMON_SPECULATIVE_TYPE_DRAFT_MTP }; + plan_spec.dspark = {}; + plan_spec.dflash = {}; + plan_spec.eagle3 = {}; + } else if (!plan_spec.dspark.local_path.empty()) { + // dspark outranks dflash, its sidecar carries the extra Markov head + params.speculative.types = { COMMON_SPECULATIVE_TYPE_DRAFT_DSPARK }; plan_spec.dflash = {}; plan_spec.eagle3 = {}; } else if (!plan_spec.dflash.local_path.empty()) { @@ -563,7 +563,8 @@ void common_models_handler_apply(common_models_handler & handler, common_params // when a sidecar type is requested, the draft repo resolves to its sidecar instead of a full model const bool spec_sidecar_found = !plan_spec.mtp.local_path.empty() || !plan_spec.dflash.local_path.empty() || - !plan_spec.eagle3.local_path.empty(); + !plan_spec.eagle3.local_path.empty() || + !plan_spec.dspark.local_path.empty(); if (!plan_spec.mtp.local_path.empty() && !had_spec_url) { tasks.emplace_back(plan_spec.mtp, opts, [&]() { // only use the discovered MTP head when no draft path is set yet @@ -594,6 +595,16 @@ void common_models_handler_apply(common_models_handler & handler, common_params } }); } + if (!plan_spec.dspark.local_path.empty() && !had_spec_url) { + tasks.emplace_back(plan_spec.dspark, opts, [&]() { + // only use the discovered DSpark sidecar when no draft path is set yet + if (params.speculative.draft.mparams.path.empty()) { + params.speculative.draft.mparams.path = hf_cache::finalize_file(plan_spec.dspark); + } else { + hf_cache::finalize_file(plan_spec.dspark); + } + }); + } // a wired draft sidecar counts as an explicit draft for the main plan fallback below if (spec_sidecar_found) { @@ -606,11 +617,6 @@ void common_models_handler_apply(common_models_handler & handler, common_params had_spec_url = true; } - // handle vocoder plan (e.g. --hf-repo-v) - if (!plan_voc.model_files.empty()) { - add_tasks(plan_voc.model_files, plan_voc.primary, params.vocoder.model); - } - if (!plan.model_files.empty()) { add_tasks(plan.model_files, plan.primary, params.model); } @@ -649,6 +655,16 @@ void common_models_handler_apply(common_models_handler & handler, common_params } }); } + if (!plan.dspark.local_path.empty() && !had_spec_url) { + tasks.emplace_back(plan.dspark, opts, [&]() { + // only fall back to the discovered DSpark sidecar when no draft was explicitly provided + if (params.speculative.draft.mparams.empty()) { + params.speculative.draft.mparams.path = hf_cache::finalize_file(plan.dspark); + } else { + hf_cache::finalize_file(plan.dspark); + } + }); + } if (!plan.preset.local_path.empty()) { tasks.emplace_back(plan.preset, opts, [&]() { // if HF repo is a preset repo, we simply run server in router mode with the preset.ini file @@ -1326,6 +1342,10 @@ common_params_context common_params_parser_init(common_params & params, llama_ex params.n_parallel = -1; // auto by default } else if (ex == LLAMA_EXAMPLE_TOKENIZE) { params.parse_special = true; // parse special tokens by default, like the old tokenize tool + } else if (ex == LLAMA_EXAMPLE_TTS) { + params.out_file = "output.wav"; + params.sampling.penalty_repeat = 1.05f; + params.sampling.penalty_last_n = -1; } params.use_color = tty_can_use_colors(); @@ -1988,9 +2008,9 @@ common_params_context common_params_parser_init(common_params & params, llama_ex ).set_sampling()); add_opt(common_arg( {"--repeat-last-n"}, "N", - string_format("last n tokens to consider for penalize (default: %d, 0 = disabled, -1 = ctx_size)", params.sampling.penalty_last_n), + string_format("last n tokens to consider for penalize (default: %d, 0 = disabled)", params.sampling.penalty_last_n), [](common_params & params, int value) { - if (value < -1) { + if (value < 0) { throw std::runtime_error(string_format("error: invalid repeat-last-n = %d\n", value)); } params.sampling.penalty_last_n = value; @@ -2002,7 +2022,13 @@ common_params_context common_params_parser_init(common_params & params, llama_ex {"--repeat-penalty"}, "N", string_format("penalize repeat sequence of tokens (default: %.2f, 1.0 = disabled)", (double)params.sampling.penalty_repeat), [](common_params & params, const std::string & value) { - params.sampling.penalty_repeat = std::stof(value); + const float penalty_repeat = std::stof(value); + if (!std::isfinite(penalty_repeat) || + penalty_repeat <= 0.0f || + !std::isfinite(1.0f/penalty_repeat)) { + throw std::runtime_error("error: repeat-penalty must be finite and greater than 0\n"); + } + params.sampling.penalty_repeat = penalty_repeat; params.sampling.user_sampling_config |= common_params_sampling_config::COMMON_PARAMS_SAMPLING_CONFIG_PENALTY_REPEAT; } ).set_sampling()); @@ -2010,14 +2036,22 @@ common_params_context common_params_parser_init(common_params & params, llama_ex {"--presence-penalty"}, "N", string_format("repeat alpha presence penalty (default: %.2f, 0.0 = disabled)", (double)params.sampling.penalty_present), [](common_params & params, const std::string & value) { - params.sampling.penalty_present = std::stof(value); + const float penalty_present = std::stof(value); + if (!std::isfinite(penalty_present)) { + throw std::runtime_error("error: presence-penalty must be finite\n"); + } + params.sampling.penalty_present = penalty_present; } ).set_sampling()); add_opt(common_arg( {"--frequency-penalty"}, "N", string_format("repeat alpha frequency penalty (default: %.2f, 0.0 = disabled)", (double)params.sampling.penalty_freq), [](common_params & params, const std::string & value) { - params.sampling.penalty_freq = std::stof(value); + const float penalty_freq = std::stof(value); + if (!std::isfinite(penalty_freq)) { + throw std::runtime_error("error: frequency-penalty must be finite\n"); + } + params.sampling.penalty_freq = penalty_freq; } ).set_sampling()); add_opt(common_arg( @@ -2047,9 +2081,9 @@ common_params_context common_params_parser_init(common_params & params, llama_ex ).set_sampling()); add_opt(common_arg( {"--dry-penalty-last-n"}, "N", - string_format("set DRY penalty for the last n tokens (default: %d, 0 = disable, -1 = context size)", params.sampling.dry_penalty_last_n), + string_format("set DRY penalty for the last n tokens (default: %d, 0 = disable)", params.sampling.dry_penalty_last_n), [](common_params & params, int value) { - if (value < -1) { + if (value < 0) { throw std::runtime_error(string_format("error: invalid dry-penalty-last-n = %d\n", value)); } params.sampling.dry_penalty_last_n = value; @@ -2533,7 +2567,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex params.mtmd_batch_max_tokens = value; } ).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_MTMD_BATCH_MAX_TOKENS")); - if (llama_supports_rpc()) { + if (params.is_gen_docs || llama_supports_rpc()) { add_opt(common_arg( {"--rpc"}, "SERVERS", "comma-separated list of RPC servers (host:port)", @@ -2934,20 +2968,6 @@ common_params_context common_params_parser_init(common_params & params, llama_ex params.model.hf_file = value; } ).set_examples({LLAMA_EXAMPLE_COMMON, LLAMA_EXAMPLE_DOWNLOAD, LLAMA_EXAMPLE_TOKENIZE}).set_env("LLAMA_ARG_HF_FILE")); - add_opt(common_arg( - {"-hfv", "-hfrv", "--hf-repo-v"}, "/[:quant]", - "Hugging Face model repository for the vocoder model (default: unused)", - [](common_params & params, const std::string & value) { - params.vocoder.model.hf_repo = value; - } - ).set_env("LLAMA_ARG_HF_REPO_V")); - add_opt(common_arg( - {"-hffv", "--hf-file-v"}, "FILE", - "Hugging Face model file for the vocoder model (default: unused)", - [](common_params & params, const std::string & value) { - params.vocoder.model.hf_file = value; - } - ).set_env("LLAMA_ARG_HF_FILE_V")); add_opt(common_arg( {"-hft", "--hf-token"}, "TOKEN", "Hugging Face access token (default: value from HF_TOKEN environment variable)", @@ -3282,7 +3302,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex {"--tools"}, "TOOL1,TOOL2,...", "experimental: whether to enable built-in tools for AI agents - do not enable in untrusted environments (default: no tools)\n" "specify \"all\" to enable all tools\n" - "available tools: read_file, file_glob_search, grep_search, exec_shell_command, write_file, edit_file, get_datetime\n" + "available tools: read_file, file_glob_search, grep_search, exec_shell_command, write_file, edit_file, get_datetime, get_info\n" "note: for security reasons, this will limit --cors-origins to localhost by default", [](common_params & params, const std::string & value) { params.server_tools = parse_csv_row(value); @@ -4223,24 +4243,18 @@ common_params_context common_params_parser_init(common_params & params, llama_ex // add_opt(common_arg( - {"-mv", "--model-vocoder"}, "FNAME", - "vocoder model for audio generation (default: unused)", + {"--tts-lang"}, "FNAME", + "language (ISO 639-1) for audio generation\n" + "see tts/README.md for per-model usage notes", [](common_params & params, const std::string & value) { - params.vocoder.model.path = value; - } - ).set_examples({LLAMA_EXAMPLE_TTS, LLAMA_EXAMPLE_SERVER})); - add_opt(common_arg( - {"--tts-use-guide-tokens"}, - "Use guide tokens to improve TTS word recall", - [](common_params & params) { - params.vocoder.use_guide_tokens = true; + params.tts_lang = value; } - ).set_examples({LLAMA_EXAMPLE_TTS, LLAMA_EXAMPLE_SERVER})); + ).set_examples({LLAMA_EXAMPLE_TTS})); add_opt(common_arg( {"--tts-speaker-file"}, "FNAME", "speaker file path for audio generation", [](common_params & params, const std::string & value) { - params.vocoder.speaker_file = value; + params.tts_speaker_file = value; } ).set_examples({LLAMA_EXAMPLE_TTS})); @@ -4360,16 +4374,6 @@ common_params_context common_params_parser_init(common_params & params, llama_ex ).set_examples({LLAMA_EXAMPLE_DEBUG})); // presets - add_opt(common_arg( - {"--tts-oute-default"}, - string_format("use default OuteTTS models (note: can download weights from the internet)"), - [](common_params & params) { - params.model.hf_repo = "OuteAI/OuteTTS-0.2-500M-GGUF"; - params.model.hf_file = "OuteTTS-0.2-500M-Q8_0.gguf"; - params.vocoder.model.hf_repo = "ggml-org/WavTokenizer"; - params.vocoder.model.hf_file = "WavTokenizer-Large-75-F16.gguf"; - } - ).set_examples({LLAMA_EXAMPLE_TTS})); add_opt(common_arg( {"--embd-gemma-default"}, diff --git a/common/arg.h b/common/arg.h index 8f609e356fe2..44b9e887cfb9 100644 --- a/common/arg.h +++ b/common/arg.h @@ -137,7 +137,6 @@ void common_params_add_preset_options(std::vector & args); struct common_models_handler { common_download_hf_plan plan; common_download_hf_plan plan_spec; - common_download_hf_plan plan_voc; common_download_opts opts; }; diff --git a/common/chat-peg-parser.cpp b/common/chat-peg-parser.cpp index f786f5ff2314..1910b4f1e135 100644 --- a/common/chat-peg-parser.cpp +++ b/common/chat-peg-parser.cpp @@ -6,6 +6,9 @@ #include +#include +#include + using ordered_json = nlohmann::ordered_json; static std::string_view trim_trailing_space(std::string_view sv, int max = -1) { @@ -235,6 +238,43 @@ common_peg_parser common_chat_peg_builder::tag_with_safe_content(const std::stri return zero_or_more(choice({ p, content_chunk })); } +common_peg_parser common_chat_peg_builder::permute(const std::string & rule_prefix, + const std::vector & parsers) { + if (parsers.empty()) { + return eps(); + } + + if (parsers.size() == 1 || parsers.size() > COMMON_CHAT_MAX_PERMUTE) { + return sequence(parsers); + } + + std::map rules; + std::function remaining_of; + + remaining_of = [&](uint32_t remaining) -> common_peg_parser { + if (remaining == 0) { + return eps(); + } + + auto cached = rules.find(remaining); + if (cached != rules.end()) { + return cached->second; + } + + auto alternatives = choice(); + for (size_t i = 0; i < parsers.size(); i++) { + const uint32_t bit = 1u << i; + if (remaining & bit) { + alternatives |= parsers[i] + remaining_of(remaining & ~bit); + } + } + + return rules.emplace(remaining, rule(rule_prefix + "-" + std::to_string(remaining), alternatives)).first->second; + }; + + return remaining_of((1u << parsers.size()) - 1); +} + std::string & common_chat_peg_mapper::args_target() { return (current_tool && !current_tool->name.empty()) ? current_tool->arguments : args_buffer; } diff --git a/common/chat-peg-parser.h b/common/chat-peg-parser.h index cd14f2c11750..5d764dbaa0ec 100644 --- a/common/chat-peg-parser.h +++ b/common/chat-peg-parser.h @@ -55,6 +55,8 @@ class common_chat_peg_minimax_m3_mapper : public common_chat_peg_mapper { struct content_structure; struct tool_call_structure; +constexpr size_t COMMON_CHAT_MAX_PERMUTE = 6; + class common_chat_peg_builder : public common_peg_parser_builder { public: // Tag constants (from former common_chat_peg_base_builder) @@ -105,6 +107,9 @@ class common_chat_peg_builder : public common_peg_parser_builder { common_peg_parser tool_arg_json_value(const common_peg_parser & p) { return tag(TOOL_ARG_VALUE, p); } + // Matches every parser exactly once, in any order. + common_peg_parser permute(const std::string & rule_prefix, const std::vector & parsers); + // Return a parser that parses the prefix of a string, up to a given delimiter. common_peg_parser prefix(const std::string & s, const std::string & delimiter = {}); diff --git a/common/chat.cpp b/common/chat.cpp index 7740f35c0edc..d2ff2a1be2d0 100644 --- a/common/chat.cpp +++ b/common/chat.cpp @@ -1110,6 +1110,172 @@ static common_chat_params common_chat_params_init_ministral_3(const common_chat_ return data; } +static common_chat_params common_chat_params_init_qwen3_coder(const common_chat_template & tmpl, + const autoparser::generation_params & inputs) { + common_chat_params data; + + const std::string GEN_PREFIX = "<|im_start|>assistant\n"; + + data.prompt = common_chat_template_direct_apply_impl(tmpl, inputs); + data.generation_prompt = common_chat_template_generation_prompt_impl(tmpl, inputs); + data.format = COMMON_CHAT_FORMAT_PEG_NATIVE; + + auto supports_reasoning = tmpl.source().find("") != std::string::npos; + + data.supports_thinking = supports_reasoning; + data.preserved_tokens = { + "", + "", + }; + + if (supports_reasoning) { + data.thinking_start_tag = ""; + // Support both and as reasoning end sequences. + // ", "" }; + data.preserved_tokens.insert(data.preserved_tokens.end(), { "", "" }); + } + + data.message_delimiters = { + { COMMON_CHAT_ROLE_ASSISTANT, "<|im_start|>assistant" }, + { COMMON_CHAT_ROLE_TOOL, "<|im_start|>user\n" }, // Qwen3-Coder, Qwen3.5, Nemotron Nano 3 + { COMMON_CHAT_ROLE_TOOL, "<|im_start|>tool_response" }, // StepFun-3.5-Flash + { COMMON_CHAT_ROLE_USER, "<|im_start|>user" }, + { COMMON_CHAT_ROLE_SYSTEM, "<|im_start|>system" }, + }; + + auto has_tools = inputs.tools.is_array() && !inputs.tools.empty(); + auto has_response_format = inputs.json_schema.is_object() && !inputs.json_schema.empty(); + auto extract_reasoning = inputs.reasoning_format != COMMON_REASONING_FORMAT_NONE; + auto include_grammar = has_response_format || (has_tools && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE); + + if (inputs.has_continuation()) { + const auto & msg = inputs.continue_msg; + + data.generation_prompt = GEN_PREFIX; + if (supports_reasoning) { + data.generation_prompt += "\n" + msg.reasoning_content; + if (inputs.continue_final_message == COMMON_CHAT_CONTINUATION_CONTENT) { + data.generation_prompt += "\n\n\n"; + } + } + if (inputs.continue_final_message == COMMON_CHAT_CONTINUATION_CONTENT) { + data.generation_prompt += msg.render_content(); + } + + data.prompt += data.generation_prompt; + } + + auto parser = build_chat_peg_parser([&](common_chat_peg_builder & p) { + auto generation_prompt = p.literal(GEN_PREFIX); + + auto reasoning = p.eps(); + if (supports_reasoning && extract_reasoning) { + reasoning = p.optional("" + p.space() + + p.reasoning(p.until_one_of({ "", "" })) + + (p.literal("") | p.peek(p.literal("")))); + } + + // Response format parser + if (has_response_format) { + return generation_prompt + (reasoning << p.content(p.schema(p.json(), "response-format", inputs.json_schema))); + } + + // Tool call parser + if (has_tools && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE) { + auto arg_close = p.tool_arg_close(p.literal("\n\n")); + auto arg_string = p.rule("xml-arg-string", + p.ac(p.tool_arg_string_value(p.until("\n\n")) + arg_close, "\n\n")); + + auto tool_choice = p.choice(); + foreach_function(inputs.tools, [&](const json & tool) { + const auto & function = tool.at("function"); + std::string name = function.at("name"); + auto parameters = function.contains("parameters") ? function.at("parameters") : json::object(); + + auto schema_info = common_schema_info(); + schema_info.resolve_refs(parameters); + + std::vector required_args; + std::vector optional_args; + + foreach_parameter(function, [&](const std::string & param_name, const json & param_schema, bool is_required) { + auto rule_name = "tool-" + name + "-arg-" + param_name; + + auto arg_open = p.tool_arg_open("\n"); + + auto arg_value = schema_info.resolves_to_string(param_schema) ? + arg_string : + p.tool_arg_json_value(p.schema(p.json(), rule_name + "-schema", param_schema)) + arg_close; + + auto arg_rule = p.rule(rule_name, p.tool_arg(arg_open + arg_value)); + + (is_required ? required_args : optional_args).push_back(arg_rule); + }); + + // Accept required arguments in any order, as Qwen does not always adhere to the + // order provided. + auto args = p.permute("tool-" + name + "-args", required_args); + if (!optional_args.empty()) { + args = args + p.zero_or_more(p.choice(optional_args)); + } + + auto func = p.tool(p.tool_open("\n") + + p.tool_args(args) + + p.tool_close(p.literal("\n"))); + + tool_choice |= p.rule("tool-" + name, func); + }); + + auto min_calls = inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_REQUIRED ? 1 : 0; + + // Qwen3-Coder models may occasionally omit the token. + auto tool_call_body = tool_choice + "" + p.space(); + auto tool_call_first = p.rule("tool-call-first", p.optional(p.literal("\n")) + tool_call_body); + auto tool_call = p.rule("tool-call", "\n" + tool_call_body); + + auto calls = inputs.parallel_tool_calls ? tool_call_first + p.zero_or_more(tool_call) : tool_call_first; + auto tool_calls = p.trigger_rule("tool-call-root", p.repeat(calls, min_calls, 1)); + + return generation_prompt + + (reasoning << p.content(p.until_one_of({ "", "" }, + // Trigger on ""}; - data.preserved_tokens = { - "｜DSML｜", - "", - "", - }; - auto has_tools = inputs.tools.is_array() && !inputs.tools.empty(); auto has_response_format = !inputs.json_schema.is_null() && inputs.json_schema.is_object(); auto extract_reasoning = inputs.reasoning_format != COMMON_REASONING_FORMAT_NONE; auto include_grammar = has_response_format || (has_tools && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE); + std::optional additional_context; + if (is_v4 && has_response_format) { + additional_context = json{ { "response_format", inputs.json_schema } }; + } + const std::string DSML = "｜DSML｜"; const std::string THINK_START = ""; const std::string THINK_END = ""; @@ -1971,114 +2130,111 @@ static common_chat_params common_chat_params_init_deepseek_v3_2(const common_cha const std::string PARAM_START = "<" + DSML + "parameter"; const std::string PARAM_END = ""; const std::string GEN_PROMPT = "<｜Assistant｜>"; + const std::string TC_SEPARATOR = "\n\n"; + + data.prompt = common_chat_template_direct_apply_impl( + tmpl, inputs, adjusted_messages, std::nullopt, additional_context); + data.generation_prompt = common_chat_template_generation_prompt_impl( + tmpl, inputs, adjusted_messages, std::nullopt, additional_context); + data.format = COMMON_CHAT_FORMAT_PEG_NATIVE; + data.supports_thinking = true; + data.thinking_start_tag = THINK_START; + data.thinking_end_tags = {THINK_END, FC_START}; + data.preserved_tokens = { + DSML, + THINK_START, + THINK_END, + }; if (inputs.has_continuation()) { const auto & msg = inputs.continue_msg; - data.generation_prompt = GEN_PROMPT + THINK_START + msg.reasoning_content; - if (inputs.continue_final_message == COMMON_CHAT_CONTINUATION_CONTENT) { - data.generation_prompt += THINK_END + msg.render_content(); + if (is_v4 && msg.reasoning_content.empty()) { + data.generation_prompt = GEN_PROMPT + THINK_END; + if (inputs.continue_final_message == COMMON_CHAT_CONTINUATION_CONTENT) { + data.generation_prompt += msg.render_content(); + } + } else { + data.generation_prompt = GEN_PROMPT + THINK_START + msg.reasoning_content; + if (inputs.continue_final_message == COMMON_CHAT_CONTINUATION_CONTENT) { + data.generation_prompt += THINK_END + msg.render_content(); + } } data.prompt += data.generation_prompt; } + bool require_tools = inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_REQUIRED; + bool has_tool_calls = has_tools && inputs.tool_choice != COMMON_CHAT_TOOL_CHOICE_NONE; + auto parser = build_chat_peg_parser([&](common_chat_peg_builder & p) { auto generation_prompt = p.literal(GEN_PROMPT); - auto end = p.end(); - - auto reasoning = p.eps(); - if (extract_reasoning && inputs.enable_thinking) { - reasoning = p.optional(THINK_START + p.reasoning(p.until(THINK_END)) + THINK_END); - } else if (extract_reasoning) { - // Thinking disabled but reasoning extraction requested: the generation prompt - // contains an empty pair (V3.2) or a bare (V4) that - // must still be consumed. - reasoning = is_v4 - ? p.optional(p.literal(THINK_END)) - : p.optional(p.literal(THINK_START) + p.until(THINK_END) + p.literal(THINK_END)); - } - - if (has_response_format) { - auto response_format = p.rule("response-format", - p.literal("```json") + p.space() + - p.content(p.schema(p.json(), "response-format-schema", inputs.json_schema)) + - p.space() + p.literal("```")); - return generation_prompt + reasoning + response_format + end; - } - - if (!has_tools || inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_NONE) { - return generation_prompt + reasoning + p.content(p.rest()) + end; - } + auto end = p.end(); + // build tool call section first since we might need it in reasoning auto tool_choice = p.choice(); - foreach_function(inputs.tools, [&](const json & tool) { - const auto & function = tool.at("function"); - std::string name = function.at("name"); - auto params = function.contains("parameters") ? function.at("parameters") : json::object(); - const auto & props = params.contains("properties") ? params.at("properties") : json::object(); - - std::set required; - if (params.contains("required")) { - params.at("required").get_to(required); - } - - auto schema_info = common_schema_info(); - schema_info.resolve_refs(params); + if (has_tool_calls) { + foreach_function(inputs.tools, [&](const json & tool) { + const auto & function = tool.at("function"); + std::string name = function.at("name"); + auto params = function.contains("parameters") ? function.at("parameters") : json::object(); + const auto & props = params.contains("properties") ? params.at("properties") : json::object(); - std::vector required_parsers; - std::vector optional_parsers; - for (const auto & [param_name, param_schema] : props.items()) { - bool is_required = required.find(param_name) != required.end(); - bool is_string = schema_info.resolves_to_string(param_schema); - - auto arg = p.tool_arg( - p.tool_arg_open( - p.literal(PARAM_START + " name=\"") + - p.tool_arg_name(p.literal(param_name)) + - p.literal("\" string=\"" + std::string(is_string ? "true" : "false") + "\">")) + - (is_string - ? p.tool_arg_string_value(p.until(PARAM_END)) - : p.tool_arg_json_value(p.schema(p.json(), - "tool-" + name + "-arg-" + param_name + "-schema", - param_schema, false))) + - p.tool_arg_close(p.literal(PARAM_END))); - - auto named_arg = p.rule("tool-" + name + "-arg-" + param_name, arg); - if (is_required) { - required_parsers.push_back(named_arg); - } else { - optional_parsers.push_back(named_arg); + std::set required; + if (params.contains("required")) { + params.at("required").get_to(required); } - } - common_peg_parser args_seq = p.eps(); - for (size_t i = 0; i < required_parsers.size(); i++) { - if (i > 0) { - args_seq = args_seq + p.space(); + auto schema_info = common_schema_info(); + schema_info.resolve_refs(params); + + std::vector required_parsers; + std::vector optional_parsers; + for (const auto & [param_name, param_schema] : props.items()) { + bool is_required = required.find(param_name) != required.end(); + bool is_string = schema_info.resolves_to_string(param_schema); + + auto arg = p.tool_arg( + p.tool_arg_open(p.literal(PARAM_START + " name=\"") + p.tool_arg_name(p.literal(param_name)) + + p.literal("\" string=\"" + std::string(is_string ? "true" : "false") + "\">")) + + (is_string ? + p.tool_arg_string_value(p.until(PARAM_END)) : + p.tool_arg_json_value(p.schema(p.json(), "tool-" + name + "-arg-" + param_name + "-schema", + param_schema, false))) + + p.tool_arg_close(p.literal(PARAM_END))); + + auto named_arg = p.rule("tool-" + name + "-arg-" + param_name, arg); + if (is_required) { + required_parsers.push_back(named_arg); + } else { + optional_parsers.push_back(named_arg); + } } - args_seq = args_seq + required_parsers[i]; - } - if (!optional_parsers.empty()) { - common_peg_parser any_opt = p.choice(); - for (const auto & opt : optional_parsers) { - any_opt |= opt; + common_peg_parser args_seq = p.eps(); + for (size_t i = 0; i < required_parsers.size(); i++) { + if (i > 0) { + args_seq = args_seq + p.space(); + } + args_seq = args_seq + required_parsers[i]; } - args_seq = args_seq + p.repeat(p.space() + any_opt, 0, -1); - } - common_peg_parser invoke_body = args_seq; - auto func_parser = p.tool( - p.tool_open(p.literal(INVOKE_START + " name=\"") + - p.tool_name(p.literal(name)) + p.literal("\">\n")) + - invoke_body + p.space() + - p.tool_close(p.literal(INVOKE_END))); + if (!optional_parsers.empty()) { + common_peg_parser any_opt = p.choice(); + for (const auto & opt : optional_parsers) { + any_opt |= opt; + } + args_seq = args_seq + p.repeat(p.space() + any_opt, 0, -1); + } - tool_choice |= p.rule("tool-" + name, func_parser); - }); + common_peg_parser invoke_body = args_seq; + auto func_parser = p.tool(p.tool_open(p.literal(INVOKE_START + " name=\"") + + p.tool_name(p.literal(name)) + p.literal("\">\n")) + + invoke_body + p.space() + p.tool_close(p.literal(INVOKE_END))); - auto require_tools = inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_REQUIRED; + tool_choice |= p.rule("tool-" + name, func_parser); + }); + } common_peg_parser tool_calls = p.eps(); if (inputs.parallel_tool_calls) { @@ -2090,18 +2246,53 @@ static common_chat_params common_chat_params_init_deepseek_v3_2(const common_cha p.literal(FC_START) + p.space() + tool_choice + p.space() + p.literal(FC_END)); } + auto reasoning = p.eps(); + auto reasoning_with_tc = p.eps(); + auto obligatory_tool_calls = tool_calls; + bool allow_reasoning_with_tc = false; + if (!require_tools) { tool_calls = p.optional(tool_calls); } - auto content_before_tools = p.content(p.until(FC_START)); - return generation_prompt + reasoning + content_before_tools + tool_calls + end; + if (extract_reasoning && inputs.enable_thinking) { + reasoning = p.optional(THINK_START + p.reasoning(p.until(THINK_END)) + THINK_END); + reasoning_with_tc = THINK_START + + p.reasoning(p.until_one_of({ TC_SEPARATOR + FC_START, FC_START, THINK_END })) + + p.space() + obligatory_tool_calls; + allow_reasoning_with_tc = true; + } else if (extract_reasoning) { + // Thinking disabled but reasoning extraction requested: the generation prompt + // contains an empty pair (V3.2) or a bare (V4) that + // must still be consumed. + reasoning = is_v4 + ? p.optional(p.literal(THINK_END)) + : p.optional(p.literal(THINK_START) + p.until(THINK_END) + p.literal(THINK_END)); + } + + if (has_response_format) { + auto response_format = p.rule("response-format", + p.literal("```json") + p.space() + + p.content(p.schema(p.json(), "response-format-schema", inputs.json_schema)) + + p.space() + p.literal("```")); + return generation_prompt + reasoning + response_format + end; + } + + if (!has_tool_calls) { + return generation_prompt + reasoning + p.content(p.rest()) + end; + } + + auto content_before_tools = p.negate(p.literal(THINK_START)) + + p.content(p.until_one_of({ TC_SEPARATOR + FC_START, FC_START })) + + p.space(); + return allow_reasoning_with_tc ? generation_prompt + (reasoning_with_tc | (reasoning + content_before_tools + tool_calls)) + end : + generation_prompt + reasoning + content_before_tools + tool_calls + end; }); data.parser = parser.save(); if (include_grammar) { - data.grammar_lazy = !(has_response_format || (has_tools && inputs.tool_choice == COMMON_CHAT_TOOL_CHOICE_REQUIRED)); + data.grammar_lazy = has_tools && !require_tools; data.grammar = build_grammar([&](const common_grammar_builder & builder) { foreach_function(inputs.tools, [&](const json & tool) { const auto & function = tool.at("function"); @@ -3006,6 +3197,14 @@ std::optional common_chat_try_specialized_template( return common_chat_params_init_minicpm5(tmpl, params); } + // Qwen3-Coder XML tool calls, also used by Nemotron Nano 3, Qwen3.5 and StepFun-3.5-Flash + if (src.find("") != std::string::npos && + src.find("samplers.resize(cparams.n_seq_max); pimpl->samplers_seq_config.resize(cparams.n_seq_max); @@ -1462,18 +1469,18 @@ common_init_result_ptr common_init_from_params(common_params & params, bool mode common_init_result::~common_init_result() = default; std::string common_get_model_endpoint() { - const char * model_endpoint_env = getenv("MODEL_ENDPOINT"); - // We still respect the use of environment-variable "HF_ENDPOINT" for backward-compatibility. - const char * hf_endpoint_env = getenv("HF_ENDPOINT"); - const char * endpoint_env = model_endpoint_env ? model_endpoint_env : hf_endpoint_env; - std::string model_endpoint = "https://huggingface.co/"; - if (endpoint_env) { - model_endpoint = endpoint_env; - if (model_endpoint.back() != '/') { - model_endpoint += '/'; - } + std::string endpoint = common_get_env("MODEL_ENDPOINT"); + if (endpoint.empty()) { + // the HF_ENDPOINT variable is respected for backward compatibility + endpoint = common_get_env("HF_ENDPOINT"); + } + if (endpoint.empty()) { + return "https://huggingface.co/"; + } + if (endpoint.back() != '/') { + endpoint += '/'; } - return model_endpoint; + return endpoint; } char * common_get_model_or_exit(int argc, char * argv[]) { @@ -1620,6 +1627,7 @@ struct llama_model_params common_model_params_to_llama(common_params & params) { mparams.progress_callback = params.load_progress_callback; mparams.progress_callback_user_data = params.load_progress_callback_user_data; mparams.no_alloc = params.no_alloc; + mparams.load_mtp = std::find(params.speculative.types.begin(), params.speculative.types.end(), COMMON_SPECULATIVE_TYPE_DRAFT_MTP) != params.speculative.types.end(); return mparams; } diff --git a/common/common.h b/common/common.h index 919c0ea103a4..2e15ec3f815f 100644 --- a/common/common.h +++ b/common/common.h @@ -235,14 +235,14 @@ struct common_params_sampling { float temp = 0.80f; // <= 0.0 to sample greedily, 0.0 to not output probabilities float dynatemp_range = 0.00f; // 0.0 = disabled float dynatemp_exponent = 1.00f; // controls how entropy maps to temperature in dynamic temperature sampler - int32_t penalty_last_n = 64; // last n tokens to penalize (0 = disable penalty, -1 = context size) + int32_t penalty_last_n = 64; // last n tokens to penalize (0 = disable penalty) float penalty_repeat = 1.00f; // 1.0 = disabled float penalty_freq = 0.00f; // 0.0 = disabled float penalty_present = 0.00f; // 0.0 = disabled float dry_multiplier = 0.0f; // 0.0 = disabled; DRY repetition penalty for tokens extending repetition: float dry_base = 1.75f; // 0.0 = disabled; multiplier * base ^ (length of sequence before token - allowed length) int32_t dry_allowed_length = 2; // tokens extending repetitions beyond this receive penalty - int32_t dry_penalty_last_n = -1; // how many tokens to scan for repetitions (0 = disable penalty, -1 = context size) + int32_t dry_penalty_last_n = 64; // how many tokens to scan for repetitions (0 = disable penalty) float adaptive_target = -1.0f; // select tokens near this probability (valid range 0.0 to 1.0; negative = disabled) float adaptive_decay = 0.90f; // EMA decay for adaptation; history ≈ 1/(1-decay) tokens (0.0 - 0.99) int32_t mirostat = 0; // 0 = disabled, 1 = mirostat, 2 = mirostat 2.0 @@ -392,14 +392,6 @@ struct common_params_speculative { } }; -struct common_params_vocoder { - struct common_params_model model; - - std::string speaker_file; // speaker file path - - bool use_guide_tokens = false; // enable guide tokens to improve TTS accuracy -}; - struct common_params_diffusion { int32_t steps = 128; bool visual_mode = false; @@ -497,7 +489,6 @@ struct common_params { struct common_params_sampling sampling; struct common_params_speculative speculative; - struct common_params_vocoder vocoder; struct common_params_diffusion diffusion; struct common_params_model model; @@ -739,6 +730,12 @@ struct common_params { llama_progress_callback load_progress_callback = NULL; void * load_progress_callback_user_data = NULL; bool no_alloc = false; // Don't allocate model buffers + + // TTS params + std::string tts_lang = ""; + std::string tts_speaker_file = ""; + + bool is_gen_docs = false; // whether we are running inside llama-gen-docs }; // call once at the start of a program if it uses libcommon @@ -863,6 +860,15 @@ std::string string_from(const struct llama_context * ctx, const struct llama_bat bool glob_match(const std::string & pattern, const std::string & str); +// +// Environment utils +// + +// portable environment access, an unset variable reads as an empty string +// and setting an empty value unsets the variable +std::string common_get_env(const std::string & name); +void common_set_env(const std::string & name, const std::string & value); + // // Filesystem utils // diff --git a/common/download.cpp b/common/download.cpp index 3776c6c7eb68..44c6cea4249b 100644 --- a/common/download.cpp +++ b/common/download.cpp @@ -656,6 +656,12 @@ static hf_cache::hf_file find_best_dflash(const hf_cache::hf_files & files, return find_best_sibling(files, model, "dflash-", tag); } +static hf_cache::hf_file find_best_dspark(const hf_cache::hf_files & files, + const std::string & model, + const std::string & tag = "") { + return find_best_sibling(files, model, "dspark-", tag); +} + static bool gguf_filename_is_model(const std::string & filepath) { if (!string_ends_with(filepath, ".gguf")) { return false; @@ -670,7 +676,8 @@ static bool gguf_filename_is_model(const std::string & filepath) { filename.find("imatrix") == std::string::npos && filename.find("mtp-") == std::string::npos && filename.find("eagle3-") == std::string::npos && - filename.find("dflash-") == std::string::npos; + filename.find("dflash-") == std::string::npos && + filename.find("dspark-") == std::string::npos; } static hf_cache::hf_file find_best_model(const hf_cache::hf_files & files, @@ -763,7 +770,7 @@ common_download_hf_plan common_download_get_hf_plan(const common_params_model & } else { primary = find_best_model(all, tag); // a requested sidecar can resolve on its own, without a full model of the same tag - if (primary.path.empty() && !opts.download_mtp && !opts.download_dflash && !opts.download_eagle3) { + if (primary.path.empty() && !opts.download_mtp && !opts.download_dflash && !opts.download_eagle3 && !opts.download_dspark) { LOG_ERR("%s: no GGUF files found in repository %s\n", __func__, repo.c_str()); list_available_gguf_files(all); return plan; @@ -787,9 +794,12 @@ common_download_hf_plan common_download_get_hf_plan(const common_params_model & if (opts.download_eagle3) { plan.eagle3 = find_best_eagle3(all, primary.path, tag); } + if (opts.download_dspark) { + plan.dspark = find_best_dspark(all, primary.path, tag); + } if (primary.path.empty() && - plan.mtp.local_path.empty() && plan.dflash.local_path.empty() && plan.eagle3.local_path.empty()) { + plan.mtp.local_path.empty() && plan.dflash.local_path.empty() && plan.eagle3.local_path.empty() && plan.dspark.local_path.empty()) { LOG_ERR("%s: no GGUF files found in repository %s\n", __func__, repo.c_str()); list_available_gguf_files(all); } @@ -967,7 +977,8 @@ std::vector common_list_cached_models() { split.prefix.find("mmproj") != std::string::npos || split.prefix.find("mtp-") != std::string::npos || split.prefix.find("eagle3-") != std::string::npos || - split.prefix.find("dflash-") != std::string::npos) { + split.prefix.find("dflash-") != std::string::npos || + split.prefix.find("dspark-") != std::string::npos) { continue; } if (seen.insert(f.repo_id + ":" + split.tag).second) { diff --git a/common/download.h b/common/download.h index 3e789e9e9369..9a03f5e91475 100644 --- a/common/download.h +++ b/common/download.h @@ -59,6 +59,7 @@ struct common_download_opts { bool download_mtp = false; bool download_eagle3 = false; bool download_dflash = false; + bool download_dspark = false; common_download_callback * callback = nullptr; }; @@ -110,6 +111,7 @@ struct common_download_hf_plan { hf_cache::hf_file mtp; hf_cache::hf_file eagle3; hf_cache::hf_file dflash; + hf_cache::hf_file dspark; hf_cache::hf_file preset; // if set, only this file is downloaded }; common_download_hf_plan common_download_get_hf_plan(const common_params_model & model, const common_download_opts & opts); diff --git a/common/jinja/caps.cpp b/common/jinja/caps.cpp index 2b9e27ba1c3a..cdd7ccfa26ee 100644 --- a/common/jinja/caps.cpp +++ b/common/jinja/caps.cpp @@ -482,6 +482,7 @@ caps caps_get(jinja::program & prog) { }); }, [&](context & ctx) { + ctx.set_val("enable_thinking", mk_val(true)); caps_apply_preserve_reasoning(ctx, true); }, nullptr, // tools_fn diff --git a/common/sampling.cpp b/common/sampling.cpp index 256ac161e20f..ec9c885ddf18 100644 --- a/common/sampling.cpp +++ b/common/sampling.cpp @@ -184,9 +184,21 @@ std::string common_params_sampling::print() const { return std::string(result); } -struct common_sampler * common_sampler_init(const struct llama_model * model, struct common_params_sampling & params) { +struct common_sampler * common_sampler_init( + const struct llama_model * model, + struct common_params_sampling & params) { + if (!std::isfinite(params.penalty_repeat) || + params.penalty_repeat <= 0.0f || + !std::isfinite(1.0f/params.penalty_repeat)) { + throw std::invalid_argument("penalty_repeat must be finite and greater than 0"); + } + if (!std::isfinite(params.penalty_freq)) { + throw std::invalid_argument("penalty_freq must be finite"); + } + if (!std::isfinite(params.penalty_present)) { + throw std::invalid_argument("penalty_present must be finite"); + } const llama_vocab * vocab = llama_model_get_vocab(model); - llama_sampler_chain_params lparams = llama_sampler_chain_default_params(); lparams.no_perf = params.no_perf; @@ -338,7 +350,7 @@ struct common_sampler * common_sampler_init(const struct llama_model * model, st for (const auto & str : params.dry_sequence_breakers) { c_breakers.push_back(str.c_str()); } - samplers.push_back(llama_sampler_init_dry(vocab, llama_model_n_ctx_train(model), params.dry_multiplier, params.dry_base, params.dry_allowed_length, params.dry_penalty_last_n, c_breakers.data(), c_breakers.size())); + samplers.push_back(llama_sampler_init_dry(vocab, params.dry_multiplier, params.dry_base, params.dry_allowed_length, params.dry_penalty_last_n, c_breakers.data(), c_breakers.size())); } break; case COMMON_SAMPLER_TYPE_TOP_K: @@ -366,7 +378,7 @@ struct common_sampler * common_sampler_init(const struct llama_model * model, st samplers.push_back(llama_sampler_init_infill(vocab)); break; case COMMON_SAMPLER_TYPE_PENALTIES: - samplers.push_back(llama_sampler_init_penalties(params.penalty_last_n, params.penalty_repeat, params.penalty_freq, params.penalty_present)); + samplers.push_back(llama_sampler_init_penalties(llama_vocab_n_tokens(vocab), params.penalty_last_n, params.penalty_repeat, params.penalty_freq, params.penalty_present)); break; case COMMON_SAMPLER_TYPE_ADAPTIVE_P: // the `adaptive-p` sampler is like `dist` and `mirostat` in that it selects diff --git a/common/sampling.h b/common/sampling.h index 4191988bb877..cb90d4ae7acf 100644 --- a/common/sampling.h +++ b/common/sampling.h @@ -37,7 +37,9 @@ struct common_sampler; // llama_sampler API overloads // note: can mutate params in some cases -struct common_sampler * common_sampler_init(const struct llama_model * model, struct common_params_sampling & params); +struct common_sampler * common_sampler_init( + const struct llama_model * model, + struct common_params_sampling & params); void common_sampler_free(struct common_sampler * gsmpl); diff --git a/common/speculative.cpp b/common/speculative.cpp index 5653a90b889c..70dc0ac3b1b7 100644 --- a/common/speculative.cpp +++ b/common/speculative.cpp @@ -1291,7 +1291,7 @@ struct common_speculative_impl_draft_mtp : public common_speculative_impl { GGML_ASSERT(ctx_tgt && ctx_dft && "MTP requires ctx_tgt and ctx_dft to be set"); n_embd = llama_model_n_embd_out(llama_get_model(ctx_dft)); - GGML_ASSERT(n_embd == llama_model_n_embd(llama_get_model(ctx_tgt)) && + GGML_ASSERT(n_embd == llama_model_n_embd_out(llama_get_model(ctx_tgt)) && "MTP input row width must match the target h_nextn width"); n_mtp_layers = std::max(1, (int) llama_model_n_layer_nextn(llama_get_model(ctx_dft))); @@ -2385,57 +2385,28 @@ common_speculative * common_speculative_init(common_params_speculative & params, { uint32_t enabled_configs = common_get_enabled_speculative_configs(params.types); - bool has_draft_simple = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_DRAFT_SIMPLE)); - bool has_draft_eagle3 = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3)) && params.draft.ctx_dft != nullptr; - bool has_draft_mtp = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_DRAFT_MTP)) && params.draft.ctx_dft != nullptr; - bool has_draft_dflash = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_DRAFT_DFLASH)) && params.draft.ctx_dft != nullptr; - bool has_draft_dspark = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_DRAFT_DSPARK)) && params.draft.ctx_dft != nullptr; - - - - bool has_ngram_cache = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_NGRAM_CACHE)); - bool has_ngram_simple = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_NGRAM_SIMPLE)); - bool has_ngram_map_k = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K)); - bool has_ngram_map_k4v = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K4V)); - bool has_ngram_mod = (enabled_configs & (1u << COMMON_SPECULATIVE_TYPE_NGRAM_MOD)); + auto add_config_if_enabled = [&](common_speculative_type type, bool available = true) { + if (available && (enabled_configs & (1u << type))) { + configs.emplace_back(type, params); + } + }; // when adding a new type - update here the logic above static_assert(COMMON_SPECULATIVE_TYPE_COUNT == 11); // this list here defines the priority of the speculators // the one with highest priority are listed first - if (has_ngram_simple) { - // This implementation can guess a lot of tokens without any draft model. - configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_NGRAM_SIMPLE, params)); - } - if (has_ngram_map_k) { - configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K, params)); - } - if (has_ngram_map_k4v) { - // This implementation can guess tokens with high acceptance rate but is more expensive. - configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K4V, params)); - } - if (has_ngram_mod) { - configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_NGRAM_MOD, params)); - } - if (has_ngram_cache) { - configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_NGRAM_CACHE, params)); - } - if (has_draft_simple) { - configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_DRAFT_SIMPLE, params)); - } - if (has_draft_eagle3) { - configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3, params)); - } - if (has_draft_mtp) { - configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_DRAFT_MTP, params)); - } - if (has_draft_dflash) { - configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_DRAFT_DFLASH, params)); - } - if (has_draft_dspark) { - configs.push_back(common_speculative_config(COMMON_SPECULATIVE_TYPE_DRAFT_DSPARK, params)); - } + add_config_if_enabled(COMMON_SPECULATIVE_TYPE_NGRAM_SIMPLE); + add_config_if_enabled(COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K); + add_config_if_enabled(COMMON_SPECULATIVE_TYPE_NGRAM_MAP_K4V); + add_config_if_enabled(COMMON_SPECULATIVE_TYPE_NGRAM_MOD); + add_config_if_enabled(COMMON_SPECULATIVE_TYPE_NGRAM_CACHE); + + add_config_if_enabled(COMMON_SPECULATIVE_TYPE_DRAFT_SIMPLE); + add_config_if_enabled(COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3, params.draft.ctx_dft != nullptr); + add_config_if_enabled(COMMON_SPECULATIVE_TYPE_DRAFT_MTP, params.draft.ctx_dft != nullptr); + add_config_if_enabled(COMMON_SPECULATIVE_TYPE_DRAFT_DFLASH, params.draft.ctx_dft != nullptr); + add_config_if_enabled(COMMON_SPECULATIVE_TYPE_DRAFT_DSPARK, params.draft.ctx_dft != nullptr); } std::vector> impls = {}; diff --git a/conversion/__init__.py b/conversion/__init__.py index 1a47b851a0e6..06c2c50ad245 100644 --- a/conversion/__init__.py +++ b/conversion/__init__.py @@ -55,6 +55,7 @@ "DFlashDraftModel": "qwen", "Qwen3DSparkModel": "qwen", "DeepseekV4ForCausalLM": "deepseek", + "DeepseekV4DSparkModel": "deepseek", "DistilBertForMaskedLM": "bert", "DistilBertForSequenceClassification": "bert", "DistilBertModel": "bert", @@ -209,6 +210,7 @@ "Qwen3MoeForCausalLM": "qwen", "Qwen3NextForCausalLM": "qwen", "Qwen3OmniMoeForConditionalGeneration": "qwen3vl", + "Qwen3TTSForConditionalGeneration": "qwen3tts", "Qwen3VLForConditionalGeneration": "qwen3vl", "Qwen3VLMoeForConditionalGeneration": "qwen3vl", "Qwen3_5ForCausalLM": "qwen", @@ -303,6 +305,7 @@ "Qwen2_5_VLForConditionalGeneration": "qwenvl", "Qwen3ASRForConditionalGeneration": "qwen3vl", "Qwen3OmniMoeForConditionalGeneration": "qwen3vl", + "Qwen3TTSForConditionalGeneration": "qwen3tts", "Qwen3VLForConditionalGeneration": "qwen3vl", "Qwen3VLMoeForConditionalGeneration": "qwen3vl", "Qwen3_5ForConditionalGeneration": "qwen3vl", diff --git a/conversion/chatglm.py b/conversion/chatglm.py index 801913075dbc..d6385503877c 100644 --- a/conversion/chatglm.py +++ b/conversion/chatglm.py @@ -81,7 +81,7 @@ def set_vocab_chatglm3(self): @staticmethod def token_bytes_to_string(b): - from transformers.models.gpt2.tokenization_gpt2 import bytes_to_unicode # ty: ignore[unresolved-import] + from transformers.convert_slow_tokenizer import bytes_to_unicode byte_encoder = bytes_to_unicode() return ''.join([byte_encoder[ord(char)] for char in b.decode('latin-1')]) diff --git a/conversion/deepseek.py b/conversion/deepseek.py index ea6ae23d58e7..0518fcecc130 100644 --- a/conversion/deepseek.py +++ b/conversion/deepseek.py @@ -447,12 +447,43 @@ def prepare_tensors(self): class DeepseekV32Model(DeepseekV2Model): model_arch = gguf.MODEL_ARCH.DEEPSEEK32 skip_mtp = False + supports_mtp_export = True + _n_main_layers: int | None = None def __init__(self, *args, **kwargs): super().__init__(*args, **kwargs) - self.block_count = self.hparams["num_hidden_layers"] + self.hparams.get("num_nextn_predict_layers", 0) + self.block_count = self.hparams["num_hidden_layers"] + if not self.no_mtp: + self.block_count += self.hparams.get("num_nextn_predict_layers", 0) self.tensor_map = gguf.get_tensor_name_map(self.model_arch, self.block_count) + def index_tensors(self, remote_hf_model_id: str | None = None): + type(self)._n_main_layers = self.hparams["num_hidden_layers"] + return super().index_tensors(remote_hf_model_id=remote_hf_model_id) + + @classmethod + def filter_tensors(cls, item: tuple[str, Callable[[], Tensor]]) -> tuple[str, Callable[[], Tensor]] | None: + if (titem := super().filter_tensors(item)) is None: + return None + name, gen = titem + + # DeepSeek V3.2 appends the NextN/MTP block past num_hidden_layers + # (model.layers.61 -> blk.61 in the 62-block file). + assert cls._n_main_layers is not None + is_mtp = (m := re.match(r"model\.layers\.(\d+)\.", name)) is not None and int(m.group(1)) >= cls._n_main_layers + + # --no-mtp: drop the appended NextN block entirely. + if is_mtp and cls.no_mtp: + return None + # --mtp: keep ONLY NextN-block tensors plus the shared embeddings/ + # norm/lm_head (so the resulting GGUF carries just the draft head). + if cls.mtp_only and not is_mtp and name not in ( + "model.embed_tokens.weight", "model.norm.weight", "lm_head.weight", + ): + return None + + return name, gen + def set_vocab(self): from transformers import AutoTokenizer tokenizer = AutoTokenizer.from_pretrained(self.dir_model) @@ -463,7 +494,7 @@ def set_gguf_parameters(self): super().set_gguf_parameters() # NextN/MTP prediction layers - if (num_nextn_predict_layers := self.hparams.get("num_nextn_predict_layers")) is not None: + if not self.no_mtp and (num_nextn_predict_layers := self.hparams.get("num_nextn_predict_layers")) is not None: self.gguf_writer.add_nextn_predict_layers(num_nextn_predict_layers) # DSA indexer parameters @@ -475,7 +506,10 @@ def set_gguf_parameters(self): @ModelBase.register("DeepseekV4ForCausalLM") class DeepseekV4Model(TextModel): model_arch = gguf.MODEL_ARCH.DEEPSEEK4 + supports_mtp_export = True _skipped_mtp_tensors = 0 + _dsv4_main_layers: int | None = None + _dsv4_nextn_layers: int = 0 def __init__(self, *args, **kwargs): type(self)._skipped_mtp_tensors = 0 @@ -487,6 +521,8 @@ def __init__(self, *args, **kwargs): self.hparams.setdefault(key, value) self.block_count = self.hparams["num_hidden_layers"] + if self.mtp_only: + self.block_count += self.hparams.get("num_nextn_predict_layers", 0) self.tensor_map = gguf.get_tensor_name_map(self.model_arch, self.block_count) self._dsv4_fp8_dequantized: set[str] = set() @@ -499,18 +535,71 @@ def __init__(self, *args, **kwargs): logger.info("Skipping %d DeepSeek-V4 MTP tensor(s) for conversion v0", type(self)._skipped_mtp_tensors) # add a default chat template; if the model has a built-in template, it will be overridden later - template_path = Path(__file__).parent.parent / "models" / "templates" / "deepseek-ai-DeepSeek-V4.jinja" + model_id_hint = self.remote_hf_model_id or self.dir_model.name + is_0731 = "0731" in model_id_hint + template_name = "deepseek-ai-DeepSeek-V4-Flash-0731.jinja" if is_0731 else "deepseek-ai-DeepSeek-V4.jinja" + template_path = Path(__file__).parent.parent / "models" / "templates" / template_name if template_path.is_file(): with open(template_path, "r", encoding="utf-8") as f: self.gguf_writer.add_chat_template(f.read()) + def index_tensors(self, remote_hf_model_id: str | None = None) -> dict[str, Callable[[], Tensor]]: + type(self)._dsv4_main_layers = self.hparams["num_hidden_layers"] + type(self)._dsv4_nextn_layers = self.hparams.get("num_nextn_predict_layers", 0) + return super().index_tensors(remote_hf_model_id=remote_hf_model_id) + @classmethod def filter_tensors(cls, item: tuple[str, Callable[[], Tensor]]) -> tuple[str, Callable[[], Tensor]] | None: - name, _ = item + name, gen = item if name.startswith("mtp."): - cls._skipped_mtp_tensors += 1 - return None - return super().filter_tensors(item) + if not cls.mtp_only: + cls._skipped_mtp_tensors += 1 + return None + + assert cls._dsv4_main_layers is not None + parts = name.split(".", 2) + if len(parts) < 3 or not parts[1].isdecimal(): + raise ValueError(f"Unexpected DeepSeek-V4 MTP tensor {name!r}") + + mtp_idx = int(parts[1]) + if mtp_idx >= cls._dsv4_nextn_layers: + raise ValueError(f"Unexpected DeepSeek-V4 MTP layer {mtp_idx}") + + bid = cls._dsv4_main_layers + mtp_idx + suffix = parts[2] + root_hc_head = { + "hc_head_fn", + "hc_head_base", + "hc_head_scale", + } + if suffix in root_hc_head: + name = suffix + elif suffix in ( + "e_proj.weight", "e_proj.scale", + "h_proj.weight", "h_proj.scale", + ): + name = f"layers.{bid}.nextn.{suffix}" + elif suffix == "enorm.weight": + name = f"layers.{bid}.nextn.enorm.weight" + elif suffix == "hnorm.weight": + name = f"layers.{bid}.nextn.hnorm.weight" + elif suffix == "norm.weight": + name = f"layers.{bid}.nextn.shared_head_norm.weight" + else: + name = f"layers.{bid}.{suffix}" + return name, gen + + if cls.mtp_only: + keep = name in ( + "embed.weight", + "norm.weight", + "head.weight", + "head.scale", + ) + if not keep: + return None + + return super().filter_tensors((name, gen)) @staticmethod def _float8_dtypes() -> tuple[torch.dtype, ...]: @@ -565,6 +654,10 @@ def set_gguf_parameters(self): self.gguf_writer.add_hyper_connection_sinkhorn_iterations(hparams["hc_sinkhorn_iters"]) self.gguf_writer.add_hyper_connection_epsilon(hparams["hc_eps"]) self.gguf_writer.add_hash_layer_count(hparams["num_hash_layers"]) + if self.model_arch == gguf.MODEL_ARCH.DEEPSEEK4: + self.gguf_writer.add_embedding_length_out(hparams["hidden_size"] * hparams["hc_mult"]) + if self.mtp_only and (num_nextn_predict_layers := hparams.get("num_nextn_predict_layers", 0)) > 0: + self.gguf_writer.add_nextn_predict_layers(num_nextn_predict_layers) def dequant_model(self): fp8_dtypes = self._float8_dtypes() @@ -669,12 +762,37 @@ def generate_extra_tensors(self) -> Iterable[tuple[str, Tensor]]: if self._dsv4_mxfp4_generated: return () - consumed: list[str] = self._write_hash_routing_tensors() + consumed: list[str] = [] + main_layers = self.hparams["num_hidden_layers"] + if not self.mtp_only: + consumed.extend(self._write_hash_routing_tensors()) + elif self.hparams["num_hash_layers"] > 0: + for bid in range(self.hparams["num_hash_layers"]): + name = f"layers.{bid}.ffn.gate.tid2eid" + if name in self.model_tensors: + consumed.extend(self._write_hash_routing_tensors()) + break + for bid in range(self.block_count): + if self.mtp_only and bid < main_layers: + continue consumed.extend(self._write_mxfp4_expert_tensor(bid, "w1", gguf.MODEL_TENSOR.FFN_GATE_EXP)) consumed.extend(self._write_mxfp4_expert_tensor(bid, "w2", gguf.MODEL_TENSOR.FFN_DOWN_EXP)) consumed.extend(self._write_mxfp4_expert_tensor(bid, "w3", gguf.MODEL_TENSOR.FFN_UP_EXP)) + for bid in range(main_layers, self.block_count): + e_name = f"layers.{bid}.nextn.e_proj.weight" + h_name = f"layers.{bid}.nextn.h_proj.weight" + if e_name not in self.model_tensors and h_name not in self.model_tensors: + continue + if e_name not in self.model_tensors or h_name not in self.model_tensors: + raise KeyError(f"Missing DeepSeek-V4 MTP e/h projection pair for block {bid}") + + e_proj = LazyTorchTensor.to_eager(self.model_tensors[e_name]()) + h_proj = LazyTorchTensor.to_eager(self.model_tensors[h_name]()) + yield (f"layers.{bid}.nextn.eh_proj.weight", torch.cat((e_proj, h_proj), dim=1).contiguous()) + consumed.extend((e_name, h_name)) + for name in consumed: del self.model_tensors[name] @@ -737,6 +855,12 @@ def _map_dsv4_tensor_name(self, name: str, bid: int | None) -> tuple[gguf.MODEL_ "ffn.shared_experts.w1.weight": (gguf.MODEL_TENSOR.FFN_GATE_SHEXP, ".weight"), "ffn.shared_experts.w2.weight": (gguf.MODEL_TENSOR.FFN_DOWN_SHEXP, ".weight"), "ffn.shared_experts.w3.weight": (gguf.MODEL_TENSOR.FFN_UP_SHEXP, ".weight"), + "nextn.eh_proj.weight": (gguf.MODEL_TENSOR.NEXTN_EH_PROJ, ".weight"), + "nextn.enorm.weight": (gguf.MODEL_TENSOR.NEXTN_ENORM, ".weight"), + "nextn.hnorm.weight": (gguf.MODEL_TENSOR.NEXTN_HNORM, ".weight"), + "nextn.shared_head_norm.weight": (gguf.MODEL_TENSOR.NEXTN_SHARED_HEAD_NORM, ".weight"), + "nextn.embed_tokens.weight": (gguf.MODEL_TENSOR.NEXTN_EMBED_TOKENS, ".weight"), + "nextn.shared_head_head.weight": (gguf.MODEL_TENSOR.NEXTN_SHARED_HEAD_HEAD, ".weight"), } tensor_name = match.group(2) @@ -759,10 +883,12 @@ def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iter return [(self._format_dsv4_tensor_name(tensor_key, bid, suffix), data_torch)] def tensor_force_quant(self, name: str, new_name: str, bid: int | None, n_dims: int) -> gguf.GGMLQuantizationType | bool: - del new_name, bid # unused + del bid # unused if name in self._dsv4_fp8_dequantized and n_dims >= 2: return gguf.GGMLQuantizationType.Q8_0 + if new_name.endswith(".nextn.eh_proj.weight"): + return gguf.GGMLQuantizationType.Q8_0 if name in self._dsv4_f32_tensors: return gguf.GGMLQuantizationType.F32 if name in self._dsv4_bf16_tensors and n_dims >= 2: @@ -770,7 +896,122 @@ def tensor_force_quant(self, name: str, new_name: str, bid: int | None, n_dims: return False + def prepare_metadata(self, vocab_only: bool): + from_dir = self.fname_out.is_dir() + super().prepare_metadata(vocab_only=vocab_only) + + if not self.mtp_only or not from_dir: + return + + output_type: str = self.ftype.name.partition("_")[2] + fname_default: str = gguf.naming_convention( + self.metadata.name, self.metadata.basename, self.metadata.finetune, + self.metadata.version, size_label=None, output_type=output_type, model_type=None) + self.fname_out = self.fname_out.parent / f"mtp-{fname_default}.gguf" + def prepare_tensors(self): super().prepare_tensors() self._is_mxfp4 = True self.ftype = gguf.LlamaFileType.MOSTLY_MXFP4_MOE + + +@ModelBase.register("DeepseekV4DSparkModel") +class DeepseekV4DSparkModel(DeepseekV4Model): + model_arch = gguf.MODEL_ARCH.DFLASH + + _DSPARK_ROOT_MAP: dict[str, tuple[gguf.MODEL_TENSOR, str]] = { + "main_proj.weight": (gguf.MODEL_TENSOR.FC, ".weight"), + "main_norm.weight": (gguf.MODEL_TENSOR.ENC_OUTPUT_NORM, ".weight"), + "markov_head.markov_w1.weight": (gguf.MODEL_TENSOR.DSPARK_MARKOV_W1, ".weight"), + "markov_head.markov_w2.weight": (gguf.MODEL_TENSOR.DSPARK_MARKOV_W2, ".weight"), + "confidence_head.proj.weight": (gguf.MODEL_TENSOR.DSPARK_CONF_PROJ, ".weight"), + } + + def __init__(self, *args, **kwargs): + super().__init__(*args, **kwargs) + + self.block_count = 1 + max( + int(match.group(1)) for name in self.model_tensors + if (match := re.match(r"layers\.(\d+)\.", name)) + ) + self.tensor_map = gguf.get_tensor_name_map(self.model_arch, self.block_count) + + self.hparams["compress_ratios"] = [0] * self.block_count + self.hparams["num_hash_layers"] = 0 + + def index_tensors(self, remote_hf_model_id: str | None = None) -> dict[str, Callable[[], Tensor]]: + if remote_hf_model_id is None: + return super().index_tensors() + + with open(self.dir_model / "model.safetensors.index.json", "r", encoding="utf-8") as f: + weight_map = json.load(f)["weight_map"] + + part_names = sorted({ + part_name for name, part_name in weight_map.items() + if name.startswith("mtp.") + }) + tensors: dict[str, Callable[[], Tensor]] = {} + + for part_name in part_names: + from huggingface_hub import hf_hub_download + + logger.info("gguf: caching remote DSpark part '%s'", part_name) + part_path = Path(hf_hub_download(repo_id=remote_hf_model_id, filename=part_name)) + with gguf.utility.SafetensorsLocal(part_path) as model_part: + for name in model_part: + data = model_part[name] + data_gen = lambda data=data: LazyTorchTensor.from_local_tensor(data) # noqa: E731 + if titem := self.filter_tensors((name, data_gen)): + tensor_name, tensor_gen = titem + tensors[tensor_name] = tensor_gen + + return tensors + + @classmethod + def filter_tensors(cls, item: tuple[str, Callable[[], Tensor]]) -> tuple[str, Callable[[], Tensor]] | None: + name, gen = item + if not name.startswith("mtp."): + return None + return super().filter_tensors((cls._rekey_mtp_tensor_name(name), gen)) + + @staticmethod + def _rekey_mtp_tensor_name(name: str) -> str: + match = re.match(r"mtp\.(\d+)\.(.+)$", name) + if match is None: + raise ValueError(f"Unexpected DSpark tensor {name!r}") + + stage, rest = match.group(1), match.group(2) + root_names = ( + "main_proj.scale", + "norm.weight", + "hc_head_fn", + "hc_head_base", + "hc_head_scale", + ) + if rest in DeepseekV4DSparkModel._DSPARK_ROOT_MAP or rest in root_names: + return rest + return f"layers.{stage}.{rest}" + + def _map_dsv4_tensor_name(self, name: str, bid: int | None) -> tuple[gguf.MODEL_TENSOR, str]: + if name in self._DSPARK_ROOT_MAP: + return self._DSPARK_ROOT_MAP[name] + return super()._map_dsv4_tensor_name(name, bid) + + def set_vocab(self): + if self.target_model_dir is None: + raise ValueError("DeepSeek-V4 DSpark requires --target-model-dir with the target tokenizer") + + original_dir = self.dir_model + try: + self.dir_model = self.target_model_dir + super().set_vocab() + finally: + self.dir_model = original_dir + + self.gguf_writer.add_mask_token_id(self.hparams["dspark_noise_token_id"]) + + def set_gguf_parameters(self): + super().set_gguf_parameters() + + self.gguf_writer.add_block_size(self.hparams["dspark_block_size"]) + self.gguf_writer.add_target_layers([layer + 1 for layer in self.hparams["dspark_target_layer_ids"]]) diff --git a/conversion/glm.py b/conversion/glm.py index cc34cddbf843..e28f54574e07 100644 --- a/conversion/glm.py +++ b/conversion/glm.py @@ -206,10 +206,70 @@ def prepare_tensors(self): @ModelBase.register("Glm4MoeLiteForCausalLM") class Glm4MoeLiteModel(DeepseekV2Model): model_arch = gguf.MODEL_ARCH.DEEPSEEK2 + skip_mtp = False + supports_mtp_export = True + _n_main_layers: int | None = None def set_vocab(self): return self._set_vocab_glm() + def __init__(self, *args, **kwargs): + super().__init__(*args, **kwargs) + + num_hidden_layers = self.hparams["num_hidden_layers"] + self.num_nextn_predict_layers = self.hparams.get("num_nextn_predict_layers", 0) + self.skip_mtp = self.no_mtp or self.num_nextn_predict_layers == 0 + + if self.skip_mtp: + self.block_count = num_hidden_layers + else: + self.block_count = num_hidden_layers + self.num_nextn_predict_layers + + self.tensor_map = gguf.get_tensor_name_map(self.model_arch, self.block_count) + + def set_gguf_parameters(self): + super().set_gguf_parameters() + + if self.skip_mtp: + return + + self.gguf_writer.add_nextn_predict_layers(self.num_nextn_predict_layers) + + def index_tensors(self, remote_hf_model_id: str | None = None): + type(self)._n_main_layers = self.hparams["num_hidden_layers"] + return super().index_tensors(remote_hf_model_id=remote_hf_model_id) + + @classmethod + def filter_tensors(cls, item): + if (titem := super().filter_tensors(item)) is None: + return None + name, gen = titem + + if cls._n_main_layers is not None: + match = re.match(r"model\.layers\.(\d+)\.", name) + is_mtp = match is not None and int(match.group(1)) >= cls._n_main_layers + if is_mtp and cls.no_mtp: + return None + if cls.mtp_only and not is_mtp and name not in ( + "model.embed_tokens.weight", "model.norm.weight", "lm_head.weight", + ): + return None + + return name, gen + + def prepare_metadata(self, vocab_only: bool): + from_dir = self.fname_out.is_dir() + super().prepare_metadata(vocab_only=vocab_only) + + if not self.mtp_only or not from_dir: + return + + output_type: str = self.ftype.name.partition("_")[2] + fname_default: str = gguf.naming_convention( + self.metadata.name, self.metadata.basename, self.metadata.finetune, + self.metadata.version, size_label=None, output_type=output_type, model_type=None) + self.fname_out = self.fname_out.parent / f"mtp-{fname_default}.gguf" + @ModelBase.register("GlmMoeDsaForCausalLM") class GlmMoeDsaModel(DeepseekV2Model): diff --git a/conversion/llama.py b/conversion/llama.py index 9b3373f911e9..1aced49c54d2 100644 --- a/conversion/llama.py +++ b/conversion/llama.py @@ -119,7 +119,7 @@ def set_vocab(self): path_tekken_json = self.dir_model / "tekken.json" path_tokenizer_json = self.dir_model / "tokenizer.json" if path_tekken_json.is_file() and not path_tokenizer_json.is_file(): - self._set_vocab_mistral() + return self._set_vocab_mistral() tokenizer_config_file = self.dir_model / 'tokenizer_config.json' if tokenizer_config_file.is_file(): diff --git a/conversion/minicpm.py b/conversion/minicpm.py index e31b26a00808..bf3fa81421bd 100644 --- a/conversion/minicpm.py +++ b/conversion/minicpm.py @@ -137,6 +137,15 @@ def filter_tensors(cls, item: tuple[str, Callable[[], Tensor]]) -> tuple[str, Ca class MiniCPMV4_6VisionModel(MmprojModel): def __init__(self, *args, **kwargs): super().__init__(*args, **kwargs) + self.downsample_mode = self.preprocessor_config.get("downsample_mode", "16x") + if self.downsample_mode not in {"4x", "16x"}: + raise ValueError(f"Unsupported downsample mode: {self.downsample_mode}") + if self.downsample_mode == "4x": + self.model_tensors = { + name: tensor for name, tensor in self.model_tensors.items() + if ".vit_merger." not in name + } + if self.hparams_vision is not None: # In MiniCPM-V 4.6 `vision_config.image_size` (980) describes the SigLIP # positional embedding bucket grid (70 x 70), while the per-slice processing @@ -156,8 +165,8 @@ def set_gguf_parameters(self): # (mapped to PROJECTOR_TYPE_MINICPMV4_6). self.gguf_writer.add_clip_projector_type(gguf.VisionProjectorType.MINICPMV4_6) - # ViT merger 2x2 + final merger 2x2 = 4x spatial merge per dimension; used for slice alignment - self.gguf_writer.add_vision_projector_scale_factor(4) + self.gguf_writer.add_vision_projector_scale_factor( + 2 if self.downsample_mode == "4x" else 4) # borrow wa_layer_indexes for vit_merger insertion point insert_layer_id = int(self.global_config.get( diff --git a/conversion/qwen.py b/conversion/qwen.py index d1127f7431f6..b4ae528bf2d4 100644 --- a/conversion/qwen.py +++ b/conversion/qwen.py @@ -18,7 +18,7 @@ class QwenModel(TextModel): @staticmethod def token_bytes_to_string(b): - from transformers.models.gpt2.tokenization_gpt2 import bytes_to_unicode # ty: ignore[unresolved-import] + from transformers.convert_slow_tokenizer import bytes_to_unicode byte_encoder = bytes_to_unicode() return ''.join([byte_encoder[ord(char)] for char in b.decode('latin-1')]) @@ -268,8 +268,101 @@ def set_vocab(self): super().set_vocab() +class _QwenMtpMixin: + """Shared MTP wiring for Qwen3-Next and Qwen3.5/3.6 text variants. The HF + config carries the MTP block under `mtp_num_hidden_layers` (computed from + the checkpoint when absent, e.g. Qwen3-Next) and the tensors under + `mtp.*`; we extend block_count, emit the nextn metadata key, and remap + `mtp.*` to the standard layer-indexed nextn naming so the existing + tensor_map handles them.""" + + supports_mtp_export = True + hparams: dict[str, Any] + model_arch: gguf.MODEL_ARCH + gguf_writer: gguf.GGUFWriter + block_count: int + tensor_map: gguf.TensorNameMap + no_mtp: bool + mtp_only: bool + _original_block_count: int | None = None + opt_num_mtp_layers: int = 0 + + def __init__(self, *args, **kwargs): + super().__init__(*args, **kwargs) + self.block_count = self.hparams["num_hidden_layers"] + if not self.no_mtp: + n_mtp = self.hparams.get("mtp_num_hidden_layers", 0) + # Qwen-3-Next doesn't include `mtp_num_hidden_layers` in config. + if n_mtp == 0: + assert self.opt_num_mtp_layers != 0 + n_mtp = self.opt_num_mtp_layers + self.block_count += n_mtp + self.tensor_map = gguf.get_tensor_name_map(self.model_arch, self.block_count) + + def index_tensors(self, remote_hf_model_id: str | None = None) -> dict[str, Callable[[], Tensor]]: + hparams = {**self.hparams, **self.hparams.get("text_config", {})} + key = next((k for k in ["n_layers", "num_hidden_layers", "n_layer", "num_layers"] if k in hparams), None) + type(self)._original_block_count = hparams.get(key) + type(self).opt_num_mtp_layers = 0 + return super().index_tensors(remote_hf_model_id=remote_hf_model_id) # ty: ignore[unresolved-attribute] + + @classmethod + def filter_tensors(cls, item): + assert cls._original_block_count is not None + # TODO: change TextModel to super() + if (titem := TextModel.filter_tensors(item)) is None: + return None + name, gen = titem + if name.startswith("model.mtp."): + name = name.replace("model.", "", 1) + if name.startswith("mtp."): + if cls.no_mtp: + return None + remapper = { + "fc": "eh_proj", + "pre_fc_norm_embedding": "enorm", + "pre_fc_norm_hidden": "hnorm", + "norm": "shared_head.norm", + } + parts = name.split(".", 3) + if len(parts) == 4 and parts[1] == "layers" and parts[2].isdecimal(): + mtp_idx = int(parts[2]) + name = f"model.layers.{cls._original_block_count + mtp_idx}.{parts[3]}" + cls.opt_num_mtp_layers = max(cls.opt_num_mtp_layers, mtp_idx + 1) + elif len(parts) == 3 and parts[1] in remapper: + name = f"model.layers.{cls._original_block_count}.{remapper[parts[1]]}.{parts[2]}" + elif cls.mtp_only: + keep = name in ( + "model.embed_tokens.weight", "model.norm.weight", "lm_head.weight", + "embed_tokens.weight", "norm.weight", + ) + if not keep: + return None + return name, gen + + def set_gguf_parameters(self): + super().set_gguf_parameters() # ty: ignore[unresolved-attribute] + if self.no_mtp: + return + if (n := self.block_count - self.hparams["num_hidden_layers"]) > 0: + self.gguf_writer.add_nextn_predict_layers(n) + + def prepare_metadata(self, vocab_only: bool): + from_dir = self.fname_out.is_dir() + super().prepare_metadata(vocab_only=vocab_only) # ty: ignore[unresolved-attribute] + + if not self.mtp_only or not from_dir: + return + + output_type: str = self.ftype.name.partition("_")[2] # pyright: ignore[reportAttributeAccessIssue] # ty: ignore[unresolved-attribute] + fname_default: str = gguf.naming_convention( + self.metadata.name, self.metadata.basename, self.metadata.finetune, # pyright: ignore[reportAttributeAccessIssue] # ty: ignore[unresolved-attribute] + self.metadata.version, size_label=None, output_type=output_type, model_type=None) # pyright: ignore[reportAttributeAccessIssue] # ty: ignore[unresolved-attribute] + self.fname_out = self.fname_out.parent / f"mtp-{fname_default}.gguf" + + @ModelBase.register("Qwen3NextForCausalLM") -class Qwen3NextModel(Qwen2MoeModel): +class Qwen3NextModel(_QwenMtpMixin, Qwen2MoeModel): model_arch = gguf.MODEL_ARCH.QWEN3NEXT def set_gguf_parameters(self): @@ -284,16 +377,6 @@ def set_gguf_parameters(self): rope_dim = self.hparams["hidden_size"] // self.hparams["num_attention_heads"] self.gguf_writer.add_rope_dimension_count(int(rope_dim * self.rope_parameters.get("partial_rotary_factor", 0.25))) - @classmethod - def filter_tensors(cls, item: tuple[str, Callable[[], Tensor]]) -> tuple[str, Callable[[], Tensor]] | None: - name, gen = item - - if name.startswith("mtp"): - # ignore MTP layers for now - return None - - return super().filter_tensors(item) - def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]: if name.endswith(".A_log"): data_torch = -torch.exp(data_torch) @@ -536,97 +619,13 @@ def set_gguf_parameters(self): self.gguf_writer.add_rope_dimension_sections(self._QWEN35_DEFAULT_MROPE_SECTION) -class _Qwen35MtpMixin: - """Shared MTP wiring for Qwen3.5/3.6 text variants. The HF config carries - the MTP block under `mtp_num_hidden_layers` and the tensors under - `mtp.*`; we extend block_count, emit the nextn metadata key, and remap - `mtp.*` to the standard layer-indexed nextn naming so the existing - tensor_map handles them.""" - - supports_mtp_export = True - hparams: dict[str, Any] - model_arch: gguf.MODEL_ARCH - gguf_writer: gguf.GGUFWriter - block_count: int - tensor_map: gguf.TensorNameMap - no_mtp: bool - mtp_only: bool - _original_block_count: int | None = None - - def __init__(self, *args, **kwargs): - super().__init__(*args, **kwargs) - self.block_count = self.hparams["num_hidden_layers"] - if not self.no_mtp: - self.block_count += self.hparams.get("mtp_num_hidden_layers", 0) - self.tensor_map = gguf.get_tensor_name_map(self.model_arch, self.block_count) - - def index_tensors(self, remote_hf_model_id: str | None = None) -> dict[str, Callable[[], Tensor]]: - hparams = {**self.hparams, **self.hparams.get("text_config", {})} - key = next((k for k in ["n_layers", "num_hidden_layers", "n_layer", "num_layers"] if k in hparams), None) - type(self)._original_block_count = hparams.get(key) - return super().index_tensors(remote_hf_model_id=remote_hf_model_id) # ty: ignore[unresolved-attribute] - - @classmethod - def filter_tensors(cls, item): - assert cls._original_block_count is not None - # TODO: change TextModel to super() - if (titem := TextModel.filter_tensors(item)) is None: - return None - name, gen = titem - if name.startswith("model.mtp."): - name = name.replace("model.", "", 1) - if name.startswith("mtp."): - if cls.no_mtp: - return None - remapper = { - "fc": "eh_proj", - "pre_fc_norm_embedding": "enorm", - "pre_fc_norm_hidden": "hnorm", - "norm": "shared_head.norm", - } - parts = name.split(".", 3) - if len(parts) == 4 and parts[1] == "layers" and parts[2].isdecimal(): - mtp_idx = int(parts[2]) - name = f"model.layers.{cls._original_block_count + mtp_idx}.{parts[3]}" - elif len(parts) == 3 and parts[1] in remapper: - name = f"model.layers.{cls._original_block_count}.{remapper[parts[1]]}.{parts[2]}" - elif cls.mtp_only: - keep = name in ( - "model.embed_tokens.weight", "model.norm.weight", "lm_head.weight", - "embed_tokens.weight", "norm.weight", - ) - if not keep: - return None - return name, gen - - def set_gguf_parameters(self): - super().set_gguf_parameters() # ty: ignore[unresolved-attribute] - if self.no_mtp: - return - if (n := self.hparams.get("mtp_num_hidden_layers", 0)) > 0: - self.gguf_writer.add_nextn_predict_layers(n) - - def prepare_metadata(self, vocab_only: bool): - from_dir = self.fname_out.is_dir() - super().prepare_metadata(vocab_only=vocab_only) # ty: ignore[unresolved-attribute] - - if not self.mtp_only or not from_dir: - return - - output_type: str = self.ftype.name.partition("_")[2] # pyright: ignore[reportAttributeAccessIssue] # ty: ignore[unresolved-attribute] - fname_default: str = gguf.naming_convention( - self.metadata.name, self.metadata.basename, self.metadata.finetune, # pyright: ignore[reportAttributeAccessIssue] # ty: ignore[unresolved-attribute] - self.metadata.version, size_label=None, output_type=output_type, model_type=None) # pyright: ignore[reportAttributeAccessIssue] # ty: ignore[unresolved-attribute] - self.fname_out = self.fname_out.parent / f"mtp-{fname_default}.gguf" - - @ModelBase.register("Qwen3_5ForConditionalGeneration", "Qwen3_5ForCausalLM") -class Qwen3_5TextModel(_Qwen35MtpMixin, _Qwen35MRopeMixin, _LinearAttentionVReorderBase): +class Qwen3_5TextModel(_Qwen35MRopeMixin, _LinearAttentionVReorderBase): model_arch = gguf.MODEL_ARCH.QWEN35 @ModelBase.register("Qwen3_5MoeForConditionalGeneration", "Qwen3_5MoeForCausalLM") -class Qwen3_5MoeTextModel(_Qwen35MtpMixin, _Qwen35MRopeMixin, _LinearAttentionVReorderBase): +class Qwen3_5MoeTextModel(_Qwen35MRopeMixin, _LinearAttentionVReorderBase): model_arch = gguf.MODEL_ARCH.QWEN35MOE diff --git a/conversion/qwen3tts.py b/conversion/qwen3tts.py new file mode 100644 index 000000000000..d21a5059517a --- /dev/null +++ b/conversion/qwen3tts.py @@ -0,0 +1,471 @@ +from __future__ import annotations + +import json +from pathlib import Path +from typing import Any, Callable, Iterable, TYPE_CHECKING + +import torch +import torch.nn.functional as F + +if TYPE_CHECKING: + from torch import Tensor + +from .base import ModelBase, MmprojModel, TextModel, gguf + +# Tricks being used to support this model via existing llama.cpp code paths: +# - Text projection MLP is folded into the embedding table +# - codec_embedding is concat to the text embedding table, vocab is extended +# example: codec_bos_id(2149) --> "<|codec_bos|>" +# codec_eos_token_id(2150) --> "<|codec_eos_token|>" +# codec_language_id.chinese(2055) --> "<|codec_language_chinese|>" +# other rows --> "<|codec_0|>", "<|codec_1|>", ..., "<|codec_1023|>" +# - output tensor codec_head is smaller than vocab, so logits will be padded at inference time +# - suppress_tokens is used to limit the backbone to only sample either semantic or EOS (stop) token + +# pipeline stage mapping: +# speaker reference encoder --> mapped to normal mtmd audio encoder +# backbone --> mapped to normal libllama text model (autoregressive) +# code_predictor --> MTMD_GEN_PROCESS_TYPE_GEN_CODE +# code2wav --> MTMD_GEN_PROCESS_TYPE_GEN_WAV + +# torch activation functions used by Qwen3TTSTalkerResizeMLP (config's hidden_act) +_ACT2FN = { + "silu": F.silu, + "gelu": F.gelu, + "relu": F.relu, +} + + +@ModelBase.register("Qwen3TTSForConditionalGeneration") +class Qwen3TTSTalkerModel(TextModel): + model_arch = gguf.MODEL_ARCH.QWEN3TTS + + _TEXT_PROJ_KEYS = ( + "model.text_embedding.weight", + "text_projection.linear_fc1.weight", + "text_projection.linear_fc1.bias", + "text_projection.linear_fc2.weight", + "text_projection.linear_fc2.bias", + ) + + _text_proj_buffer: dict[str, Tensor] + _folded_text_embed: Tensor | None + _codec_embed: Tensor | None + + def __init__(self, dir_model: Path, *args, **kwargs): + hparams = kwargs.pop("hparams", None) + if hparams is None: + hparams = ModelBase.load_hparams(dir_model, is_mistral_format=False) + raw_talker_config = dict(hparams["talker_config"]) + self._talker_config = raw_talker_config + self.n_codec_vocab = raw_talker_config["vocab_size"] + talker_config = dict(raw_talker_config) + talker_config["vocab_size"] = talker_config["text_vocab_size"] + hparams["text_config"] = talker_config + super().__init__(dir_model, *args, hparams=hparams, **kwargs) + self._text_proj_buffer = {} + self._folded_text_embed = None + self._codec_embed = None + + def _codec_token_names(self) -> list[str]: + # start every row with a generic name, then override the ones with a + # known meaning (bos/eos/language/etc, derived from the *_id fields + # of talker_config) with a more descriptive one + names = [f"<|codec_{i}|>" for i in range(self.n_codec_vocab)] + for key, val in self._talker_config.items(): + if not key.endswith("_id"): + continue + prefix = key[:-len("_id")] + if isinstance(val, int): + names[val] = f"<|{prefix}|>" + elif isinstance(val, dict): + for subkey, subval in val.items(): + names[subval] = f"<|{prefix}_{subkey}|>" + return names + + def set_vocab(self): + codec_tokens = self._codec_token_names() + codec_toktypes = [gguf.TokenType.CONTROL] * len(codec_tokens) + + try: + tokens, scores, toktypes = self._create_vocab_sentencepiece() + self.gguf_writer.add_tokenizer_model("llama") + self.gguf_writer.add_tokenizer_pre("default") + tokens += [t.encode("utf-8") for t in codec_tokens] + scores += [0.0] * len(codec_tokens) + toktypes += codec_toktypes + self.gguf_writer.add_token_list(tokens) + self.gguf_writer.add_token_scores(scores) + self.gguf_writer.add_token_types(toktypes) + special_vocab = gguf.SpecialVocab(self.dir_model, n_vocab=len(tokens)) + special_vocab.add_to_gguf(self.gguf_writer) + return + except FileNotFoundError: + pass + + tokens, toktypes, tokpre = self.get_vocab_base() + tokens += codec_tokens + toktypes += codec_toktypes + self.gguf_writer.add_tokenizer_model("gpt2") + self.gguf_writer.add_tokenizer_pre(tokpre) + self.gguf_writer.add_token_list(tokens) + self.gguf_writer.add_token_types(toktypes) + + special_vocab = gguf.SpecialVocab(self.dir_model, load_merges=True) + special_vocab.add_to_gguf(self.gguf_writer) + + # make sure that the model has no chat template, so chat will be disabled + self.gguf_writer.add_chat_template(None) + + def set_gguf_parameters(self): + super().set_gguf_parameters() + + # note: final vocab layout is [text_vocab | codec_vocab], with text_vocab is actually padded with -inf in cgraph + # for codec_vocab, only first 2048 rows can be sampled for semantic code + # plus codec_eos_token_id that used for signaling end of generation + # ref: https://github.com/QwenLM/Qwen3-TTS/blob/022e286b98fbec7e1e916cb940cdf532cd9f488e/qwen_tts/core/models/modeling_qwen3_tts.py#L2059-L2063 + + vocab_size = self.hparams["vocab_size"] + self.n_codec_vocab + codec_eos_token_id = self.hparams["vocab_size"] + self._talker_config["codec_eos_token_id"] + self.gguf_writer.add_suppress_tokens([ + i for i in range(vocab_size - 1024, vocab_size) + if i != codec_eos_token_id + ]) + self.gguf_writer.add_eos_token_id(codec_eos_token_id) + self.gguf_writer.add_add_eos_token(False) + + @classmethod + def filter_tensors(cls, item: tuple[str, Callable[[], Tensor]]) -> tuple[str, Callable[[], Tensor]] | None: + name, gen = item + + if not name.startswith("talker.") or name.startswith("talker.code_predictor."): + return None + + name = name[len("talker."):] + return super().filter_tensors((name, gen)) + + def _maybe_emit_token_embd(self) -> Iterable[tuple[str, Tensor]]: + if self._folded_text_embed is None or self._codec_embed is None: + return + combined = torch.cat([self._folded_text_embed, self._codec_embed], dim=0) + yield (self.format_tensor_name(gguf.MODEL_TENSOR.TOKEN_EMBD), combined) + + def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]: + # codec_embedding rows are appended after the text vocab, extending the embedding table + if name == "model.codec_embedding.weight": + self._codec_embed = data_torch + yield from self._maybe_emit_token_embd() + return + + # codec_head is the output head for the (smaller) codec vocab; logits get padded to + # the extended vocab size at inference time + if name == "codec_head.weight": + yield (self.format_tensor_name(gguf.MODEL_TENSOR.OUTPUT), data_torch) + return + + if name in self._TEXT_PROJ_KEYS: + self._text_proj_buffer[name] = data_torch + if len(self._text_proj_buffer) < len(self._TEXT_PROJ_KEYS): + return + + # fold MLP into the embedding table at conversion time, MLP won't be used at inference time anyway + act_fn = _ACT2FN[self.hparams["hidden_act"]] + embed = self._text_proj_buffer["model.text_embedding.weight"] + hidden = act_fn(F.linear(embed, + self._text_proj_buffer["text_projection.linear_fc1.weight"], + self._text_proj_buffer["text_projection.linear_fc1.bias"])) + folded = F.linear(hidden, + self._text_proj_buffer["text_projection.linear_fc2.weight"], + self._text_proj_buffer["text_projection.linear_fc2.bias"]) + self._folded_text_embed = folded + yield from self._maybe_emit_token_embd() + return + + yield from super().modify_tensors(data_torch, name, bid) + + +@ModelBase.register("Qwen3TTSForConditionalGeneration") +class Qwen3TTSSpeakerEncoderModel(MmprojModel): + has_vision_encoder = False + has_audio_encoder = True + + # talker.code_predictor.model.layers.{bid}. -> A_GEN_CODE_* + # bypass tensor_mapping.py for now to make it simple + _CODE_LAYER_TENSOR_MAP = { + "input_layernorm": gguf.MODEL_TENSOR.A_GEN_CODE_ATTN_NORM, + "self_attn.q_proj": gguf.MODEL_TENSOR.A_GEN_CODE_ATTN_Q, + "self_attn.q_norm": gguf.MODEL_TENSOR.A_GEN_CODE_ATTN_Q_NORM, + "self_attn.k_proj": gguf.MODEL_TENSOR.A_GEN_CODE_ATTN_K, + "self_attn.k_norm": gguf.MODEL_TENSOR.A_GEN_CODE_ATTN_K_NORM, + "self_attn.v_proj": gguf.MODEL_TENSOR.A_GEN_CODE_ATTN_V, + "self_attn.o_proj": gguf.MODEL_TENSOR.A_GEN_CODE_ATTN_OUT, + "post_attention_layernorm": gguf.MODEL_TENSOR.A_GEN_CODE_FFN_NORM, + "mlp.gate_proj": gguf.MODEL_TENSOR.A_GEN_CODE_FFN_GATE, + "mlp.up_proj": gguf.MODEL_TENSOR.A_GEN_CODE_FFN_UP, + "mlp.down_proj": gguf.MODEL_TENSOR.A_GEN_CODE_FFN_DOWN, + } + + # note: codebook pages will be stacked to 3D + _CODE_GEN_N_CODEBOOKS = 15 + _code_embed_buffer: dict[int, Tensor] = {} + _code_head_buffer: dict[int, Tensor] = {} + _wav_config_cache: dict[str, Any] | None = None + + def __init__(self, dir_model: Path, *args, **kwargs): + hparams = kwargs.pop("hparams", None) + if hparams is None: + hparams = ModelBase.load_hparams(dir_model, is_mistral_format=False) + hparams["text_config"] = {"hidden_size": hparams["talker_config"]["hidden_size"]} + # ECAPA-TDNN has a fixed 4-stage backbone, but MmprojModel.__init__ needs a n_block_keys + hparams["speaker_encoder_config"]["n_layers"] = 4 + super().__init__(dir_model, *args, hparams=hparams, **kwargs) + self._wav_config_cache = None + + def get_audio_config(self) -> dict[str, Any] | None: + return self.global_config.get("speaker_encoder_config") + + def set_gguf_parameters(self): + self.gguf_writer.add_file_type(self.ftype) + self.gguf_writer.add_clip_has_audio_encoder(True) + self.gguf_writer.add_clip_audio_projector_type(gguf.VisionProjectorType.QWEN3TTS_SPKENC) + + # handle speaker encoder config + self.gguf_writer.add_audio_projection_dim(self.n_embd_text) + # mel_spectrogram() front-end: sr=24000, n_fft=1024, hop=256, n_mels=128, fmin=0, fmax=12000 (=sr/2, the clip.cpp default) + self.gguf_writer.add_audio_num_mel_bins(128) + # 3 SE-Res2Net stages; the stem conv, mfa, asp and fc are not counted here + self.gguf_writer.add_audio_block_count(3) + # ECAPA-TDNN has no attention/FFN, these are dummy to allow clip.cpp to load it + self.gguf_writer.add_audio_embedding_length(1536) + self.gguf_writer.add_audio_head_count(1) + self.gguf_writer.add_audio_feed_forward_length(1536) + self.gguf_writer.add_audio_attention_layernorm_eps(1e-5) + + # handle code predictor config + self.gguf_writer.add_clip_has_gen_audio_encoder(True) + self.gguf_writer.add_clip_gen_audio_projector_type(gguf.VisionProjectorType.QWEN3TTS_GEN) + code_predictor_config = self.global_config["talker_config"]["code_predictor_config"] + self.gguf_writer.add_gen_audio_projection_dim(self.n_embd_text) + self.gguf_writer.add_gen_audio_embedding_length(code_predictor_config["hidden_size"]) + self.gguf_writer.add_gen_audio_feed_forward_length(code_predictor_config["intermediate_size"]) + self.gguf_writer.add_gen_audio_block_count(code_predictor_config["num_hidden_layers"]) + self.gguf_writer.add_gen_audio_head_count(code_predictor_config["num_attention_heads"]) + self.gguf_writer.add_gen_audio_head_count_kv(code_predictor_config["num_key_value_heads"]) + self.gguf_writer.add_gen_audio_attention_layernorm_eps(code_predictor_config["rms_norm_eps"]) + # note: code2wav hparams are hardcoded on the mtmd/clip.cpp side for now, not written here + + def _wav_decoder_config(self) -> dict[str, Any] | None: + # code2wav has its own config.json, inside the speech_tokenizer dir + if self._wav_config_cache is None: + path = self.dir_model / "speech_tokenizer" / "config.json" + with open(path, "r", encoding="utf-8") as f: + cfg = json.load(f) + self._wav_config_cache = cfg["decoder_config"] + return self._wav_config_cache + + def tensor_force_quant(self, name, new_name, bid, n_dims): + # conv1d/conv1d_dw kernels must be F16, ggml_conv_1d(_dw) has no BF16 path + if new_name.endswith(".weight") and ( + new_name in ("a.gen.wav.pre_conv.weight", "a.gen.wav.dac.entry.weight", "a.gen.wav.dac.post_conv.weight") + or (".up.blk." in new_name and new_name.endswith(".dwconv.weight")) + or (".dac.blk." in new_name and (new_name.endswith(".conv1.weight") or new_name.endswith(".conv2.weight"))) + ): + return gguf.GGMLQuantizationType.F16 + # ConvTranspose1d kernels: only F16/F32 are implemented, no BF16 + if new_name.endswith(".conv.weight") and (".up.blk." in new_name or ".dac.blk." in new_name): + return gguf.GGMLQuantizationType.F32 + return super().tensor_force_quant(name, new_name, bid, n_dims) + + @classmethod + def filter_tensors(cls, item: tuple[str, Callable[[], Tensor]]) -> tuple[str, Callable[[], Tensor]] | None: + name, gen = item + + if not ( + name.startswith("speaker_encoder.") + or name.startswith("talker.code_predictor.") + or name == "talker.model.codec_embedding.weight" + ): + return None + + return super().filter_tensors((name, gen)) + + def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]: + # code2wav tensors are already named by generate_extra_tensors(), pass them through + if name.startswith("a.gen.wav."): + yield (name, data_torch) + return + + # codebook-0 embedding, fed back to the talker backbone (codebooks 1-15 live in code_predictor) + if name == "talker.model.codec_embedding.weight": + yield (self.format_tensor_name(gguf.MODEL_TENSOR.A_GEN_CODE_OUT_EMBD), data_torch) + return + + if name == "talker.code_predictor.model.norm.weight": + yield (self.format_tensor_name(gguf.MODEL_TENSOR.A_GEN_CODE_OUTPUT_NORM), data_torch) + return + + if name.startswith("talker.code_predictor.small_to_mtp_projection."): + suffix = "." + name.rsplit(".", 1)[1] + yield (self.format_tensor_name(gguf.MODEL_TENSOR.A_GEN_CODE_PROJ_IN, suffix=suffix), data_torch) + return + + if name.startswith("talker.code_predictor.model.codec_embedding."): + idx = int(name.split("codec_embedding.")[1].split(".")[0]) + self._code_embed_buffer[idx] = data_torch + if len(self._code_embed_buffer) < self._CODE_GEN_N_CODEBOOKS: + return + stacked = torch.stack([self._code_embed_buffer.pop(i) for i in range(self._CODE_GEN_N_CODEBOOKS)], dim=0) + yield (self.format_tensor_name(gguf.MODEL_TENSOR.A_GEN_CODE_EMBD), stacked) + return + + if name.startswith("talker.code_predictor.lm_head."): + idx = int(name.split("lm_head.")[1].split(".")[0]) + self._code_head_buffer[idx] = data_torch + if len(self._code_head_buffer) < self._CODE_GEN_N_CODEBOOKS: + return + stacked = torch.stack([self._code_head_buffer.pop(i) for i in range(self._CODE_GEN_N_CODEBOOKS)], dim=0) + yield (self.format_tensor_name(gguf.MODEL_TENSOR.A_GEN_CODE_HEAD), stacked) + return + + if name.startswith("talker.code_predictor.model.layers."): + rest = name.split("model.layers.")[1] # "{bid}..weight" + _, key_with_suffix = rest.split(".", 1) # ".weight" + key = key_with_suffix.rsplit(".", 1)[0] # "" + tensor = self._CODE_LAYER_TENSOR_MAP.get(key) + if tensor is not None: + yield (self.format_tensor_name(tensor, bid), data_torch) + return + + if "res2net_block.blocks." in name: + assert bid is not None # the outer stage index, picked up from the tensor name automatically + xid = int(name.split("res2net_block.blocks.")[1].split(".")[0]) + suffix = "." + name.rsplit(".", 1)[1] + new_name = gguf.TENSOR_NAMES[gguf.MODEL_TENSOR.A_ENC_CONV_RES2].format(bid=bid, xid=xid) + suffix + yield (new_name, data_torch) + return + + yield from super().modify_tensors(data_torch, name, bid) + + def generate_extra_tensors(self) -> Iterable[tuple[str, Tensor]]: + yield from self._generate_code2wav_tensors() + + def _generate_code2wav_tensors(self) -> Iterable[tuple[str, Tensor]]: + # code2wav weights live in speech_tokenizer/model.safetensors, not the main safetensors + from safetensors.torch import load_file + + wav_config = self._wav_decoder_config() + state_dict = load_file(self.dir_model / "speech_tokenizer" / "model.safetensors") + + def get(name: str) -> Tensor: + return state_dict[name] + + def snake_fold(alpha: Tensor, beta: Tensor) -> tuple[Tensor, Tensor]: + # fold SnakeBeta's exp()/reciprocal here, so the graph is only mul/sin/sqr/mul/add + return torch.exp(alpha), 1.0 / (torch.exp(beta) + 1e-9) + + def rvq_codebook(prefix: str, n_layers: int) -> Tensor: + # checkpoint has EMA accumulators, so codebook[i] = embedding_sum[i] / cluster_usage[i] + books = [] + for i in range(n_layers): + embedding_sum = get(f"{prefix}.vq.layers.{i}._codebook.embedding_sum") + cluster_usage = get(f"{prefix}.vq.layers.{i}._codebook.cluster_usage") + books.append(embedding_sum / cluster_usage.clamp_min(1e-5).unsqueeze(-1)) + return torch.stack(books, dim=0) if n_layers > 1 else books[0] + + T = gguf.MODEL_TENSOR + + # --- quantizer: RVQ codebook decode --- + yield (self.format_tensor_name(T.A_GEN_WAV_QUANT_FIRST_IN), get("decoder.quantizer.rvq_first.input_proj.weight").squeeze(-1)) + yield (self.format_tensor_name(T.A_GEN_WAV_QUANT_FIRST_OUT), get("decoder.quantizer.rvq_first.output_proj.weight").squeeze(-1)) + yield (self.format_tensor_name(T.A_GEN_WAV_QUANT_FIRST_CB), rvq_codebook("decoder.quantizer.rvq_first", 1)) + yield (self.format_tensor_name(T.A_GEN_WAV_QUANT_REST_IN), get("decoder.quantizer.rvq_rest.input_proj.weight").squeeze(-1)) + yield (self.format_tensor_name(T.A_GEN_WAV_QUANT_REST_OUT), get("decoder.quantizer.rvq_rest.output_proj.weight").squeeze(-1)) + yield (self.format_tensor_name(T.A_GEN_WAV_QUANT_REST_CB), rvq_codebook("decoder.quantizer.rvq_rest", self._CODE_GEN_N_CODEBOOKS)) + + # --- pre_conv --- + yield (self.format_tensor_name(T.A_GEN_WAV_PRE_CONV, suffix=".weight"), get("decoder.pre_conv.conv.weight")) + yield (self.format_tensor_name(T.A_GEN_WAV_PRE_CONV, suffix=".bias"), get("decoder.pre_conv.conv.bias")) + + # --- pre_transformer --- + yield (self.format_tensor_name(T.A_GEN_WAV_TFM_IN_PROJ, suffix=".weight"), get("decoder.pre_transformer.input_proj.weight")) + yield (self.format_tensor_name(T.A_GEN_WAV_TFM_IN_PROJ, suffix=".bias"), get("decoder.pre_transformer.input_proj.bias")) + yield (self.format_tensor_name(T.A_GEN_WAV_TFM_OUT_PROJ, suffix=".weight"), get("decoder.pre_transformer.output_proj.weight")) + yield (self.format_tensor_name(T.A_GEN_WAV_TFM_OUT_PROJ, suffix=".bias"), get("decoder.pre_transformer.output_proj.bias")) + yield (self.format_tensor_name(T.A_GEN_WAV_TFM_OUTPUT_NORM), get("decoder.pre_transformer.norm.weight")) + + tfm_layer_map = { + "input_layernorm.weight": T.A_GEN_WAV_TFM_ATTN_NORM, + "self_attn.q_proj.weight": T.A_GEN_WAV_TFM_ATTN_Q, + "self_attn.k_proj.weight": T.A_GEN_WAV_TFM_ATTN_K, + "self_attn.v_proj.weight": T.A_GEN_WAV_TFM_ATTN_V, + "self_attn.o_proj.weight": T.A_GEN_WAV_TFM_ATTN_OUT, + "self_attn_layer_scale.scale": T.A_GEN_WAV_TFM_ATTN_SCALE, + "post_attention_layernorm.weight": T.A_GEN_WAV_TFM_FFN_NORM, + "mlp.gate_proj.weight": T.A_GEN_WAV_TFM_FFN_GATE, + "mlp.up_proj.weight": T.A_GEN_WAV_TFM_FFN_UP, + "mlp.down_proj.weight": T.A_GEN_WAV_TFM_FFN_DOWN, + "mlp_layer_scale.scale": T.A_GEN_WAV_TFM_FFN_SCALE, + } + assert wav_config is not None + for bid in range(wav_config["num_hidden_layers"]): + for key, tensor_id in tfm_layer_map.items(): + yield (self.format_tensor_name(tensor_id, bid), get(f"decoder.pre_transformer.layers.{bid}.{key}")) + + # --- upsample: 2x (causal ConvTranspose1d + ConvNeXt block) --- + up_map = { + "0.conv.weight": (T.A_GEN_WAV_UP_CONV, ".weight"), + "0.conv.bias": (T.A_GEN_WAV_UP_CONV, ".bias"), + "1.dwconv.conv.weight": (T.A_GEN_WAV_UP_DWCONV, ".weight"), + "1.dwconv.conv.bias": (T.A_GEN_WAV_UP_DWCONV, ".bias"), + "1.norm.weight": (T.A_GEN_WAV_UP_NORM, ".weight"), + "1.norm.bias": (T.A_GEN_WAV_UP_NORM, ".bias"), + "1.pwconv1.weight": (T.A_GEN_WAV_UP_PW1, ".weight"), + "1.pwconv1.bias": (T.A_GEN_WAV_UP_PW1, ".bias"), + "1.pwconv2.weight": (T.A_GEN_WAV_UP_PW2, ".weight"), + "1.pwconv2.bias": (T.A_GEN_WAV_UP_PW2, ".bias"), + "1.gamma": (T.A_GEN_WAV_UP_GAMMA, ""), + } + for bid in range(len(wav_config["upsampling_ratios"])): + for key, (tensor_id, suffix) in up_map.items(): + yield (self.format_tensor_name(tensor_id, bid, suffix=suffix), get(f"decoder.upsample.{bid}.{key}")) + + # --- DAC decoder --- + yield (self.format_tensor_name(T.A_GEN_WAV_DAC_ENTRY, suffix=".weight"), get("decoder.decoder.0.conv.weight")) + yield (self.format_tensor_name(T.A_GEN_WAV_DAC_ENTRY, suffix=".bias"), get("decoder.decoder.0.conv.bias")) + + n_dac_blocks = len(wav_config["upsample_rates"]) + for bid in range(n_dac_blocks): + py = bid + 1 # decoder.decoder.0 is the entry conv, blocks start at 1 + + a, b = snake_fold(get(f"decoder.decoder.{py}.block.0.alpha"), get(f"decoder.decoder.{py}.block.0.beta")) + yield (self.format_tensor_name(T.A_GEN_WAV_DAC_UP_SNAKE, bid, suffix=".alpha"), a) + yield (self.format_tensor_name(T.A_GEN_WAV_DAC_UP_SNAKE, bid, suffix=".beta"), b) + yield (self.format_tensor_name(T.A_GEN_WAV_DAC_UP_CONV, bid, suffix=".weight"), get(f"decoder.decoder.{py}.block.1.conv.weight")) + yield (self.format_tensor_name(T.A_GEN_WAV_DAC_UP_CONV, bid, suffix=".bias"), get(f"decoder.decoder.{py}.block.1.conv.bias")) + + for xid in range(3): + ridx = xid + 2 # block.2/3/4 are the 3 residual units + + a1, b1 = snake_fold(get(f"decoder.decoder.{py}.block.{ridx}.act1.alpha"), get(f"decoder.decoder.{py}.block.{ridx}.act1.beta")) + name1 = gguf.TENSOR_NAMES[T.A_GEN_WAV_DAC_RES_ACT1].format(bid=bid, xid=xid) + yield (name1 + ".alpha", a1) + yield (name1 + ".beta", b1) + + name_conv1 = gguf.TENSOR_NAMES[T.A_GEN_WAV_DAC_RES_CONV1].format(bid=bid, xid=xid) + yield (name_conv1 + ".weight", get(f"decoder.decoder.{py}.block.{ridx}.conv1.conv.weight")) + yield (name_conv1 + ".bias", get(f"decoder.decoder.{py}.block.{ridx}.conv1.conv.bias")) + + a2, b2 = snake_fold(get(f"decoder.decoder.{py}.block.{ridx}.act2.alpha"), get(f"decoder.decoder.{py}.block.{ridx}.act2.beta")) + name2 = gguf.TENSOR_NAMES[T.A_GEN_WAV_DAC_RES_ACT2].format(bid=bid, xid=xid) + yield (name2 + ".alpha", a2) + yield (name2 + ".beta", b2) + + name_conv2 = gguf.TENSOR_NAMES[T.A_GEN_WAV_DAC_RES_CONV2].format(bid=bid, xid=xid) + yield (name_conv2 + ".weight", get(f"decoder.decoder.{py}.block.{ridx}.conv2.conv.weight")) + yield (name_conv2 + ".bias", get(f"decoder.decoder.{py}.block.{ridx}.conv2.conv.bias")) + + a5, b5 = snake_fold(get("decoder.decoder.5.alpha"), get("decoder.decoder.5.beta")) + yield (self.format_tensor_name(T.A_GEN_WAV_DAC_POST_SNAKE, suffix=".alpha"), a5) + yield (self.format_tensor_name(T.A_GEN_WAV_DAC_POST_SNAKE, suffix=".beta"), b5) + yield (self.format_tensor_name(T.A_GEN_WAV_DAC_POST_CONV, suffix=".weight"), get("decoder.decoder.6.conv.weight")) + yield (self.format_tensor_name(T.A_GEN_WAV_DAC_POST_CONV, suffix=".bias"), get("decoder.decoder.6.conv.bias")) diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py index 2c5e62a16fbe..78ad26c65630 100755 --- a/convert_hf_to_gguf.py +++ b/convert_hf_to_gguf.py @@ -122,8 +122,12 @@ def parse_args() -> argparse.Namespace: help="Export only the multi-token prediction (MTP) head as a separate GGUF, suitable for use as a speculative draft. An 'mtp-' prefix will be added to the output file name.", ) parser.add_argument( - "--no-mtp", action="store_true", - help="Exclude the multi-token prediction (MTP) head from the converted GGUF. Pair with --mtp on a second run to publish trunk and MTP as two files. Note: the split form duplicates embeddings, but even though the bundled default is more space-efficient overall, this allows differing quantization which may be more performant.", + "--no-nextn", "--no-mtp", dest="no_mtp", action="store_true", + help="Exclude NextN speculative draft tensors from the converted GGUF. Pair with --mtp or --dspark on a second run to publish target and draft as two files.", + ) + parser.add_argument( + "--dspark", action="store_true", + help="Export only the DeepSeek-V4 DSpark draft tensors as a separate GGUF.", ) parser.add_argument( "--mistral-format", action="store_true", @@ -254,13 +258,20 @@ def main() -> None: from conversion.mistral import MistralModel model_class = MistralModel - if args.mtp and args.no_mtp: - logger.error("--mtp and --no-mtp are mutually exclusive") + if sum((args.mtp, args.no_mtp, args.dspark)) > 1: + logger.error("--mtp, --no-nextn, and --dspark are mutually exclusive") sys.exit(1) + if args.dspark: + if is_mistral_format or model_architecture != "DeepseekV4ForCausalLM": + logger.error("--dspark is only supported for DeepseekV4ForCausalLM") + sys.exit(1) + from conversion.deepseek import DeepseekV4DSparkModel + model_class = DeepseekV4DSparkModel + if args.mtp or args.no_mtp: if not model_class.supports_mtp_export: - logger.error("--mtp / --no-mtp are not supported for %s", model_architecture) + logger.error("--mtp / --no-nextn are not supported for %s", model_architecture) sys.exit(1) if args.no_mtp: model_class.no_mtp = True diff --git a/docs/backend/SYCL.md b/docs/backend/SYCL.md index 914d63af22db..814e541e1a1b 100644 --- a/docs/backend/SYCL.md +++ b/docs/backend/SYCL.md @@ -797,6 +797,9 @@ use 1 SYCL GPUs: [0] with Max compute units:512 | GGML_SYCL_FA_ONEDNN | 1 (default) or 0 | Enable the oneDNN fused SDPA (flash-attention) path on supported GPUs. Set to 0 to always use the native SYCL flash-attention kernel. | | GGML_SYCL_FA_ONEDNN_MAX_KV | 0 (default, disabled) or positive integer | By default (0), all sequences are handled by the oneDNN fused SDPA path, regardless of KV length; a positive value caps that length, past which sequences fall back to the native kernel. If GPU driver watchdog resets (DEVICE_LOST) occur during long-context inference, set this near the context depth where they start, e.g. 24576. | | GGML_SYCL_ENABLE_VMM | 0 or 1 (default) | Enable the virtual-memory device pool. | +| GGML_SYCL_ENABLE_MKL_FA | 1 (default) or 0 | Enable oneMKL GEMM flash attention for XMX-accelerated prompt processing with quantized KV cache. Automatically activates during prefill (prompt processing) when all conditions are met: (1) flash-attn enabled (`-fa` or `--flash-attn on`), (2) KV cache quantized (`--cache-type-k q8_0 --cache-type-v q8_0` or other `*_0/*_1` types), (3) batch size ≥ 1024 (`--batch-size 1024`), (4) prompt length ≥ 1024 tokens. Set to 0 to force the TILE kernel for A/B testing. Example minimum command: `llama-cli -m model.gguf -fa -ngl 99 --cache-type-k q8_0 --cache-type-v q8_0 --batch-size 1024 -p "your prompt"` | +| GGML_SYCL_MKL_FA_DEBUG | 0 (default) or 1 | Enable per-call diagnostic logging for MKL flash attention: GEMM/softmax timings, interleaved-head detection, and buffer memory usage. | +| GGML_SYCL_MKL_FA_DIAG | 0 (default) or 1 | Enable output fingerprinting for MKL flash attention. Dumps the first 64 float output values for the first 6 FA calls with n_kv ≥ 1024, labeled with kernel type (MKL/TILE/VEC) for cross-kernel comparison. | | GGML_SYCL_ENABLE_FUSION | 0 or 1 (default) | Enable fused-kernel dispatch in graph compute (currently top-k MoE gating). | | ZES_ENABLE_SYSMAN | 0 (default) or 1 | Support to get free memory of GPU by sycl::aspect::ext_intel_free_memory.
Recommended to use when --split-mode = layer | | UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS | 0 (default) or 1 | Allow SYCL/Unified Runtime Level Zero device allocations larger than 4 GiB. llama.cpp's direct Level Zero allocation path requests the relaxed maximum-size limit itself when GGML_SYCL_ENABLE_LEVEL_ZERO=1. | diff --git a/docs/development/HOWTO-add-model.md b/docs/development/HOWTO-add-model.md index 102f479eb02c..270e6b735651 100644 --- a/docs/development/HOWTO-add-model.md +++ b/docs/development/HOWTO-add-model.md @@ -133,6 +133,7 @@ Note: - To debug the multimodal preprocessor and encoder, you can use [llama-mtmd-debug](tools/mtmd/debug/mtmd-debug.cpp). - Adding a model-specific API or CLI is an anti-pattern in `libmtmd`. The goal of `libmtmd` is to provide an easy-to-use, model-agnostic library for multimodal pipeline. - In most cases, `llama-mtmd-cli` should not be modified. If a model requires a specific prompt, either let the user provide it or bake it into the Jinja chat template. +- For audio generation models, see `tools/mtmd/README-dev.md` ## Tips and tricks diff --git a/docs/ops.md b/docs/ops.md index 557b1a023d2e..71bd72011eae 100644 --- a/docs/ops.md +++ b/docs/ops.md @@ -23,16 +23,16 @@ Legend: | ARGMAX | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | | ARGSORT | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ | | CEIL | ❌ | ❌ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | -| CLAMP | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | 🟡 | ✅ | 🟡 | ✅ | ❌ | ❌ | -| COL2IM_1D | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | +| CLAMP | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ | +| COL2IM_1D | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | | CONCAT | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | 🟡 | ❌ | ❌ | | CONT | ❌ | 🟡 | ✅ | ✅ | 🟡 | ✅ | 🟡 | ✅ | ✅ | 🟡 | ❌ | ❌ | -| CONV_2D | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | +| CONV_2D | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ❌ | ❌ | | CONV_2D_DW | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | -| CONV_3D | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | +| CONV_3D | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | | CONV_TRANSPOSE_1D | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | | CONV_TRANSPOSE_2D | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | -| COS | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | 🟡 | ✅ | ❌ | ❌ | +| COS | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | | COUNT_EQUAL | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | | CPY | ❌ | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | ❌ | ❌ | | CROSS_ENTROPY_LOSS | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | @@ -51,8 +51,8 @@ Legend: | FILL | ❌ | ❌ | ✅ | ✅ | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | | FLASH_ATTN_EXT | ❌ | 🟡 | ✅ | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | ❌ | ❌ | | FLOOR | ❌ | ❌ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | -| GATED_DELTA_NET | ❌ | ❌ | ✅ | ❌ | ✅ | 🟡 | ❌ | ✅ | 🟡 | ✅ | ❌ | ❌ | -| GATED_LINEAR_ATTN | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | +| GATED_DELTA_NET | ❌ | ❌ | ✅ | ❌ | ✅ | 🟡 | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | +| GATED_LINEAR_ATTN | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | | GEGLU | ❌ | ✅ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | | GEGLU_ERF | ❌ | ✅ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | | GEGLU_QUICK | ❌ | ✅ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | @@ -60,14 +60,14 @@ Legend: | GELU_ERF | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ | | GELU_QUICK | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ | | GET_ROWS | ❌ | 🟡 | ✅ | 🟡 | 🟡 | 🟡 | 🟡 | ✅ | ✅ | 🟡 | ❌ | ❌ | -| GET_ROWS_BACK | ❌ | ❌ | 🟡 | 🟡 | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | +| GET_ROWS_BACK | ❌ | ❌ | 🟡 | 🟡 | ❌ | ❌ | ❌ | ❌ | 🟡 | ❌ | ❌ | ❌ | | GROUP_NORM | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | | HARDSIGMOID | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | | HARDSWISH | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | | IM2COL | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | | IM2COL_3D | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | | L2_NORM | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ❌ | ✅ | ✅ | 🟡 | ❌ | ❌ | -| LEAKY_RELU | ❌ | ✅ | ✅ | ✅ | ❌ | 🟡 | ❌ | ✅ | 🟡 | ❌ | ❌ | ❌ | +| LEAKY_RELU | ❌ | ✅ | ✅ | ✅ | ❌ | 🟡 | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | | LIGHTNING_INDEXER | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | | LOG | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | | MEAN | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | @@ -76,13 +76,13 @@ Legend: | MUL_MAT_HADAMARD | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | | MUL_MAT_ID | ❌ | 🟡 | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | ✅ | 🟡 | 🟡 | ❌ | | NEG | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | -| NORM | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ✅ | ✅ | 🟡 | 🟡 | ❌ | ❌ | +| NORM | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ✅ | ✅ | ✅ | 🟡 | ❌ | ❌ | | OPT_STEP_ADAMW | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | | OPT_STEP_SGD | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | -| OUT_PROD | 🟡 | 🟡 | 🟡 | 🟡 | ❌ | ❌ | ❌ | 🟡 | ❌ | ❌ | ❌ | 🟡 | +| OUT_PROD | 🟡 | 🟡 | 🟡 | 🟡 | ❌ | ❌ | ❌ | 🟡 | 🟡 | ❌ | ❌ | 🟡 | | PAD | ❌ | 🟡 | ✅ | 🟡 | ❌ | 🟡 | 🟡 | 🟡 | ✅ | ✅ | ❌ | ❌ | | PAD_REFLECT_1D | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | -| POOL_1D | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | +| POOL_1D | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | | POOL_2D | ❌ | 🟡 | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | | REGLU | ❌ | ✅ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | | RELU | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ | @@ -103,13 +103,13 @@ Legend: | SIGMOID | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ | | SILU | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ | | SILU_BACK | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | -| SIN | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | 🟡 | ✅ | ❌ | ❌ | +| SIN | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | | SOFTPLUS | ❌ | ❌ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | | SOFT_MAX | ❌ | 🟡 | ✅ | ✅ | 🟡 | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | | SOFT_MAX_BACK | ❌ | ❌ | 🟡 | 🟡 | ❌ | ❌ | ❌ | 🟡 | ✅ | ❌ | ❌ | ❌ | | SOLVE_TRI | ❌ | ❌ | ✅ | 🟡 | 🟡 | ✅ | ❌ | 🟡 | ✅ | ✅ | ❌ | ❌ | -| SQR | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ✅ | ✅ | 🟡 | ✅ | ❌ | ❌ | -| SQRT | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ❌ | ❌ | +| SQR | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | +| SQRT | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | | SSM_CONV | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | | SSM_SCAN | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | 🟡 | 🟡 | ✅ | ❌ | ❌ | | STEP | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | diff --git a/docs/ops/Vulkan.csv b/docs/ops/Vulkan.csv index 3aa7976a2087..59e67e1b208d 100644 --- a/docs/ops/Vulkan.csv +++ b/docs/ops/Vulkan.csv @@ -167,6 +167,16 @@ "Vulkan0","ROUND","type=f32,ne_a=[5,7,11,13],v=1","support","1","yes","Vulkan" "Vulkan0","TRUNC","type=f32,ne_a=[128,2,2,2],v=1","support","1","yes","Vulkan" "Vulkan0","TRUNC","type=f32,ne_a=[5,7,11,13],v=1","support","1","yes","Vulkan" +"Vulkan0","DSV4_HC_COMB","n_tokens=1,n_iter=1,eps=0.000001","support","0","no","Vulkan" +"Vulkan0","DSV4_HC_COMB","n_tokens=17,n_iter=4,eps=0.000001","support","0","no","Vulkan" +"Vulkan0","DSV4_HC_COMB","n_tokens=257,n_iter=8,eps=0.000001","support","0","no","Vulkan" +"Vulkan0","DSV4_HC_PRE","n_embd=1,n_tokens=1","support","0","no","Vulkan" +"Vulkan0","DSV4_HC_PRE","n_embd=31,n_tokens=17","support","0","no","Vulkan" +"Vulkan0","DSV4_HC_PRE","n_embd=128,n_tokens=257","support","0","no","Vulkan" +"Vulkan0","DSV4_HC_PRE","n_embd=4096,n_tokens=21","support","0","no","Vulkan" +"Vulkan0","DSV4_HC_POST","n_embd=1,n_tokens=1","support","0","no","Vulkan" +"Vulkan0","DSV4_HC_POST","n_embd=31,n_tokens=17","support","0","no","Vulkan" +"Vulkan0","DSV4_HC_POST","n_embd=128,n_tokens=257","support","0","no","Vulkan" "Vulkan0","REGLU","type=f16,ne_a=[128,2,2,2],v=0,swapped=0","support","1","yes","Vulkan" "Vulkan0","REGLU","type=f16,ne_a=[5,7,11,13],v=0,swapped=0","support","1","yes","Vulkan" "Vulkan0","REGLU","type=f16,ne_a=[128,2,2,2],v=0,swapped=1","support","1","yes","Vulkan" @@ -338,6 +348,10 @@ "Vulkan0","GET_ROWS","type=q1_0,n=256,m=5,r=4,be1=1,be2=1,v=1","support","1","yes","Vulkan" "Vulkan0","GET_ROWS","type=q1_0,n=256,m=5,r=4,be1=7,be2=1,v=0","support","1","yes","Vulkan" "Vulkan0","GET_ROWS","type=q1_0,n=256,m=5,r=4,be1=7,be2=1,v=1","support","1","yes","Vulkan" +"Vulkan0","GET_ROWS","type=q2_0,n=256,m=5,r=4,be1=1,be2=1,v=0","support","1","yes","Vulkan" +"Vulkan0","GET_ROWS","type=q2_0,n=256,m=5,r=4,be1=1,be2=1,v=1","support","1","yes","Vulkan" +"Vulkan0","GET_ROWS","type=q2_0,n=256,m=5,r=4,be1=7,be2=1,v=0","support","1","yes","Vulkan" +"Vulkan0","GET_ROWS","type=q2_0,n=256,m=5,r=4,be1=7,be2=1,v=1","support","1","yes","Vulkan" "Vulkan0","GET_ROWS","type=mxfp4,n=256,m=5,r=4,be1=1,be2=1,v=0","support","1","yes","Vulkan" "Vulkan0","GET_ROWS","type=mxfp4,n=256,m=5,r=4,be1=1,be2=1,v=1","support","1","yes","Vulkan" "Vulkan0","GET_ROWS","type=mxfp4,n=256,m=5,r=4,be1=7,be2=1,v=0","support","1","yes","Vulkan" @@ -406,9 +420,10 @@ "Vulkan0","GET_ROWS","type=i32,n=256,m=5,r=4,be1=1,be2=1,v=1","support","1","yes","Vulkan" "Vulkan0","GET_ROWS","type=i32,n=256,m=5,r=4,be1=7,be2=1,v=0","support","1","yes","Vulkan" "Vulkan0","GET_ROWS","type=i32,n=256,m=5,r=4,be1=7,be2=1,v=1","support","1","yes","Vulkan" -"Vulkan0","GET_ROWS_BACK","type=f32,n=1,m=8,r=2,b=1,v=0","support","0","no","Vulkan" -"Vulkan0","GET_ROWS_BACK","type=f32,n=256,m=5,r=4,b=1,v=0","support","0","no","Vulkan" -"Vulkan0","GET_ROWS_BACK","type=f32,n=256,m=5,r=4,b=1,v=1","support","0","no","Vulkan" +"Vulkan0","GET_ROWS_BACK","type=f32,n=1,m=8,r=2,b=1,v=0","support","1","yes","Vulkan" +"Vulkan0","GET_ROWS_BACK","type=f32,n=1,m=70000,r=4,b=1,v=0","support","1","yes","Vulkan" +"Vulkan0","GET_ROWS_BACK","type=f32,n=256,m=5,r=4,b=1,v=0","support","1","yes","Vulkan" +"Vulkan0","GET_ROWS_BACK","type=f32,n=256,m=5,r=4,b=1,v=1","support","1","yes","Vulkan" "Vulkan0","GET_ROWS_BACK","type=f16,n=256,m=5,r=4,b=1,v=0","support","0","no","Vulkan" "Vulkan0","GET_ROWS_BACK","type=f16,n=256,m=5,r=4,b=1,v=1","support","0","no","Vulkan" "Vulkan0","GET_ROWS_BACK","type=bf16,n=256,m=5,r=4,b=1,v=0","support","0","no","Vulkan" @@ -425,6 +440,8 @@ "Vulkan0","GET_ROWS_BACK","type=q8_0,n=256,m=5,r=4,b=1,v=1","support","0","no","Vulkan" "Vulkan0","GET_ROWS_BACK","type=q1_0,n=256,m=5,r=4,b=1,v=0","support","0","no","Vulkan" "Vulkan0","GET_ROWS_BACK","type=q1_0,n=256,m=5,r=4,b=1,v=1","support","0","no","Vulkan" +"Vulkan0","GET_ROWS_BACK","type=q2_0,n=256,m=5,r=4,b=1,v=0","support","0","no","Vulkan" +"Vulkan0","GET_ROWS_BACK","type=q2_0,n=256,m=5,r=4,b=1,v=1","support","0","no","Vulkan" "Vulkan0","GET_ROWS_BACK","type=mxfp4,n=256,m=5,r=4,b=1,v=0","support","0","no","Vulkan" "Vulkan0","GET_ROWS_BACK","type=mxfp4,n=256,m=5,r=4,b=1,v=1","support","0","no","Vulkan" "Vulkan0","GET_ROWS_BACK","type=nvfp4,n=256,m=5,r=4,b=1,v=0","support","0","no","Vulkan" @@ -459,333 +476,685 @@ "Vulkan0","GET_ROWS_BACK","type=iq4_xs,n=256,m=5,r=4,b=1,v=1","support","0","no","Vulkan" "Vulkan0","GET_ROWS_BACK","type=i32,n=256,m=5,r=4,b=1,v=0","support","0","no","Vulkan" "Vulkan0","GET_ROWS_BACK","type=i32,n=256,m=5,r=4,b=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[1,8,1,3],nr23=[1,1],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i32,ne=[1,8,1,3],nr23=[1,1],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q8_0,type_idx=i32,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f32,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=f16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=bf16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q4_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q5_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q8_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q8_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q8_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q8_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q8_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q8_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q8_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q8_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q8_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q8_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q8_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q8_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q1_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q1_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q1_0,type_idx=i64,ne=[384,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q1_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q1_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q1_0,type_idx=i64,ne=[384,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q1_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q1_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q1_0,type_idx=i64,ne=[384,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q1_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q1_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=q1_0,type_idx=i64,ne=[384,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=mxfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=mxfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=mxfp4,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=mxfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=mxfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=mxfp4,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=mxfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=mxfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=mxfp4,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=mxfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=mxfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=mxfp4,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=nvfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=nvfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=nvfp4,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=nvfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=nvfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=nvfp4,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=nvfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=nvfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=nvfp4,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=nvfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=nvfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=nvfp4,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q2_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q2_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q2_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q2_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q2_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q2_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q2_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q2_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q2_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q2_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q2_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q2_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q3_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q3_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q3_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q3_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q3_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q3_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q3_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q3_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q3_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q3_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q3_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q3_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q4_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q4_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q4_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q4_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q4_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q4_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q4_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q4_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q4_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q4_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q4_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q4_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q5_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q5_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q5_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q5_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q5_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q5_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q5_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q5_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q5_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q5_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q5_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q5_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q6_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q6_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q6_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q6_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q6_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q6_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q6_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q6_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q6_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q6_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q6_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=q6_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq2_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_m,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_m,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_m,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_m,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_m,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_m,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_m,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_m,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_m,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_m,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_m,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq1_m,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_nl,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq3_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" -"Vulkan0","SET_ROWS","type=iq4_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[1,8,1,3],nr23=[1,1],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i32,ne=[1,8,1,3],nr23=[1,1],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i32,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f32,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=bf16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q8_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[384,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[384,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[384,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q1_0,type_idx=i64,ne=[384,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_0,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=mxfp4,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=nvfp4,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q2_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q3_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q4_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q5_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=q6_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq2_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq1_m,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_nl,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq3_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=iq4_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f32,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=f16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[3,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[31,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[33,5,1,1],nr23=[2,3],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[3,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[31,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=bf16,type_idx=i64,ne=[33,5,1,7],nr23=[2,3],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_1,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q8_0,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[384,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[384,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[384,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q1_0,type_idx=i64,ne=[384,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_0,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=mxfp4,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[192,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=nvfp4,type_idx=i64,ne=[192,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q2_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q3_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q4_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q5_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=q6_K,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq2_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_xxs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq1_m,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[96,3,1,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_nl,type_idx=i64,ne=[96,3,7,1],nr23=[2,3],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq3_s,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[256,5,1,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[256,11,1,1],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[768,3,1,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=0","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[256,5,7,3],nr23=[1,1],r=1,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[256,11,1,7],nr23=[2,3],r=7,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f32,type_dst=iq4_xs,type_idx=i64,ne=[768,3,7,1],nr23=[2,3],r=2,v=1","support","0","no","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[1,8,1,3],nr23=[1,1],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i32,ne=[1,8,1,3],nr23=[1,1],r=2,v=0","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i64,ne=[1,8,1,3],nr23=[1,1],r=2,v=1","support","1","yes","Vulkan" +"Vulkan0","SET_ROWS","type_src=f16,type_dst=f16,type_idx=i32,ne=[1,8,1,3],nr23=[1,1],r=2,v=1","support","1","yes","Vulkan" "Vulkan0","POOL_2D","pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=1,p0=0,p1=0","support","1","yes","Vulkan" "Vulkan0","POOL_2D","pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=1,p0=0,p1=1","support","1","yes","Vulkan" "Vulkan0","POOL_2D","pool_type=avg,type_input=f32,ne_input=[10,10,3,1],k0=1,k1=1,s0=1,s1=1,p0=1,p1=0","support","1","yes","Vulkan" @@ -914,57 +1283,226 @@ "Vulkan0","POOL_2D","pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=2,s1=2,p0=0,p1=1","support","1","yes","Vulkan" "Vulkan0","POOL_2D","pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=2,s1=2,p0=1,p1=0","support","1","yes","Vulkan" "Vulkan0","POOL_2D","pool_type=max,type_input=f32,ne_input=[10,10,3,1],k0=3,k1=3,s0=2,s1=2,p0=1,p1=1","support","1","yes","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=1,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=1,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=1,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=1,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=1,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=1,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=2,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=2,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=2,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=2,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=2,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=2,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=1,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=1,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=1,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=1,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=1,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=1,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=2,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=2,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=2,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=2,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=2,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=2,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=1,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=1,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=1,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=1,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=1,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=1,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=2,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=2,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=2,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=2,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=2,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=2,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=1,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=1,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=1,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=1,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=1,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=1,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=2,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=2,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=2,p0=0","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=2,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=2,p0=1","support","0","no","Vulkan" -"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=2,p0=1","support","0","no","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=1,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=1,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=1,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=1,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=1,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=1,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=1,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=1,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=1,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=2,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=2,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=2,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=2,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=2,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=2,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=2,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=2,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=2,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=3,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=3,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=3,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=3,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=3,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=3,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=1,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=1,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=1,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=1,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=1,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=1,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=1,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=1,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=1,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=2,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=2,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=2,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=2,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=2,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=2,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=2,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=2,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=2,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=3,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=3,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=3,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=3,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=3,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=3,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=1,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=1,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=1,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=1,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=1,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=1,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=1,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=1,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=1,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=2,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=2,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=2,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=2,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=2,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=2,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=2,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=2,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=2,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=3,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=3,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=3,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=3,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=3,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=avg,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=3,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=1,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=1,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=1,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=1,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=1,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=1,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=1,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=1,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=1,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=2,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=2,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=2,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=2,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=2,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=2,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=2,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=2,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=2,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=3,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=3,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=3,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=1,s0=3,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=1,s0=3,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=1,s0=3,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=1,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=1,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=1,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=1,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=1,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=1,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=1,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=1,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=1,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=2,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=2,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=2,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=2,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=2,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=2,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=2,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=2,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=2,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=3,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=3,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=3,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=2,s0=3,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=2,s0=3,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=2,s0=3,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=1,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=1,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=1,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=1,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=1,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=1,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=1,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=1,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=1,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=2,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=2,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=2,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=2,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=2,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=2,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=2,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=2,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=2,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=3,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=3,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=3,p0=2","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[10,3,2,1],k0=3,s0=3,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[11,1,3,2],k0=3,s0=3,p0=3","support","1","yes","Vulkan" +"Vulkan0","POOL_1D","pool_type=max,type_input=f32,ne_input=[128,2,1,3],k0=3,s0=3,p0=3","support","1","yes","Vulkan" "Vulkan0","IM2COL","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[3000,128,1,1],ne_kernel=[3,128,1280,1],s0=1,s1=0,p0=1,p1=0,d0=1,d1=0,is_2D=0","support","1","yes","Vulkan" "Vulkan0","IM2COL","type_input=f32,type_kernel=f16,dst_type=f32,ne_input=[3000,128,1,1],ne_kernel=[3,128,1280,1],s0=1,s1=0,p0=1,p1=0,d0=1,d1=0,is_2D=0","support","1","yes","Vulkan" "Vulkan0","IM2COL","type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[3000,128,1,1],ne_kernel=[3,128,1280,1],s0=1,s1=0,p0=1,p1=0,d0=1,d1=0,is_2D=0","support","1","yes","Vulkan" +"Vulkan0","IM2COL","type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[3000,384,1,1],ne_kernel=[3,384,384,1],s0=1,s1=0,p0=1,p1=0,d0=1,d1=0,is_2D=0","support","1","yes","Vulkan" "Vulkan0","IM2COL","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,2,2,1],ne_kernel=[3,2,2,1],s0=1,s1=0,p0=0,p1=0,d0=1,d1=0,is_2D=0","support","1","yes","Vulkan" "Vulkan0","IM2COL","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,2,2,1],ne_kernel=[3,2,2,1],s0=1,s1=0,p0=0,p1=0,d0=3,d1=0,is_2D=0","support","1","yes","Vulkan" "Vulkan0","IM2COL","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,2,2,1],ne_kernel=[3,2,2,1],s0=1,s1=0,p0=3,p1=0,d0=1,d1=0,is_2D=0","support","1","yes","Vulkan" @@ -974,6 +1512,7 @@ "Vulkan0","IM2COL","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,2,2,1],ne_kernel=[3,2,2,1],s0=3,s1=0,p0=3,p1=0,d0=1,d1=0,is_2D=0","support","1","yes","Vulkan" "Vulkan0","IM2COL","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,2,2,1],ne_kernel=[3,2,2,1],s0=3,s1=0,p0=3,p1=0,d0=3,d1=0,is_2D=0","support","1","yes","Vulkan" "Vulkan0","IM2COL","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[10,10,3,1],ne_kernel=[3,3,3,1],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1","support","1","yes","Vulkan" +"Vulkan0","IM2COL","type_input=f32,type_kernel=f32,dst_type=f16,ne_input=[10,10,3,1],ne_kernel=[3,3,3,1],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1","support","1","yes","Vulkan" "Vulkan0","IM2COL","type_input=f32,type_kernel=f16,dst_type=f32,ne_input=[10,10,3,1],ne_kernel=[3,3,3,1],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1","support","1","yes","Vulkan" "Vulkan0","IM2COL","type_input=f32,type_kernel=f16,dst_type=f16,ne_input=[10,10,3,1],ne_kernel=[3,3,3,1],s0=1,s1=1,p0=1,p1=1,d0=1,d1=1,is_2D=1","support","1","yes","Vulkan" "Vulkan0","IM2COL","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,2,2],ne_kernel=[3,3,2,2],s0=1,s1=1,p0=0,p1=0,d0=1,d1=1,is_2D=1","support","1","yes","Vulkan" @@ -3104,1835 +3643,3411 @@ "Vulkan0","IM2COL_3D","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=0","support","1","yes","Vulkan" "Vulkan0","IM2COL_3D","type_input=f32,type_kernel=f32,dst_type=f32,ne_input=[20,20,10,3],ne_kernel=[3,3,3,3],IC=3,s0=3,s1=3,s2=3,p0=3,p1=3,p2=3,d0=3,d1=3,d2=3,v=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f32,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f16,stride0=1,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=2,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","1","yes","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,1,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,2,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,3,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[1,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[2,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[3,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,1,2],ne_kernel=[11,11,1,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,1],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,1,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,2,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,1,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,3,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[1,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[2,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[1,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[3,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f32,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" "Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=0","support","1","yes","Vulkan" -"Vulkan0","CONV_2D_DW","ne_input=[17,34,9,1],ne_kernel=[3,3,1,9],stride=1,padding=0,dilation=1,cwhn=0","support","1","yes","Vulkan" -"Vulkan0","CONV_2D_DW","ne_input=[17,34,9,1],ne_kernel=[3,3,1,9],stride=1,padding=0,dilation=1,cwhn=1","support","1","yes","Vulkan" -"Vulkan0","CONV_2D_DW","ne_input=[32,8,64,1],ne_kernel=[3,3,1,64],stride=2,padding=1,dilation=1,cwhn=0","support","1","yes","Vulkan" -"Vulkan0","CONV_2D_DW","ne_input=[32,8,64,1],ne_kernel=[3,3,1,64],stride=2,padding=1,dilation=1,cwhn=1","support","1","yes","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=4,ID=8,IH=8,IW=8,OC=8,KD=1,KH=1,KW=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","0","no","Vulkan" -"Vulkan0","CONV_3D","N=1,IC=4,ID=8,IH=8,IW=8,OC=8,KD=1,KH=1,KW=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","0","no","Vulkan" +"Vulkan0","CONV_2D","ne_input=[141,133,25,2],ne_kernel=[11,11,25,12],type_kernel=f16,stride0=3,stride1=5,padding0=5,padding1=5,dilation0=2,dilation1=4,cwhn=1","support","0","no","Vulkan" +"Vulkan0","CONV_2D","ne_input=[256,256,192,1],ne_kernel=[3,3,192,96],type_kernel=f32,stride0=1,stride1=1,padding0=1,padding1=1,dilation0=1,dilation1=1,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[256,256,192,1],ne_kernel=[3,3,192,96],type_kernel=f32,stride0=1,stride1=1,padding0=1,padding1=1,dilation0=1,dilation1=1,cwhn=1","support","0","no","Vulkan" +"Vulkan0","CONV_2D","ne_input=[256,256,192,1],ne_kernel=[3,3,192,96],type_kernel=f16,stride0=1,stride1=1,padding0=1,padding1=1,dilation0=1,dilation1=1,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D","ne_input=[256,256,192,1],ne_kernel=[3,3,192,96],type_kernel=f16,stride0=1,stride1=1,padding0=1,padding1=1,dilation0=1,dilation1=1,cwhn=1","support","0","no","Vulkan" +"Vulkan0","CONV_2D_DW","ne_input=[17,34,9,1],ne_kernel=[3,3,1,9],type_kernel=f32,stride=1,padding=0,dilation=1,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D_DW","ne_input=[17,34,9,1],ne_kernel=[3,3,1,9],type_kernel=f32,stride=1,padding=0,dilation=1,cwhn=1","support","1","yes","Vulkan" +"Vulkan0","CONV_2D_DW","ne_input=[32,8,64,1],ne_kernel=[3,3,1,64],type_kernel=f32,stride=2,padding=1,dilation=1,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D_DW","ne_input=[32,8,64,1],ne_kernel=[3,3,1,64],type_kernel=f32,stride=2,padding=1,dilation=1,cwhn=1","support","1","yes","Vulkan" +"Vulkan0","CONV_2D_DW","ne_input=[17,34,9,1],ne_kernel=[3,3,1,9],type_kernel=f16,stride=1,padding=0,dilation=1,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D_DW","ne_input=[17,34,9,1],ne_kernel=[3,3,1,9],type_kernel=f16,stride=1,padding=0,dilation=1,cwhn=1","support","1","yes","Vulkan" +"Vulkan0","CONV_2D_DW","ne_input=[32,8,64,1],ne_kernel=[3,3,1,64],type_kernel=f16,stride=2,padding=1,dilation=1,cwhn=0","support","1","yes","Vulkan" +"Vulkan0","CONV_2D_DW","ne_input=[32,8,64,1],ne_kernel=[3,3,1,64],type_kernel=f16,stride=2,padding=1,dilation=1,cwhn=1","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=4,ID=8,IH=8,IW=8,OC=8,KD=1,KH=1,KW=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f32","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=1,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=1,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=1,s1=1,s2=1,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=0,p1=0,p2=0,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=3,KW=3,s0=2,s1=2,s2=2,p0=1,p1=1,p2=1,d0=2,d1=2,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=2,IC=3,ID=18,IH=22,IW=20,OC=4,KD=3,KH=1,KW=5,s0=2,s1=1,s2=1,p0=2,p1=0,p2=1,d0=1,d1=1,d2=2,type_kernel=f16","support","1","yes","Vulkan" +"Vulkan0","CONV_3D","N=1,IC=4,ID=8,IH=8,IW=8,OC=8,KD=1,KH=1,KW=1,s0=1,s1=1,s2=1,p0=0,p1=0,p2=0,d0=1,d1=1,d2=1,type_kernel=f16","support","1","yes","Vulkan" "Vulkan0","CONV_TRANSPOSE_1D","ne_input=[1,1,1,1],ne_kernel=[1,1,1,1],s0=1,p0=0,d0=1","support","1","yes","Vulkan" "Vulkan0","CONV_TRANSPOSE_1D","ne_input=[1,1,1,1],ne_kernel=[1,1,1,1],s0=2,p0=0,d0=1","support","1","yes","Vulkan" "Vulkan0","CONV_TRANSPOSE_1D","ne_input=[1,1,1,1],ne_kernel=[1,1,1,1],s0=3,p0=0,d0=1","support","1","yes","Vulkan" @@ -5049,6 +7164,39 @@ "Vulkan0","CONV_TRANSPOSE_1D","ne_input=[3,2,1,1],ne_kernel=[3,2,2,1],s0=1,p0=0,d0=1","support","1","yes","Vulkan" "Vulkan0","CONV_TRANSPOSE_1D","ne_input=[3,2,1,1],ne_kernel=[3,1,2,1],s0=1,p0=0,d0=1","support","1","yes","Vulkan" "Vulkan0","CONV_TRANSPOSE_1D","ne_input=[2,1,1,1],ne_kernel=[3,1,1,1],s0=1,p0=0,d0=1","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f32,K=16,OC=32,T_in=197,s0=8,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f32,K=4,OC=3,T_in=7,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f32,K=1,OC=5,T_in=13,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f32,K=6,OC=4,T_in=11,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f32,K=2,OC=3,T_in=9,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f32,K=5,OC=4,T_in=11,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f32,K=8,OC=4,T_in=13,s0=4,p0=2","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f32,K=4,OC=3,T_in=1,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f32,K=16,OC=1,T_in=197,s0=8,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f32,K=1,OC=5,T_in=13,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f32,K=8,OC=2,T_in=3,s0=2,p0=5","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f16,K=16,OC=32,T_in=197,s0=8,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f16,K=4,OC=3,T_in=7,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f16,K=1,OC=5,T_in=13,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f16,K=6,OC=4,T_in=11,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f16,K=2,OC=3,T_in=9,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f16,K=5,OC=4,T_in=11,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f16,K=8,OC=4,T_in=13,s0=4,p0=2","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f16,K=4,OC=3,T_in=1,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f16,K=16,OC=1,T_in=197,s0=8,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f16,K=1,OC=5,T_in=13,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=f16,K=8,OC=2,T_in=3,s0=2,p0=5","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=bf16,K=16,OC=32,T_in=197,s0=8,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=bf16,K=4,OC=3,T_in=7,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=bf16,K=1,OC=5,T_in=13,s0=1,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=bf16,K=6,OC=4,T_in=11,s0=3,p0=1","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=bf16,K=2,OC=3,T_in=9,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=bf16,K=5,OC=4,T_in=11,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=bf16,K=8,OC=4,T_in=13,s0=4,p0=2","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=bf16,K=4,OC=3,T_in=1,s0=2,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=bf16,K=16,OC=1,T_in=197,s0=8,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=bf16,K=1,OC=5,T_in=13,s0=3,p0=0","support","1","yes","Vulkan" +"Vulkan0","COL2IM_1D","type=bf16,K=8,OC=2,T_in=3,s0=2,p0=5","support","1","yes","Vulkan" "Vulkan0","CONV_TRANSPOSE_2D","kernel_type=f32,ne_input=[3,2,3,1],ne_kernel=[2,2,1,3],stride=1","support","1","yes","Vulkan" "Vulkan0","CONV_TRANSPOSE_2D","kernel_type=f32,ne_input=[10,10,9,1],ne_kernel=[3,3,1,9],stride=2","support","1","yes","Vulkan" "Vulkan0","CONV_TRANSPOSE_2D","kernel_type=f32,ne_input=[129,63,35,1],ne_kernel=[3,3,48,35],stride=1","support","1","yes","Vulkan" @@ -5071,6 +7219,7 @@ "Vulkan0","REPEAT","type=f32,ne=[10,5,4,1],nr=[1,1,1,2]","support","1","yes","Vulkan" "Vulkan0","REPEAT","type=i32,ne=[10,5,4,1],nr=[2,1,1,1]","support","1","yes","Vulkan" "Vulkan0","REPEAT","type=i16,ne=[10,5,4,1],nr=[1,1,1,2]","support","1","yes","Vulkan" +"Vulkan0","REPEAT","type=bf16,ne=[10,5,4,1],nr=[2,1,1,1]","support","1","yes","Vulkan" "Vulkan0","REPEAT","type=f32,ne=[10,5,4,3],nr=[1,1,1,1]","support","1","yes","Vulkan" "Vulkan0","REPEAT","type=f32,ne=[10,5,4,3],nr=[2,1,1,1]","support","1","yes","Vulkan" "Vulkan0","REPEAT","type=f32,ne=[10,5,4,3],nr=[1,2,1,1]","support","1","yes","Vulkan" @@ -5078,6 +7227,7 @@ "Vulkan0","REPEAT","type=f32,ne=[10,5,4,3],nr=[1,1,1,2]","support","1","yes","Vulkan" "Vulkan0","REPEAT","type=i32,ne=[10,5,4,3],nr=[2,1,1,1]","support","1","yes","Vulkan" "Vulkan0","REPEAT","type=i16,ne=[10,5,4,3],nr=[1,1,1,2]","support","1","yes","Vulkan" +"Vulkan0","REPEAT","type=bf16,ne=[10,5,4,3],nr=[2,1,1,1]","support","1","yes","Vulkan" "Vulkan0","REPEAT_BACK","type=f32,ne=[8,6,4,2],nr=[1,1,1,1],v=0","support","1","yes","Vulkan" "Vulkan0","REPEAT_BACK","type=f32,ne=[8,6,4,2],nr=[2,1,1,1],v=0","support","1","yes","Vulkan" "Vulkan0","REPEAT_BACK","type=f32,ne=[8,6,4,2],nr=[1,2,1,1],v=0","support","1","yes","Vulkan" @@ -5191,6 +7341,15 @@ "Vulkan0","CPY","type_src=q1_0,type_dst=q1_0,ne_src=[384,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" "Vulkan0","CPY","type_src=q1_0,type_dst=q1_0,ne_src=[384,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" "Vulkan0","CPY","type_src=q1_0,type_dst=q1_0,ne_src=[384,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","Vulkan" +"Vulkan0","CPY","type_src=q2_0,type_dst=q2_0,ne_src=[64,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" +"Vulkan0","CPY","type_src=q2_0,type_dst=q2_0,ne_src=[64,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" +"Vulkan0","CPY","type_src=q2_0,type_dst=q2_0,ne_src=[64,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","Vulkan" +"Vulkan0","CPY","type_src=q2_0,type_dst=q2_0,ne_src=[128,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" +"Vulkan0","CPY","type_src=q2_0,type_dst=q2_0,ne_src=[128,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" +"Vulkan0","CPY","type_src=q2_0,type_dst=q2_0,ne_src=[128,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","Vulkan" +"Vulkan0","CPY","type_src=q2_0,type_dst=q2_0,ne_src=[192,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" +"Vulkan0","CPY","type_src=q2_0,type_dst=q2_0,ne_src=[192,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" +"Vulkan0","CPY","type_src=q2_0,type_dst=q2_0,ne_src=[192,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","Vulkan" "Vulkan0","CPY","type_src=mxfp4,type_dst=mxfp4,ne_src=[32,2,3,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" "Vulkan0","CPY","type_src=mxfp4,type_dst=mxfp4,ne_src=[32,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" "Vulkan0","CPY","type_src=mxfp4,type_dst=mxfp4,ne_src=[32,2,3,4],permute_src=[0,3,1,2],permute_dst=[0,2,1,3],_src_transpose=0","support","0","no","Vulkan" @@ -5353,6 +7512,8 @@ "Vulkan0","CPY","type_src=f16,type_dst=q8_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" "Vulkan0","CPY","type_src=f16,type_dst=q1_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" "Vulkan0","CPY","type_src=f16,type_dst=q1_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" +"Vulkan0","CPY","type_src=f16,type_dst=q2_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" +"Vulkan0","CPY","type_src=f16,type_dst=q2_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" "Vulkan0","CPY","type_src=f16,type_dst=mxfp4,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" "Vulkan0","CPY","type_src=f16,type_dst=mxfp4,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" "Vulkan0","CPY","type_src=f16,type_dst=nvfp4,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" @@ -5403,6 +7564,8 @@ "Vulkan0","CPY","type_src=bf16,type_dst=q8_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" "Vulkan0","CPY","type_src=bf16,type_dst=q1_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" "Vulkan0","CPY","type_src=bf16,type_dst=q1_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" +"Vulkan0","CPY","type_src=bf16,type_dst=q2_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" +"Vulkan0","CPY","type_src=bf16,type_dst=q2_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" "Vulkan0","CPY","type_src=bf16,type_dst=mxfp4,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" "Vulkan0","CPY","type_src=bf16,type_dst=mxfp4,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" "Vulkan0","CPY","type_src=bf16,type_dst=nvfp4,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" @@ -5453,6 +7616,8 @@ "Vulkan0","CPY","type_src=f32,type_dst=q8_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" "Vulkan0","CPY","type_src=f32,type_dst=q1_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" "Vulkan0","CPY","type_src=f32,type_dst=q1_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" +"Vulkan0","CPY","type_src=f32,type_dst=q2_0,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" +"Vulkan0","CPY","type_src=f32,type_dst=q2_0,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" "Vulkan0","CPY","type_src=f32,type_dst=mxfp4,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" "Vulkan0","CPY","type_src=f32,type_dst=mxfp4,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" "Vulkan0","CPY","type_src=f32,type_dst=nvfp4,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" @@ -5503,6 +7668,8 @@ "Vulkan0","CPY","type_src=q8_0,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" "Vulkan0","CPY","type_src=q1_0,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" "Vulkan0","CPY","type_src=q1_0,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" +"Vulkan0","CPY","type_src=q2_0,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" +"Vulkan0","CPY","type_src=q2_0,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" "Vulkan0","CPY","type_src=mxfp4,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" "Vulkan0","CPY","type_src=mxfp4,type_dst=f32,ne_src=[256,2,3,4],permute_src=[0,2,1,3],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" "Vulkan0","CPY","type_src=nvfp4,type_dst=f32,ne_src=[256,4,4,4],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","0","no","Vulkan" @@ -5553,6 +7720,10 @@ "Vulkan0","CPY","type_src=i32,type_dst=i32,ne_src=[256,4,1,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=1","support","1","yes","Vulkan" "Vulkan0","CPY","type_src=i32,type_dst=i32,ne_src=[256,1,4,1],permute_src=[1,2,0,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" "Vulkan0","CPY","type_src=f32,type_dst=f32,ne_src=[256,1,4,1],permute_src=[1,2,0,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" +"Vulkan0","CPY","type_src=f32,type_dst=f32,ne_src=[2,2097121,1,1],permute_src=[1,0,2,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" +"Vulkan0","CPY","type_src=f32,type_dst=f32,ne_src=[2,2,524281,1],permute_src=[1,0,2,3],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" +"Vulkan0","CPY","type_src=f32,type_dst=f32,ne_src=[128,2,3,1],ne_dst=[128,2,3,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0,dst_alloc=[128,4,3,1]","support","1","yes","Vulkan" +"Vulkan0","CPY","type_src=f16,type_dst=f16,ne_src=[128,2,3,1],ne_dst=[128,2,3,1],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0,dst_alloc=[128,4,3,1]","support","1","yes","Vulkan" "Vulkan0","CPY","type_src=f32,type_dst=f32,ne_src=[3,5,7,32],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" "Vulkan0","CPY","type_src=f32,type_dst=f32,ne_src=[3,5,32,7],ne_dst=[3,5,7,32],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" "Vulkan0","CPY","type_src=f32,type_dst=f32,ne_src=[3,5,32,7],ne_dst=[32,7,5,3],permute_src=[0,0,0,0],permute_dst=[0,0,0,0],_src_transpose=0","support","1","yes","Vulkan" @@ -6052,76 +8223,96 @@ "Vulkan0","SCALE","type=f32,ne=[10,10,10,10],scale=2.000000,bias=1.000000,inplace=1","support","1","yes","Vulkan" "Vulkan0","SCALE","type=f32,ne=[100,10,10,10],scale=2.000000,bias=1.000000,inplace=0","support","1","yes","Vulkan" "Vulkan0","SILU_BACK","type=f32,ne=[64,5,4,3],eps=0.000001","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000000","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000000,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000000,inplace=0","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000000","support","0","no","Vulkan" +"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000000,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000000,inplace=0","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000000,noncontig_rows=1","support","1","yes","Vulkan" "Vulkan0","RMS_NORM_BACK","type=f32,ne=[64,5,4,3],eps=0.000000","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000000,v=0","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000000,v=1","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000000","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000000,v=0,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000000,v=1,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000000,v=0,noncontig_rows=1","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000000,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000000,inplace=0","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000000","support","0","no","Vulkan" +"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000000,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000000,inplace=0","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000000,noncontig_rows=1","support","1","yes","Vulkan" "Vulkan0","RMS_NORM_BACK","type=f32,ne=[1025,5,4,3],eps=0.000000","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000000,v=0","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000000,v=1","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000001","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000000,v=0,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000000,v=1,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000000,v=0,noncontig_rows=1","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000001,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000001,inplace=0","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000001","support","0","no","Vulkan" +"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000001,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000001,inplace=0","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000001,noncontig_rows=1","support","1","yes","Vulkan" "Vulkan0","RMS_NORM_BACK","type=f32,ne=[64,5,4,3],eps=0.000001","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000001,v=0","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000001,v=1","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000001","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000001,v=0,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000001,v=1,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000001,v=0,noncontig_rows=1","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000001,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000001,inplace=0","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000001","support","0","no","Vulkan" +"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000001,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000001,inplace=0","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000001,noncontig_rows=1","support","1","yes","Vulkan" "Vulkan0","RMS_NORM_BACK","type=f32,ne=[1025,5,4,3],eps=0.000001","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000001,v=0","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000001,v=1","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000100","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000001,v=0,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000001,v=1,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000001,v=0,noncontig_rows=1","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000100,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000100,inplace=0","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000100","support","0","no","Vulkan" +"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000100,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.000100,inplace=0","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000100,noncontig_rows=1","support","1","yes","Vulkan" "Vulkan0","RMS_NORM_BACK","type=f32,ne=[64,5,4,3],eps=0.000100","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000100,v=0","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000100,v=1","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000100","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000100,v=0,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000100,v=1,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.000100,v=0,noncontig_rows=1","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000100,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000100,inplace=0","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000100","support","0","no","Vulkan" +"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000100,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.000100,inplace=0","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.000100,noncontig_rows=1","support","1","yes","Vulkan" "Vulkan0","RMS_NORM_BACK","type=f32,ne=[1025,5,4,3],eps=0.000100","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000100,v=0","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000100,v=1","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.100000","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000100,v=0,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000100,v=1,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.000100,v=0,noncontig_rows=1","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.100000,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.100000,inplace=0","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.100000","support","0","no","Vulkan" +"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.100000,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[64,5,4,3],v=1,eps=0.100000,inplace=0","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.100000,noncontig_rows=1","support","1","yes","Vulkan" "Vulkan0","RMS_NORM_BACK","type=f32,ne=[64,5,4,3],eps=0.100000","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.100000,v=0","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.100000,v=1","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.100000","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.100000,v=0,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.100000,v=1,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=0.100000,v=0,noncontig_rows=1","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.100000,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.100000,inplace=0","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.100000","support","0","no","Vulkan" +"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.100000,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[1025,5,4,3],v=1,eps=0.100000,inplace=0","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=0.100000,noncontig_rows=1","support","1","yes","Vulkan" "Vulkan0","RMS_NORM_BACK","type=f32,ne=[1025,5,4,3],eps=0.100000","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.100000,v=0","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.100000,v=1","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=0,eps=10.000000","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.100000,v=0,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.100000,v=1,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=0.100000,v=0,noncontig_rows=1","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=0,eps=10.000000,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[64,5,4,3],v=0,eps=10.000000,inplace=0","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=1,eps=10.000000","support","0","no","Vulkan" +"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=1,eps=10.000000,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[64,5,4,3],v=1,eps=10.000000,inplace=0","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[64,5,4,3],v=0,eps=10.000000,noncontig_rows=1","support","1","yes","Vulkan" "Vulkan0","RMS_NORM_BACK","type=f32,ne=[64,5,4,3],eps=10.000000","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=10.000000,v=0","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=10.000000,v=1","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=10.000000","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=10.000000,v=0,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=10.000000,v=1,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[64,5,4,3],eps=10.000000,v=0,noncontig_rows=1","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=10.000000,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[1025,5,4,3],v=0,eps=10.000000,inplace=0","support","1","yes","Vulkan" -"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=10.000000","support","0","no","Vulkan" +"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=1,eps=10.000000,noncontig_rows=0","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[1025,5,4,3],v=1,eps=10.000000,inplace=0","support","1","yes","Vulkan" +"Vulkan0","NORM","type=f32,ne=[1025,5,4,3],v=0,eps=10.000000,noncontig_rows=1","support","1","yes","Vulkan" "Vulkan0","RMS_NORM_BACK","type=f32,ne=[1025,5,4,3],eps=10.000000","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=10.000000,v=0","support","1","yes","Vulkan" -"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=10.000000,v=1","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=10.000000,v=0,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=10.000000,v=1,noncontig_rows=0","support","1","yes","Vulkan" +"Vulkan0","L2_NORM","type=f32,ne=[1025,5,4,3],eps=10.000000,v=0,noncontig_rows=1","support","1","yes","Vulkan" "Vulkan0","RMS_NORM","type=f32,ne=[64,5,4,3],v=0,eps=0.000001,inplace=1","support","1","yes","Vulkan" "Vulkan0","SSM_CONV","type=f32,ne_a=[3,1024,1,1],ne_b=[3,1024,1,1]","support","1","yes","Vulkan" "Vulkan0","SSM_CONV","type=f32,ne_a=[6,1024,1,1],ne_b=[3,1024,1,1]","support","1","yes","Vulkan" @@ -6172,6 +8363,9 @@ "Vulkan0","SSM_SCAN","type=f32,d_state=128,head_dim=64,n_head=16,n_group=2,n_seq_tokens=32,n_seqs=4,xbc_overlap=0","support","1","yes","Vulkan" "Vulkan0","SSM_SCAN","type=f32,d_state=256,head_dim=64,n_head=8,n_group=2,n_seq_tokens=32,n_seqs=4,xbc_overlap=0","support","1","yes","Vulkan" "Vulkan0","SSM_SCAN","type=f32,d_state=128,head_dim=128,n_head=4,n_group=4,n_seq_tokens=16,n_seqs=2,xbc_overlap=1","support","1","yes","Vulkan" +"Vulkan0","SSM_SCAN","type=f32,d_state=128,head_dim=80,n_head=128,n_group=1,n_seq_tokens=256,n_seqs=1,xbc_overlap=0","support","1","yes","Vulkan" +"Vulkan0","SSM_SCAN","type=f32,d_state=128,head_dim=80,n_head=128,n_group=1,n_seq_tokens=512,n_seqs=1,xbc_overlap=0","support","1","yes","Vulkan" +"Vulkan0","SSM_SCAN","type=f32,d_state=128,head_dim=64,n_head=80,n_group=8,n_seq_tokens=300,n_seqs=2,xbc_overlap=0","support","1","yes","Vulkan" "Vulkan0","RWKV_WKV6","type=f32,head_count=32,head_size=64,n_seq_tokens=1,n_seqs=1","support","1","yes","Vulkan" "Vulkan0","RWKV_WKV6","type=f32,head_count=32,head_size=64,n_seq_tokens=32,n_seqs=1","support","1","yes","Vulkan" "Vulkan0","RWKV_WKV6","type=f32,head_count=32,head_size=64,n_seq_tokens=32,n_seqs=4","support","1","yes","Vulkan" @@ -6180,16 +8374,19 @@ "Vulkan0","RWKV_WKV7","type=f32,head_count=32,head_size=64,n_seq_tokens=32,n_seqs=1","support","1","yes","Vulkan" "Vulkan0","RWKV_WKV7","type=f32,head_count=32,head_size=64,n_seq_tokens=32,n_seqs=4","support","1","yes","Vulkan" "Vulkan0","RWKV_WKV7","type=f32,head_count=32,head_size=64,n_seq_tokens=128,n_seqs=4","support","1","yes","Vulkan" -"Vulkan0","GATED_LINEAR_ATTN","type=f32,head_count=32,head_size=64,n_seq_tokens=1,n_seqs=1","support","0","no","Vulkan" -"Vulkan0","GATED_LINEAR_ATTN","type=f32,head_count=32,head_size=64,n_seq_tokens=32,n_seqs=1","support","0","no","Vulkan" -"Vulkan0","GATED_LINEAR_ATTN","type=f32,head_count=32,head_size=64,n_seq_tokens=32,n_seqs=4","support","0","no","Vulkan" -"Vulkan0","GATED_LINEAR_ATTN","type=f32,head_count=32,head_size=64,n_seq_tokens=128,n_seqs=4","support","0","no","Vulkan" +"Vulkan0","GATED_LINEAR_ATTN","type=f32,head_count=32,head_size=64,n_seq_tokens=1,n_seqs=1","support","1","yes","Vulkan" +"Vulkan0","GATED_LINEAR_ATTN","type=f32,head_count=32,head_size=64,n_seq_tokens=32,n_seqs=1","support","1","yes","Vulkan" +"Vulkan0","GATED_LINEAR_ATTN","type=f32,head_count=32,head_size=64,n_seq_tokens=32,n_seqs=4","support","1","yes","Vulkan" +"Vulkan0","GATED_LINEAR_ATTN","type=f32,head_count=32,head_size=64,n_seq_tokens=128,n_seqs=4","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_HADAMARD","type_a=f32,type_b=f32,m=128,n=1,k=128,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_HADAMARD","type_a=f32,type_b=f32,m=64,n=1,k=64,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_HADAMARD","type_a=f32,type_b=f32,m=256,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_HADAMARD","type_a=f32,type_b=f32,m=512,n=1,k=512,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_HADAMARD","type_a=f32,type_b=f32,m=128,n=32,k=128,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_HADAMARD","type_a=f32,type_b=f32,m=128,n=4,k=128,bs=[2,3],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_HADAMARD","type_a=f32,type_b=f32,m=256,n=512,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_HADAMARD","type_a=f32,type_b=f32,m=32,n=1,k=32,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_HADAMARD","type_a=f32,type_b=f32,m=1024,n=1,k=1024,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" @@ -6271,6 +8468,15 @@ "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=4,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=5,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=6,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=2,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=3,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" @@ -6415,6 +8621,16 @@ "Vulkan0","MUL_MAT","type_a=iq4_xs,type_b=f32,m=16,n=7,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=iq4_xs,type_b=f32,m=16,n=8,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=iq4_xs,type_b=f32,m=16,n=9,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q4_0,type_b=f32,m=2880,n=32,k=2880,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q8_0,type_b=f32,m=2880,n=32,k=2880,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f32,m=2880,n=32,k=2880,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=1,n=1,k=2048,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=1,n=7,k=2048,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=1,n=8,k=2048,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=1,n=9,k=2048,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=1,n=16,k=2048,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=1,n=128,k=2048,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=1,n=512,k=2048,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6424,6 +8640,7 @@ "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6436,6 +8653,7 @@ "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" @@ -6451,6 +8669,7 @@ "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=4,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=16,k=4,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=16,k=4,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=16,k=4,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6463,6 +8682,7 @@ "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=4,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f32,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" @@ -6482,6 +8702,7 @@ "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6494,6 +8715,7 @@ "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" @@ -6509,6 +8731,7 @@ "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=4,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=16,k=4,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=16,k=4,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=16,k=4,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6521,6 +8744,7 @@ "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=4,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f32,type_b=f16,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" @@ -6540,6 +8764,7 @@ "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6552,6 +8777,7 @@ "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" @@ -6567,6 +8793,7 @@ "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=4,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=16,k=4,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=16,k=4,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=16,k=4,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6579,6 +8806,7 @@ "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=4,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f32,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" @@ -6598,6 +8826,7 @@ "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6610,6 +8839,7 @@ "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" @@ -6625,6 +8855,7 @@ "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=4,k=4,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=16,k=4,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=16,k=4,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=16,k=4,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6637,6 +8868,7 @@ "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=1,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=4,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=f16,type_b=f16,m=16,n=8,k=4,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","1","yes","Vulkan" @@ -6656,6 +8888,7 @@ "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6668,6 +8901,7 @@ "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" @@ -6687,6 +8921,7 @@ "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6699,6 +8934,7 @@ "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" @@ -6718,6 +8954,7 @@ "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6730,6 +8967,7 @@ "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" @@ -6749,6 +8987,7 @@ "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6761,6 +9000,7 @@ "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" @@ -6771,6 +9011,72 @@ "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f16,m=16,n=8,k=256,bs=[1536,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=8,k=256,bs=[1536,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[3,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=1,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=8,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=16,k=1024,bs=[3,2],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f16,m=16,n=8,k=256,bs=[1536,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6780,6 +9086,7 @@ "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6792,6 +9099,7 @@ "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" @@ -6811,6 +9119,7 @@ "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6823,6 +9132,7 @@ "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_0,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" @@ -6842,6 +9152,7 @@ "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6854,6 +9165,7 @@ "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" @@ -6873,6 +9185,7 @@ "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6885,6 +9198,7 @@ "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_1,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" @@ -6904,6 +9218,7 @@ "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6916,6 +9231,7 @@ "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" @@ -6935,6 +9251,7 @@ "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6947,6 +9264,7 @@ "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=q4_K,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" @@ -6966,6 +9284,7 @@ "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -6978,6 +9297,7 @@ "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" @@ -6997,6 +9317,7 @@ "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -7009,6 +9330,7 @@ "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" @@ -7028,6 +9350,7 @@ "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -7040,6 +9363,7 @@ "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" @@ -7059,6 +9383,7 @@ "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -7071,6 +9396,7 @@ "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" @@ -7090,6 +9416,7 @@ "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -7102,6 +9429,7 @@ "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f32,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" @@ -7121,6 +9449,7 @@ "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=4,k=256,bs=[3,2],nr=[2,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[2,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=16,k=256,bs=[1,1],nr=[1,2],per=[0,1,2,3],k_v=0,o=1","support","0","no","Vulkan" @@ -7133,6 +9462,7 @@ "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=1,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" +"Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=4,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,2,1,3],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,1,3,2],k_v=0,o=1","support","0","no","Vulkan" "Vulkan0","MUL_MAT","type_a=iq2_xxs,type_b=f16,m=16,n=8,k=256,bs=[2,3],nr=[1,1],per=[0,3,2,1],k_v=0,o=1","support","0","no","Vulkan" @@ -7162,6 +9492,8 @@ "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=1,k=128,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=64,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q2_K,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q3_K,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q5_K,type_b=f32,m=16,n=1,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" @@ -7197,6 +9529,7 @@ "Vulkan0","MUL_MAT","type_a=q5_1,type_b=f32,m=1,n=64,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q8_0,type_b=f32,m=1,n=64,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q1_0,type_b=f32,m=1,n=64,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT","type_a=q2_0,type_b=f32,m=1,n=64,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=mxfp4,type_b=f32,m=1,n=64,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=nvfp4,type_b=f32,m=1,n=64,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT","type_a=q2_K,type_b=f32,m=1,n=64,k=256,bs=[1,1],nr=[1,1],per=[0,1,2,3],k_v=0,o=1","support","1","yes","Vulkan" @@ -7606,6 +9939,33 @@ "Vulkan0","MUL_MAT_ID","type_a=f16,type_b=f32,n_mats=16,n_used=16,b=1,m=50,n=200,k=64","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_ID","type_a=f16,type_b=f32,n_mats=1,n_used=1,b=0,m=8,n=16,k=1","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_ID","type_a=mxfp4,type_b=f32,n_mats=32,n_used=2,b=0,m=2880,n=32,k=2880","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q4_0,type_b=f32,n_mats=32,n_used=2,b=0,m=2880,n=32,k=2880","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=f32,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=3","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=f16,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=3","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=bf16,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=3","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q4_0,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=96","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q4_1,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=96","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q5_0,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=96","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q5_1,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=96","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q8_0,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=96","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q1_0,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=384","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=192","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=mxfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=96","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=nvfp4,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=192","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_K,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q3_K,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q4_K,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q5_K,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q6_K,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=iq2_xxs,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=iq2_xs,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=iq2_s,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=iq3_xxs,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=iq1_s,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=iq1_m,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=iq4_nl,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=96","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=iq3_s,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=iq4_xs,type_b=f32,n_mats=4,n_used=2,b=0,m=64,n=16,k=768","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_ID","type_a=f32,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=1,k=256","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_ID","type_a=f32,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=4,k=256","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_ID","type_a=f32,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=5,k=256","support","1","yes","Vulkan" @@ -7894,6 +10254,78 @@ "Vulkan0","MUL_MAT_ID","type_a=q1_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=17,k=256","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_ID","type_a=q1_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=32,k=256","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_ID","type_a=q1_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=129,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=1,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=4,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=5,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=17,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=32,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=129,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=1,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=4,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=5,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=17,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=32,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=1,b=1,m=512,n=129,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=4,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=5,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=17,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=129,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=1,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=4,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=5,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=17,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=32,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=1,m=512,n=129,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=1,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=4,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=5,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=17,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=32,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=0,m=512,n=129,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=1,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=4,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=5,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=17,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=32,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=4,b=1,m=512,n=129,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=1,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=4,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=5,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=17,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=32,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=0,m=512,n=129,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=1,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=4,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=5,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=17,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=32,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=1,b=1,m=512,n=129,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=1,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=4,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=5,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=17,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=32,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=0,m=512,n=129,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=1,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=4,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=5,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=17,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=32,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=2,b=1,m=512,n=129,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=1,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=4,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=5,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=17,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=32,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=0,m=512,n=129,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=1,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=4,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=5,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=17,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=32,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=8,n_used=4,b=1,m=512,n=129,k=256","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_ID","type_a=q4_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=1,k=256","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_ID","type_a=q4_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=4,k=256","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_ID","type_a=q4_0,type_b=f32,n_mats=4,n_used=1,b=0,m=512,n=5,k=256","support","1","yes","Vulkan" @@ -8336,6 +10768,8 @@ "Vulkan0","MUL_MAT_ID","type_a=q8_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_ID","type_a=q1_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_ID","type_a=q1_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256","support","1","yes","Vulkan" +"Vulkan0","MUL_MAT_ID","type_a=q2_0,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_ID","type_a=q2_K,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_ID","type_a=q2_K,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_ID","type_a=q3_K,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256","support","1","yes","Vulkan" @@ -8362,70 +10796,70 @@ "Vulkan0","MUL_MAT_ID","type_a=iq4_xs,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_ID","type_a=bf16,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=1,k=256","support","1","yes","Vulkan" "Vulkan0","MUL_MAT_ID","type_a=bf16,type_b=f32,n_mats=4,n_used=2,b=0,m=512,n=32,k=256","support","1","yes","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0","support","1","yes","Vulkan" "Vulkan0","OUT_PROD","type_a=f32,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" "Vulkan0","OUT_PROD","type_a=f32,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" "Vulkan0","OUT_PROD","type_a=f32,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" @@ -8874,6 +11308,134 @@ "Vulkan0","OUT_PROD","type_a=q1_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" "Vulkan0","OUT_PROD","type_a=q1_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" "Vulkan0","OUT_PROD","type_a=q1_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f32,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=1,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=1,k=16,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=1,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[1,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[1,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[3,1],nr=[2,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=q2_0,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" "Vulkan0","OUT_PROD","type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" "Vulkan0","OUT_PROD","type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[1,2],trans_b=0","support","0","no","Vulkan" "Vulkan0","OUT_PROD","type_a=q4_0,type_b=f32,m=256,n=1,k=1,bs=[1,1],nr=[2,1],trans_b=0","support","0","no","Vulkan" @@ -9642,10 +12204,13 @@ "Vulkan0","OUT_PROD","type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[1,2],trans_b=0","support","0","no","Vulkan" "Vulkan0","OUT_PROD","type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,1],trans_b=0","support","0","no","Vulkan" "Vulkan0","OUT_PROD","type_a=iq2_xxs,type_b=f16,m=256,n=16,k=16,bs=[3,3],nr=[2,2],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[8,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[16,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" -"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[32,1],nr=[1,1],trans_b=0","support","0","no","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[8,1],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[16,1],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[32,1],nr=[1,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[8,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[16,1],trans_b=0","support","1","yes","Vulkan" +"Vulkan0","OUT_PROD","type_a=f32,type_b=f32,m=256,n=16,k=16,bs=[1,1],nr=[32,1],trans_b=0","support","1","yes","Vulkan" "Vulkan0","ADD_ID","type_a=f32,type_b=f32,n_embd=32,n_experts=4,n_experts_used=1,n_token=1","support","1","yes","Vulkan" "Vulkan0","ADD_ID","type_a=f32,type_b=f32,n_embd=32,n_experts=4,n_experts_used=1,n_token=32","support","1","yes","Vulkan" "Vulkan0","ADD_ID","type_a=f32,type_b=f32,n_embd=32,n_experts=4,n_experts_used=1,n_token=129","support","1","yes","Vulkan" @@ -9682,31 +12247,31 @@ "Vulkan0","ADD_ID","type_a=f32,type_b=f32,n_embd=129,n_experts=8,n_experts_used=4,n_token=1","support","1","yes","Vulkan" "Vulkan0","ADD_ID","type_a=f32,type_b=f32,n_embd=129,n_experts=8,n_experts_used=4,n_token=32","support","1","yes","Vulkan" "Vulkan0","ADD_ID","type_a=f32,type_b=f32,n_embd=129,n_experts=8,n_experts_used=4,n_token=129","support","1","yes","Vulkan" -"Vulkan0","SQR","type=f16,ne=[10,5,4,3]","support","0","no","Vulkan" -"Vulkan0","SQRT","type=f16,ne=[10,3,3,2]","support","0","no","Vulkan" +"Vulkan0","SQR","type=f16,ne=[10,5,4,3]","support","1","yes","Vulkan" +"Vulkan0","SQRT","type=f16,ne=[10,3,3,2]","support","1","yes","Vulkan" "Vulkan0","LOG","type=f16,ne=[10,5,4,3]","support","1","yes","Vulkan" -"Vulkan0","SIN","type=f16,ne=[10,2,2,2]","support","0","no","Vulkan" -"Vulkan0","COS","type=f16,ne=[10,2,2,2]","support","0","no","Vulkan" -"Vulkan0","CLAMP","type=f16,ne=[10,5,4,3],min=-0.500000,max=0.500000","support","0","no","Vulkan" -"Vulkan0","LEAKY_RELU","type=f16,ne_a=[10,5,4,3],negative_slope=0.100000","support","0","no","Vulkan" +"Vulkan0","SIN","type=f16,ne=[10,2,2,2]","support","1","yes","Vulkan" +"Vulkan0","COS","type=f16,ne=[10,2,2,2]","support","1","yes","Vulkan" +"Vulkan0","CLAMP","type=f16,ne=[10,5,4,3],min=-0.500000,max=0.500000","support","1","yes","Vulkan" +"Vulkan0","LEAKY_RELU","type=f16,ne_a=[10,5,4,3],negative_slope=0.100000","support","1","yes","Vulkan" "Vulkan0","FLOOR","type=f16,ne=[10,2,2,2]","support","1","yes","Vulkan" "Vulkan0","CEIL","type=f16,ne=[10,2,2,2]","support","1","yes","Vulkan" "Vulkan0","ROUND","type=f16,ne=[10,2,2,2]","support","1","yes","Vulkan" "Vulkan0","TRUNC","type=f16,ne=[10,2,2,2]","support","1","yes","Vulkan" -"Vulkan0","SQR","type=f16,ne=[7,1,5,3]","support","0","no","Vulkan" -"Vulkan0","SQR","type=f16,ne=[1024,1024,1,1]","support","0","no","Vulkan" -"Vulkan0","SQRT","type=f16,ne=[7,1,5,3]","support","0","no","Vulkan" -"Vulkan0","SQRT","type=f16,ne=[1024,1024,1,1]","support","0","no","Vulkan" +"Vulkan0","SQR","type=f16,ne=[7,1,5,3]","support","1","yes","Vulkan" +"Vulkan0","SQR","type=f16,ne=[1024,1024,1,1]","support","1","yes","Vulkan" +"Vulkan0","SQRT","type=f16,ne=[7,1,5,3]","support","1","yes","Vulkan" +"Vulkan0","SQRT","type=f16,ne=[1024,1024,1,1]","support","1","yes","Vulkan" "Vulkan0","LOG","type=f16,ne=[7,1,5,3]","support","1","yes","Vulkan" "Vulkan0","LOG","type=f16,ne=[1024,1024,1,1]","support","1","yes","Vulkan" -"Vulkan0","SIN","type=f16,ne=[7,1,5,3]","support","0","no","Vulkan" -"Vulkan0","SIN","type=f16,ne=[1024,1024,1,1]","support","0","no","Vulkan" -"Vulkan0","COS","type=f16,ne=[7,1,5,3]","support","0","no","Vulkan" -"Vulkan0","COS","type=f16,ne=[1024,1024,1,1]","support","0","no","Vulkan" -"Vulkan0","CLAMP","type=f16,ne=[7,1,5,3],min=-0.500000,max=0.500000","support","0","no","Vulkan" -"Vulkan0","CLAMP","type=f16,ne=[1024,1024,1,1],min=-0.500000,max=0.500000","support","0","no","Vulkan" -"Vulkan0","LEAKY_RELU","type=f16,ne_a=[7,1,5,3],negative_slope=0.100000","support","0","no","Vulkan" -"Vulkan0","LEAKY_RELU","type=f16,ne_a=[1024,1024,1,1],negative_slope=0.100000","support","0","no","Vulkan" +"Vulkan0","SIN","type=f16,ne=[7,1,5,3]","support","1","yes","Vulkan" +"Vulkan0","SIN","type=f16,ne=[1024,1024,1,1]","support","1","yes","Vulkan" +"Vulkan0","COS","type=f16,ne=[7,1,5,3]","support","1","yes","Vulkan" +"Vulkan0","COS","type=f16,ne=[1024,1024,1,1]","support","1","yes","Vulkan" +"Vulkan0","CLAMP","type=f16,ne=[7,1,5,3],min=-0.500000,max=0.500000","support","1","yes","Vulkan" +"Vulkan0","CLAMP","type=f16,ne=[1024,1024,1,1],min=-0.500000,max=0.500000","support","1","yes","Vulkan" +"Vulkan0","LEAKY_RELU","type=f16,ne_a=[7,1,5,3],negative_slope=0.100000","support","1","yes","Vulkan" +"Vulkan0","LEAKY_RELU","type=f16,ne_a=[1024,1024,1,1],negative_slope=0.100000","support","1","yes","Vulkan" "Vulkan0","FLOOR","type=f16,ne=[7,1,5,3]","support","1","yes","Vulkan" "Vulkan0","FLOOR","type=f16,ne=[1024,1024,1,1]","support","1","yes","Vulkan" "Vulkan0","CEIL","type=f16,ne=[7,1,5,3]","support","1","yes","Vulkan" @@ -10848,37 +13413,197 @@ "Vulkan0","ROPE","type=f16,ne_a=[128,32,2,1],n_dims=128,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1,inplace=1","support","1","yes","Vulkan" "Vulkan0","ROPE","type=f16,ne_a=[128,32,2,3],n_dims=128,mode=24,n_ctx=512,fs=1.424500,ef=0.746500,af=1.424500,ff=1,v=1,inplace=1","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=0","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=0","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=0","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=0","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=0","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=0","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=0","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=0","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=1","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=1","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=1","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=1","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=1","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=1","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=1","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=1","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=1","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=2","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=2","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=2","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=2","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=2","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=2","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=2","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=2","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=2","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=3","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=0,v=3","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=3","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=1,v=3","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=3","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=2,v=3","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=f32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=f16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=bf16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i8,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i16,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=3","support","1","yes","Vulkan" "Vulkan0","CONCAT","type=i32,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=i64,ne_a=[11,12,13,14],ne_b_d=7,dim=3,v=3","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=12","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=12","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=12","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=12","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=12","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=12","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=12","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q4_1,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=12","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=12","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=12","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=12","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=12","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=12","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=12","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=12","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q5_1,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=12","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=0","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=4","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=8","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=256,dim=0,v=12","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=1,v=12","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=2,v=12","support","1","yes","Vulkan" +"Vulkan0","CONCAT","type=q8_0,ne_a=[128,12,13,14],ne_b_d=7,dim=3,v=12","support","1","yes","Vulkan" "Vulkan0","ARGSORT","type=f32,ne=[3,1,1,1],order=0","support","1","yes","Vulkan" "Vulkan0","ARGSORT","type=f32,ne=[4,1,1,1],order=0","support","1","yes","Vulkan" "Vulkan0","ARGSORT","type=f32,ne=[7,1,1,1],order=0","support","1","yes","Vulkan" @@ -11426,6 +14151,42 @@ "Vulkan0","PAD","type=f32,ne_a=[11,22,33,44],lp0=1,rp0=2,lp1=3,rp1=4,lp2=5,rp2=6,lp3=7,rp3=8,tfrm=2,circular=0","support","1","yes","Vulkan" "Vulkan0","PAD","type=f32,ne_a=[512,512,1,1],lp0=0,rp0=1,lp1=0,rp1=1,lp2=0,rp2=0,lp3=0,rp3=0,tfrm=2,circular=1","support","1","yes","Vulkan" "Vulkan0","PAD","type=f32,ne_a=[11,22,33,44],lp0=1,rp0=2,lp1=3,rp1=4,lp2=5,rp2=6,lp3=7,rp3=8,tfrm=2,circular=1","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=8,nr23=[4,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=8,nr23=[4,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q8_0,type_V=q8_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=8,nr23=[4,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=8,nr23=[4,1],kv=1024,nb=64,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=8,nr23=[4,1],kv=1024,nb=64,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q8_0,type_V=q8_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=8,nr23=[4,1],kv=1024,nb=64,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=128,hsv=128,nh=8,nr23=[4,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=128,hsv=128,nh=8,nr23=[4,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q8_0,type_V=q8_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=128,hsv=128,nh=8,nr23=[4,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=128,hsv=128,nh=8,nr23=[4,1],kv=1024,nb=64,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=128,hsv=128,nh=8,nr23=[4,1],kv=1024,nb=64,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q8_0,type_V=q8_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=128,hsv=128,nh=8,nr23=[4,1],kv=1024,nb=64,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=256,hsv=256,nh=8,nr23=[4,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=256,hsv=256,nh=8,nr23=[4,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q8_0,type_V=q8_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=256,hsv=256,nh=8,nr23=[4,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=256,hsv=256,nh=8,nr23=[4,1],kv=1024,nb=64,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=256,hsv=256,nh=8,nr23=[4,1],kv=1024,nb=64,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q8_0,type_V=q8_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=256,hsv=256,nh=8,nr23=[4,1],kv=1024,nb=64,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=8,nr23=[4,1],kv=2048,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=8,nr23=[4,1],kv=2048,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q8_0,type_V=q8_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=8,nr23=[4,1],kv=2048,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=8,nr23=[4,1],kv=2048,nb=64,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=8,nr23=[4,1],kv=2048,nb=64,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q8_0,type_V=q8_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=8,nr23=[4,1],kv=2048,nb=64,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=128,hsv=128,nh=8,nr23=[4,1],kv=2048,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=128,hsv=128,nh=8,nr23=[4,1],kv=2048,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q8_0,type_V=q8_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=128,hsv=128,nh=8,nr23=[4,1],kv=2048,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=128,hsv=128,nh=8,nr23=[4,1],kv=2048,nb=64,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=128,hsv=128,nh=8,nr23=[4,1],kv=2048,nb=64,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q8_0,type_V=q8_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=128,hsv=128,nh=8,nr23=[4,1],kv=2048,nb=64,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=256,hsv=256,nh=8,nr23=[4,1],kv=2048,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=256,hsv=256,nh=8,nr23=[4,1],kv=2048,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q8_0,type_V=q8_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=256,hsv=256,nh=8,nr23=[4,1],kv=2048,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=256,hsv=256,nh=8,nr23=[4,1],kv=2048,nb=64,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=256,hsv=256,nh=8,nr23=[4,1],kv=2048,nb=64,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q8_0,type_V=q8_0,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=256,hsv=256,nh=8,nr23=[4,1],kv=2048,nb=64,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=40,hsv=40,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=40,hsv=40,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=40,hsv=40,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11658,7 +14419,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11667,7 +14428,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11676,7 +14437,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11685,7 +14446,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11702,8 +14463,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11720,8 +14481,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11738,8 +14499,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11756,8 +14517,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11766,7 +14527,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11775,7 +14536,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11784,7 +14545,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11793,7 +14554,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11810,8 +14571,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11828,8 +14589,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11846,8 +14607,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11864,8 +14625,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11874,7 +14635,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11883,7 +14644,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11892,7 +14653,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11901,7 +14662,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11918,8 +14679,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11936,8 +14697,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11954,8 +14715,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11972,8 +14733,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11982,7 +14743,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -11991,7 +14752,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12000,7 +14761,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12009,7 +14770,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12026,8 +14787,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12044,8 +14805,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12062,8 +14823,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12080,8 +14841,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12090,7 +14851,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12099,7 +14860,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12108,7 +14869,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12117,7 +14878,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12126,7 +14887,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12135,7 +14896,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12144,7 +14905,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12153,7 +14914,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12162,7 +14923,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12171,7 +14932,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12180,7 +14941,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12189,7 +14950,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12198,7 +14959,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12207,7 +14968,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12216,7 +14977,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12225,7 +14986,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12234,7 +14995,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12243,7 +15004,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12252,7 +15013,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12261,7 +15022,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12270,7 +15031,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12279,7 +15040,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12288,7 +15049,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12297,7 +15058,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12306,7 +15067,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12315,7 +15076,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12324,7 +15085,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12333,7 +15094,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12342,7 +15103,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12351,7 +15112,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12360,7 +15121,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12369,7 +15130,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12378,7 +15139,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12387,7 +15148,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12396,7 +15157,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12405,7 +15166,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12422,8 +15183,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12440,8 +15201,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12458,8 +15219,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12476,8 +15237,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12486,7 +15247,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12495,7 +15256,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12504,7 +15265,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12513,7 +15274,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12530,8 +15291,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12548,8 +15309,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12566,8 +15327,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12584,8 +15345,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12594,7 +15355,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12603,7 +15364,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12612,7 +15373,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12621,7 +15382,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12638,8 +15399,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12656,8 +15417,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12674,8 +15435,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12692,8 +15453,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12702,7 +15463,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12711,7 +15472,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12720,7 +15481,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12729,7 +15490,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12746,8 +15507,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12764,8 +15525,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12782,8 +15543,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12800,8 +15561,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12810,7 +15571,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12819,7 +15580,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12828,7 +15589,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12837,7 +15598,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12846,7 +15607,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12855,7 +15616,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12864,7 +15625,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12873,7 +15634,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12882,7 +15643,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12891,7 +15652,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12900,7 +15661,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12909,7 +15670,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12918,7 +15679,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12927,7 +15688,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12936,7 +15697,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12945,7 +15706,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12954,7 +15715,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12963,7 +15724,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12972,7 +15733,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12981,7 +15742,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12990,7 +15751,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -12999,7 +15760,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13008,7 +15769,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13017,7 +15778,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13026,7 +15787,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13035,7 +15796,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13044,7 +15805,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13053,7 +15814,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13062,7 +15823,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13071,7 +15832,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13080,7 +15841,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13089,7 +15850,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13098,7 +15859,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13107,7 +15868,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13116,7 +15877,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13125,7 +15886,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13134,7 +15895,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13143,7 +15904,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13152,7 +15913,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13161,7 +15922,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13170,7 +15931,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13179,7 +15940,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13188,7 +15949,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13197,7 +15958,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13206,7 +15967,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13215,7 +15976,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13224,7 +15985,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13233,7 +15994,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13242,7 +16003,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13251,7 +16012,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13260,7 +16021,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13269,7 +16030,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13278,7 +16039,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13287,7 +16048,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13296,7 +16057,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13305,7 +16066,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13314,7 +16075,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13323,7 +16084,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13332,7 +16093,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13341,7 +16102,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13350,7 +16111,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13359,7 +16120,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13368,7 +16129,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13377,7 +16138,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13386,7 +16147,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13395,7 +16156,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13404,7 +16165,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13413,7 +16174,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13422,7 +16183,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13431,7 +16192,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13440,7 +16201,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13449,7 +16210,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13458,7 +16219,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13467,7 +16228,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13476,7 +16237,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13485,7 +16246,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13494,7 +16255,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13503,7 +16264,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13512,7 +16273,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13521,7 +16282,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13530,7 +16291,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13539,7 +16300,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13548,7 +16309,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13557,7 +16318,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13566,7 +16327,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13575,7 +16336,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13584,7 +16345,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13593,7 +16354,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13602,7 +16363,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13611,7 +16372,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13620,7 +16381,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13629,7 +16390,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[1,3],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13638,7 +16399,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13647,7 +16408,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13656,7 +16417,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13665,7 +16426,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=64,nh=4,nr23=[4,3],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13674,7 +16435,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13683,7 +16444,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13692,7 +16453,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13701,7 +16462,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13718,8 +16479,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13736,8 +16497,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13754,8 +16515,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13772,8 +16533,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13782,7 +16543,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13791,7 +16552,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13800,7 +16561,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13809,7 +16570,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13826,8 +16587,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13844,8 +16605,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13862,8 +16623,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13880,8 +16641,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13890,7 +16651,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13899,7 +16660,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13908,7 +16669,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13917,7 +16678,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13926,7 +16687,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13935,7 +16696,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13944,7 +16705,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13953,7 +16714,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13962,7 +16723,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13971,7 +16732,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13980,7 +16741,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13989,7 +16750,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -13998,7 +16759,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14007,7 +16768,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14016,7 +16777,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14025,7 +16786,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=1,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14034,7 +16795,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14043,7 +16804,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14052,7 +16813,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14061,7 +16822,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14078,8 +16839,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14096,8 +16857,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14114,8 +16875,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14132,8 +16893,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14142,7 +16903,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14151,7 +16912,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14160,7 +16921,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14169,7 +16930,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14186,8 +16947,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14204,8 +16965,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14222,8 +16983,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14240,8 +17001,8 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,2,1,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,2,1,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14250,7 +17011,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14259,7 +17020,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14268,7 +17029,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14277,7 +17038,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14286,7 +17047,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14295,7 +17056,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14304,7 +17065,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14313,7 +17074,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14322,7 +17083,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14331,7 +17092,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14340,7 +17101,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14349,7 +17110,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14358,7 +17119,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14367,7 +17128,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14376,7 +17137,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14385,7 +17146,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=1,sinks=0,max_bias=8.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14394,7 +17155,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14403,7 +17164,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14412,7 +17173,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14421,7 +17182,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14430,7 +17191,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14439,7 +17200,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14448,7 +17209,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14457,7 +17218,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14466,7 +17227,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14475,7 +17236,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14484,7 +17245,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14493,7 +17254,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14502,7 +17263,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14511,7 +17272,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14520,7 +17281,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14529,7 +17290,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14538,7 +17299,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14547,7 +17308,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14556,7 +17317,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14565,7 +17326,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=113,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14574,7 +17335,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14583,7 +17344,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14592,7 +17353,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14601,7 +17362,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14610,7 +17371,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14619,7 +17380,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14628,7 +17389,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14637,7 +17398,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[1,1],kv=1024,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14646,7 +17407,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=1,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14655,7 +17416,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=3,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14664,7 +17425,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=32,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f32,type_V=f32,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=bf16,type_V=bf16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -14673,7 +17434,7 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q5_0,type_V=q5_0,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_1,type_V=q4_1,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q4_0,permute=[0,1,2,3]","support","1","yes","Vulkan" -"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=72,hsv=72,nh=4,nr23=[4,1],kv=512,nb=75,mask=0,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=iq4_nl,type_V=iq4_nl,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=80,hsv=80,nh=4,nr23=[1,1],kv=113,nb=1,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=80,hsv=80,nh=4,nr23=[1,1],kv=113,nb=3,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=80,hsv=80,nh=4,nr23=[1,1],kv=113,nb=32,mask=1,sinks=1,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" @@ -16523,6 +19284,14 @@ "Vulkan0","FLASH_ATTN_EXT","hsk=128,hsv=64,nh=4,nr23=[1,1],kv=128,nb=2,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q1_0,type_V=q4_0,permute=[0,1,2,3]","support","0","no","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=128,nh=4,nr23=[1,1],kv=128,nb=2,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q1_0,permute=[0,1,2,3]","support","0","no","Vulkan" "Vulkan0","FLASH_ATTN_EXT","hsk=128,hsv=64,nh=4,nr23=[1,1],kv=64,nb=2,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q1_0,type_V=f16,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=128,hsv=128,nh=4,nr23=[1,1],kv=96,nb=2,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q2_0,type_V=q2_0,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=128,hsv=64,nh=4,nr23=[1,1],kv=128,nb=2,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q2_0,type_V=q4_0,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=64,hsv=128,nh=4,nr23=[1,1],kv=128,nb=2,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q4_0,type_V=q2_0,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=128,hsv=64,nh=4,nr23=[1,1],kv=64,nb=2,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=q2_0,type_V=f16,permute=[0,1,2,3]","support","0","no","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=256,hsv=256,nh=4,nr23=[6,1],kv=4096,nb=512,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=128,hsv=128,nh=8,nr23=[4,1],kv=4096,nb=512,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=256,hsv=256,nh=4,nr23=[6,1],kv=16384,nb=512,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" +"Vulkan0","FLASH_ATTN_EXT","hsk=128,hsv=128,nh=8,nr23=[4,1],kv=16384,nb=512,mask=1,sinks=0,max_bias=0.000000,logit_softcap=0.000000,prec=f32,type_K=f16,type_V=f16,permute=[0,1,2,3]","support","1","yes","Vulkan" "Vulkan0","CROSS_ENTROPY_LOSS","type=f32,ne=[10,5,4,3]","support","0","no","Vulkan" "Vulkan0","CROSS_ENTROPY_LOSS","type=f32,ne=[30000,1,1,1]","support","0","no","Vulkan" "Vulkan0","CROSS_ENTROPY_LOSS_BACK","type=f32,ne=[10,5,4,3]","support","0","no","Vulkan" @@ -16530,9 +19299,9 @@ "Vulkan0","OPT_STEP_ADAMW","type=f32,ne=[10,5,4,3]","support","1","yes","Vulkan" "Vulkan0","OPT_STEP_SGD","type=f32,ne=[10,5,4,3]","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=32,head_size=128,n_seq_tokens=1,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","Vulkan" -"Vulkan0","GATED_DELTA_NET","type=f32,head_count=32,head_size=16,n_seq_tokens=1,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=1","support","0","no","Vulkan" -"Vulkan0","GATED_DELTA_NET","type=f32,head_count=32,head_size=16,n_seq_tokens=1,n_seqs=1,v_repeat=1,permuted=1,kda=1,K=1","support","0","no","Vulkan" -"Vulkan0","GATED_DELTA_NET","type=f32,head_count=32,head_size=16,n_seq_tokens=1,n_seqs=1,v_repeat=1,permuted=0,kda=1,K=1","support","0","no","Vulkan" +"Vulkan0","GATED_DELTA_NET","type=f32,head_count=32,head_size=16,n_seq_tokens=1,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","Vulkan" +"Vulkan0","GATED_DELTA_NET","type=f32,head_count=32,head_size=16,n_seq_tokens=1,n_seqs=1,v_repeat=1,permuted=1,kda=1,K=1","support","1","yes","Vulkan" +"Vulkan0","GATED_DELTA_NET","type=f32,head_count=32,head_size=16,n_seq_tokens=1,n_seqs=1,v_repeat=1,permuted=0,kda=1,K=1","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=16,head_size=64,n_seq_tokens=1,n_seqs=2,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=2,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","Vulkan" @@ -16541,12 +19310,12 @@ "Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=1,v_repeat=1,permuted=1,kda=0,K=1","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=1,n_seqs=1,v_repeat=1,permuted=0,kda=1,K=1","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=1,n_seqs=2,v_repeat=1,permuted=0,kda=1,K=1","support","1","yes","Vulkan" -"Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=16,n_seq_tokens=1,n_seqs=2,v_repeat=1,permuted=0,kda=1,K=1","support","0","no","Vulkan" +"Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=16,n_seq_tokens=1,n_seqs=2,v_repeat=1,permuted=0,kda=1,K=1","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=32,n_seq_tokens=4,n_seqs=1,v_repeat=1,permuted=0,kda=1,K=1","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=2,v_repeat=1,permuted=0,kda=1,K=1","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=8,head_size=32,n_seq_tokens=4,n_seqs=2,v_repeat=2,permuted=0,kda=1,K=1","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=2,v_repeat=1,permuted=1,kda=1,K=1","support","1","yes","Vulkan" -"Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=16,n_seq_tokens=4,n_seqs=2,v_repeat=1,permuted=1,kda=1,K=1","support","0","no","Vulkan" +"Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=16,n_seq_tokens=4,n_seqs=2,v_repeat=1,permuted=1,kda=1,K=1","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=64,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=127,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=256,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=1","support","1","yes","Vulkan" @@ -16557,7 +19326,7 @@ "Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=64,n_seqs=1,v_repeat=1,permuted=0,kda=1,K=1","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=33,n_seqs=1,v_repeat=1,permuted=0,kda=1,K=1","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=100,n_seqs=1,v_repeat=1,permuted=0,kda=1,K=1","support","1","yes","Vulkan" -"Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=16,n_seq_tokens=2,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=2","support","0","no","Vulkan" +"Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=16,n_seq_tokens=2,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=2","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=32,n_seq_tokens=4,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=4","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=4,n_seqs=2,v_repeat=1,permuted=0,kda=0,K=4","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=8,head_size=128,n_seq_tokens=4,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=4","support","1","yes","Vulkan" @@ -16565,3 +19334,111 @@ "Vulkan0","GATED_DELTA_NET","type=f32,head_count=8,head_size=32,n_seq_tokens=4,n_seqs=2,v_repeat=2,permuted=0,kda=1,K=4","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=32,n_seq_tokens=8,n_seqs=1,v_repeat=1,permuted=0,kda=0,K=3","support","1","yes","Vulkan" "Vulkan0","GATED_DELTA_NET","type=f32,head_count=4,head_size=64,n_seq_tokens=16,n_seqs=2,v_repeat=1,permuted=0,kda=0,K=4","support","1","yes","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=1,nm=1,type_K=f32","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=1,nm=1,type_K=f16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=1,nm=1,type_K=bf16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=1,nm=1,type_K=q8_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=1,nm=1,type_K=q5_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=1,nm=1,type_K=q5_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=1,nm=1,type_K=q4_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=1,nm=1,type_K=q4_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=1,nm=1,type_K=iq4_nl","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=4,type_K=f32","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=4,type_K=f16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=4,type_K=bf16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=4,type_K=q8_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=4,type_K=q5_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=4,type_K=q5_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=4,type_K=q4_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=4,type_K=q4_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=4,type_K=iq4_nl","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=1,type_K=f32","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=1,type_K=f16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=1,type_K=bf16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=1,type_K=q8_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=1,type_K=q5_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=1,type_K=q5_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=1,type_K=q4_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=1,type_K=q4_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=1,ns=4,nm=1,type_K=iq4_nl","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=1,nm=1,type_K=f32","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=1,nm=1,type_K=f16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=1,nm=1,type_K=bf16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=1,nm=1,type_K=q8_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=1,nm=1,type_K=q5_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=1,nm=1,type_K=q5_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=1,nm=1,type_K=q4_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=1,nm=1,type_K=q4_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=1,nm=1,type_K=iq4_nl","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=4,type_K=f32","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=4,type_K=f16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=4,type_K=bf16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=4,type_K=q8_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=4,type_K=q5_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=4,type_K=q5_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=4,type_K=q4_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=4,type_K=q4_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=4,type_K=iq4_nl","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=1,type_K=f32","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=1,type_K=f16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=1,type_K=bf16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=1,type_K=q8_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=1,type_K=q5_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=1,type_K=q5_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=1,type_K=q4_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=1,type_K=q4_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=1,ns=4,nm=1,type_K=iq4_nl","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=1,nm=1,type_K=f32","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=1,nm=1,type_K=f16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=1,nm=1,type_K=bf16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=1,nm=1,type_K=q8_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=1,nm=1,type_K=q5_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=1,nm=1,type_K=q5_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=1,nm=1,type_K=q4_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=1,nm=1,type_K=q4_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=1,nm=1,type_K=iq4_nl","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=4,type_K=f32","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=4,type_K=f16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=4,type_K=bf16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=4,type_K=q8_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=4,type_K=q5_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=4,type_K=q5_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=4,type_K=q4_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=4,type_K=q4_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=4,type_K=iq4_nl","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=1,type_K=f32","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=1,type_K=f16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=1,type_K=bf16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=1,type_K=q8_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=1,type_K=q5_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=1,type_K=q5_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=1,type_K=q4_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=1,type_K=q4_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=32,kv=256,nb=512,ns=4,nm=1,type_K=iq4_nl","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=1,nm=1,type_K=f32","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=1,nm=1,type_K=f16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=1,nm=1,type_K=bf16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=1,nm=1,type_K=q8_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=1,nm=1,type_K=q5_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=1,nm=1,type_K=q5_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=1,nm=1,type_K=q4_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=1,nm=1,type_K=q4_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=1,nm=1,type_K=iq4_nl","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=4,type_K=f32","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=4,type_K=f16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=4,type_K=bf16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=4,type_K=q8_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=4,type_K=q5_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=4,type_K=q5_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=4,type_K=q4_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=4,type_K=q4_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=4,type_K=iq4_nl","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=1,type_K=f32","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=1,type_K=f16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=1,type_K=bf16","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=1,type_K=q8_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=1,type_K=q5_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=1,type_K=q5_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=1,type_K=q4_1","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=1,type_K=q4_0","support","0","no","Vulkan" +"Vulkan0","LIGHTNING_INDEXER","hsk=128,nh=64,kv=256,nb=512,ns=4,nm=1,type_K=iq4_nl","support","0","no","Vulkan" diff --git a/examples/gen-docs/gen-docs.cpp b/examples/gen-docs/gen-docs.cpp index baf61bf27b54..114416719c7f 100644 --- a/examples/gen-docs/gen-docs.cpp +++ b/examples/gen-docs/gen-docs.cpp @@ -70,6 +70,8 @@ static void write_table(std::ostringstream & ss, std::vector & opt static void write_help(std::ostringstream & ss, const md_file & md) { common_params params; + params.is_gen_docs = true; + auto ctx_arg = common_params_parser_init(params, md.ex); std::vector common_options; diff --git a/ggml/CMakeLists.txt b/ggml/CMakeLists.txt index 159da3afa0b0..6c7337edd398 100644 --- a/ggml/CMakeLists.txt +++ b/ggml/CMakeLists.txt @@ -5,7 +5,7 @@ project("ggml" C CXX ASM) ### GGML Version set(GGML_VERSION_MAJOR 0) set(GGML_VERSION_MINOR 18) -set(GGML_VERSION_PATCH 0) +set(GGML_VERSION_PATCH 1) set(GGML_VERSION_BASE "${GGML_VERSION_MAJOR}.${GGML_VERSION_MINOR}.${GGML_VERSION_PATCH}") list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/cmake/") diff --git a/ggml/src/ggml-backend.cpp b/ggml/src/ggml-backend.cpp index 7f4e252dca39..f6fb91798ca4 100644 --- a/ggml/src/ggml-backend.cpp +++ b/ggml/src/ggml-backend.cpp @@ -765,8 +765,9 @@ struct ggml_backend_sched_split { int backend_id; int i_start; int i_end; - struct ggml_tensor * inputs[GGML_SCHED_MAX_SPLIT_INPUTS]; + struct ggml_tensor ** inputs; int n_inputs; + int inputs_capacity; // graph view of this split struct ggml_cgraph graph; }; @@ -805,8 +806,9 @@ struct ggml_backend_sched { int cur_copy; int next_copy; ggml_backend_event_t events[GGML_SCHED_MAX_BACKENDS][GGML_SCHED_MAX_COPIES]; - struct ggml_tensor * graph_inputs[GGML_SCHED_MAX_SPLIT_INPUTS]; + struct ggml_tensor ** graph_inputs; int n_graph_inputs; + int graph_inputs_capacity; struct ggml_context * ctx; @@ -832,6 +834,36 @@ struct ggml_backend_sched { #define tensor_id_copy(id, backend_id, copy_id) sched->hv_tensor_copies[(id) * sched->n_backends * sched->n_copies + (backend_id) * sched->n_copies + (copy_id)] #define tensor_copy(tensor, backend_id, copy_id) tensor_id_copy(hash_id(tensor), backend_id, copy_id) +static void ggml_backend_sched_split_inputs_grow(struct ggml_backend_sched_split * split) { + int new_cap = GGML_SCHED_MAX_SPLIT_INPUTS; + if (split->inputs_capacity > 0) { + new_cap = 2*split->inputs_capacity; + GGML_LOG_WARN("%s: increasing split inputs capacity from %d to %d\n", __func__, split->inputs_capacity, new_cap); + } + auto * pnew = (struct ggml_tensor **) realloc((void *) split->inputs, new_cap * sizeof(struct ggml_tensor *)); + if (pnew == NULL) { + GGML_LOG_ERROR("%s: failed to allocate %zu bytes\n", __func__, new_cap * sizeof(struct ggml_tensor *)); + GGML_ABORT("failed to grow split inputs container"); + } + split->inputs = pnew; + split->inputs_capacity = new_cap; +} + +static void ggml_backend_sched_graph_inputs_grow(ggml_backend_sched_t sched) { + int new_cap = GGML_SCHED_MAX_SPLIT_INPUTS; + if (sched->graph_inputs_capacity > 0) { + new_cap = 2*sched->graph_inputs_capacity; + GGML_LOG_WARN("%s: increasing graph inputs capacity from %d to %d\n", __func__, sched->graph_inputs_capacity, new_cap); + } + auto * pnew = (struct ggml_tensor **) realloc((void *) sched->graph_inputs, new_cap * sizeof(struct ggml_tensor *)); + if (pnew == NULL) { + GGML_LOG_ERROR("%s: failed to allocate %zu bytes\n", __func__, new_cap * sizeof(struct ggml_tensor *)); + GGML_ABORT("failed to grow graph inputs container"); + } + sched->graph_inputs = pnew; + sched->graph_inputs_capacity = new_cap; +} + // returns the priority of the backend, lower id is higher priority static int ggml_backend_sched_backend_id(ggml_backend_sched_t sched, ggml_backend_t backend) { for (int i = 0; i < sched->n_backends; i++) { @@ -1297,7 +1329,7 @@ void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct ggml_cgra } // check if the split has too many inputs // FIXME: count the number of inputs instead of only checking when full - if (split->n_inputs == GGML_SCHED_MAX_SPLIT_INPUTS) { + if (split->n_inputs >= split->inputs_capacity) { const size_t id = hash_id(src); int src_backend_id = sched->hv_tensor_backend_ids[id]; bool supported = ggml_backend_sched_buffer_supported(sched, src, cur_backend_id); @@ -1313,10 +1345,14 @@ void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct ggml_cgra split->i_end = i; i_split++; if (i_split >= sched->splits_capacity) { + int old_cap = sched->splits_capacity; sched->splits_capacity *= 2; sched->splits = (ggml_backend_sched_split *) realloc(sched->splits, sched->splits_capacity * sizeof(struct ggml_backend_sched_split)); GGML_ASSERT(sched->splits != NULL); + for (int k = old_cap; k < sched->splits_capacity; k++) { + memset(&sched->splits[k], 0, sizeof(struct ggml_backend_sched_split)); + } } split = &sched->splits[i_split]; split->backend_id = node_backend_id; @@ -1353,7 +1389,9 @@ void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct ggml_cgra SET_CAUSE(tensor_copy, "4.cpy"); } int n_graph_inputs = sched->n_graph_inputs++; - GGML_ASSERT(n_graph_inputs < GGML_SCHED_MAX_SPLIT_INPUTS); + if (n_graph_inputs >= sched->graph_inputs_capacity) { + ggml_backend_sched_graph_inputs_grow(sched); + } sched->graph_inputs[n_graph_inputs] = src; } } @@ -1373,7 +1411,9 @@ void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct ggml_cgra SET_CAUSE(tensor_copy, "4.cpy"); } int n_inputs = split->n_inputs++; - GGML_ASSERT(n_inputs < GGML_SCHED_MAX_SPLIT_INPUTS); + if (n_inputs >= split->inputs_capacity) { + ggml_backend_sched_split_inputs_grow(split); + } split->inputs[n_inputs] = src; } node->src[j] = tensor_id_copy(src_id, cur_backend_id, sched->cur_copy); @@ -1399,7 +1439,11 @@ void ggml_backend_sched_split_graph(ggml_backend_sched_t sched, struct ggml_cgra sched->prev_leaf_backend_ids = tmp; } - int graph_size = std::max(graph->n_nodes, graph->n_leafs) + sched->n_splits*GGML_SCHED_MAX_SPLIT_INPUTS*2*sched->n_copies; + int total_inputs = sched->n_graph_inputs; + for (int i = 0; i < sched->n_splits; i++) { + total_inputs += sched->splits[i].n_inputs; + } + int graph_size = std::max(graph->n_nodes, graph->n_leafs) + total_inputs * 2 * sched->n_copies; // remember the actual graph_size for performing reallocation checks later [GGML_SCHED_DEBUG_REALLOC] sched->debug_prev_graph_size = sched->debug_graph_size; @@ -1782,6 +1826,9 @@ ggml_backend_sched_t ggml_backend_sched_new( sched->splits = (ggml_backend_sched_split *) calloc(initial_splits_capacity, sizeof(sched->splits[0])); sched->splits_capacity = initial_splits_capacity; + sched->graph_inputs_capacity = GGML_SCHED_MAX_SPLIT_INPUTS; + sched->graph_inputs = (struct ggml_tensor **) calloc(sched->graph_inputs_capacity, sizeof(struct ggml_tensor *)); + for (int b = 0; b < n_backends; b++) { sched->backends[b] = backends[b]; sched->bufts[b] = bufts ? bufts[b] : ggml_backend_get_default_buffer_type(backends[b]); @@ -1814,7 +1861,11 @@ void ggml_backend_sched_free(ggml_backend_sched_t sched) { ggml_gallocr_free(sched->galloc); ggml_free(sched->ctx); ggml_hash_set_free(&sched->hash_set); + for (int i = 0; i < sched->splits_capacity; i++) { + free(sched->splits[i].inputs); + } free(sched->splits); + free(sched->graph_inputs); free(sched->hv_tensor_backend_ids); free(sched->hv_tensor_copies); free(sched->node_backend_ids); diff --git a/ggml/src/ggml-cuda/common.cuh b/ggml/src/ggml-cuda/common.cuh index 33be16dc5cce..d27d8acb1d37 100644 --- a/ggml/src/ggml-cuda/common.cuh +++ b/ggml/src/ggml-cuda/common.cuh @@ -627,7 +627,8 @@ template struct block_reduce_policy { }; template -static __device__ T block_reduce(T val, T * shared_vals) { +static __device__ T block_reduce(T val, [[maybe_unused]] T * shared_vals) { + // for multi-warp reductions, callers must not reuse shared_vals until all reads from this invocation have completed val = block_reduce_policy::reduce(val); const unsigned int block_size = block_size_template == 0 ? blockDim.x : block_size_template; if (block_size > WARP_SIZE) { diff --git a/ggml/src/ggml-cuda/mmq-load-tiles.cuh b/ggml/src/ggml-cuda/mmq-load-tiles.cuh index 8c9070c6bebf..8ed704c281a4 100644 --- a/ggml/src/ggml-cuda/mmq-load-tiles.cuh +++ b/ggml/src/ggml-cuda/mmq-load-tiles.cuh @@ -130,43 +130,27 @@ template static __device__ __forceinline_ } const block_q2_0 * bxi = (const block_q2_0 *) x + kbx0 + i*stride + kbx; - // Each 32-element chunk occupies 8 bytes of qs (32 elements * 2 bits = 64 bits) - const int qs_offset = 8*kqsx; - const int qs0 = bxi->qs[qs_offset + 0] | (bxi->qs[qs_offset + 1] << 8) | - (bxi->qs[qs_offset + 2] << 16) | (bxi->qs[qs_offset + 3] << 24); - const int qs1 = bxi->qs[qs_offset + 4] | (bxi->qs[qs_offset + 5] << 8) | - (bxi->qs[qs_offset + 6] << 16) | (bxi->qs[qs_offset + 7] << 24); - - // Unpack 32 2-bit codes into 8 int32s, each holding 4 signed int8s in {-1,0,1,2}. - int unpacked_bytes[8]; -#pragma unroll - for (int j = 0; j < 4; ++j) { - const int shift = j * 8; - const int codes = (qs0 >> shift) & 0xFF; - const int c0 = ((codes >> 0) & 0x3) - 1; - const int c1 = ((codes >> 2) & 0x3) - 1; - const int c2 = ((codes >> 4) & 0x3) - 1; - const int c3 = ((codes >> 6) & 0x3) - 1; - unpacked_bytes[j] = (c0 & 0xFF) | ((c1 & 0xFF) << 8) | ((c2 & 0xFF) << 16) | ((c3 & 0xFF) << 24); - } -#pragma unroll - for (int j = 0; j < 4; ++j) { - const int shift = j * 8; - const int codes = (qs1 >> shift) & 0xFF; - const int c0 = ((codes >> 0) & 0x3) - 1; - const int c1 = ((codes >> 2) & 0x3) - 1; - const int c2 = ((codes >> 4) & 0x3) - 1; - const int c3 = ((codes >> 6) & 0x3) - 1; - unpacked_bytes[4 + j] = (c0 & 0xFF) | ((c1 & 0xFF) << 8) | ((c2 & 0xFF) << 16) | ((c3 & 0xFF) << 24); - } + const int16_t * qxi = (const int16_t *) bxi->qs + kqsx * 4; const int dst_offset = kbx*(scale_entries_per_block*QI8_0) + kqsx*QI8_0; + #pragma unroll - for (int j = 0; j < 8; ++j) { + for (int j = 0; j < 4; ++j) { + const int q = qxi[j]; + + // unpack even and odd crumbs into byte values + const int qe = __byte_perm(0x020100FF, 0x020100FF, q >> 0); + const int qo = __byte_perm(0x020100FF, 0x020100FF, q >> 2); + // unshuffle values + const int qx = __byte_perm(qe, qo, 0x5140); + const int qy = __byte_perm(qe, qo, 0x7362); + #if defined(AMD_MFMA_AVAILABLE) || defined(TURING_MMA_AVAILABLE) || defined(AMD_WMMA_AVAILABLE) - x_qs[i*sram_stride + dst_offset + j] = unpacked_bytes[j]; + x_qs[i*sram_stride + dst_offset + j*2+0] = qx; + x_qs[i*sram_stride + dst_offset + j*2+1] = qy; #else - x_qs[i*(2*MMQ_TILE_NE_K + 1) + dst_offset + j] = unpacked_bytes[j]; + x_qs[i*(2*MMQ_TILE_NE_K + 1) + dst_offset + j*2+0] = qx; + x_qs[i*(2*MMQ_TILE_NE_K + 1) + dst_offset + j*2+1] = qy; #endif // defined(AMD_MFMA_AVAILABLE) || defined(TURING_MMA_AVAILABLE) || defined(AMD_WMMA_AVAILABLE) } } diff --git a/ggml/src/ggml-cuda/norm.cu b/ggml/src/ggml-cuda/norm.cu index 09d9f3a7d624..c3758cd50cfe 100644 --- a/ggml/src/ggml-cuda/norm.cu +++ b/ggml/src/ggml-cuda/norm.cu @@ -64,7 +64,7 @@ static __global__ void group_norm_f32(const float * x, float * dst, const int gr tmp += xi * xi; } - tmp = block_reduce(tmp, s_sum); + tmp = block_reduce(tmp, s_sum + 32); const float variance = tmp / group_size; const float scale = rsqrtf(variance + eps); @@ -297,7 +297,7 @@ static void group_norm_f32_cuda( group_norm_f32<<>>(x, dst, group_size, ne_elements, eps); } else { const dim3 block_dims(1024, 1, 1); - group_norm_f32<1024><< WARP_SIZE ? 32 * sizeof(float): 0, stream>>>(x, dst, group_size, ne_elements, eps); + group_norm_f32<1024><< WARP_SIZE ? 2 * 32 * sizeof(float): 0, stream>>>(x, dst, group_size, ne_elements, eps); } } diff --git a/ggml/src/ggml-cuda/softmax.cu b/ggml/src/ggml-cuda/softmax.cu index 285c0e9543a2..f320c6f004ea 100644 --- a/ggml/src/ggml-cuda/softmax.cu +++ b/ggml/src/ggml-cuda/softmax.cu @@ -116,6 +116,11 @@ static __global__ void soft_max_f32( vals[col] = val; } + if (block_size > WARP_SIZE) { + // sync is needed as we reuse buf_iw across block_reduce invocations, see #26385 + // for block_size <= WARP_SIZE, block_reduce does not access buf_iw + __syncthreads(); + } // find the sum of exps in the block tmp = block_reduce(tmp, buf_iw); @@ -142,6 +147,8 @@ static __device__ void soft_max_f32_parallelize_cols_single_row(const float * __ float * __restrict__ dst, float * __restrict__ tmp_maxs, float * __restrict__ tmp_sums, + float * shared_vals_max, + float * shared_vals_sum, const soft_max_params p) { namespace cg = cooperative_groups; @@ -154,7 +161,6 @@ static __device__ void soft_max_f32_parallelize_cols_single_row(const float * __ float local_vals[n_elem_per_thread] = { -INFINITY, -INFINITY, -INFINITY, -INFINITY }; float local_max = -INFINITY; const int step_size = gridDim.x * blockDim.x; - __shared__ float shared_vals[32]; // Compute thread-local max for (int col = col_start; col < p.ncols;) { @@ -171,7 +177,7 @@ static __device__ void soft_max_f32_parallelize_cols_single_row(const float * __ } // Compute CTA-level max - local_max = block_reduce(local_max, shared_vals); + local_max = block_reduce(local_max, shared_vals_max); // Store CTA-level max to GMEM if (tid == 0) { @@ -186,7 +192,7 @@ static __device__ void soft_max_f32_parallelize_cols_single_row(const float * __ } else { local_max = -INFINITY; } - local_max = block_reduce(local_max, shared_vals); + local_max = block_reduce(local_max, shared_vals_max); // Compute softmax dividends, accumulate divisor float tmp_expf = 0.0f; @@ -209,7 +215,7 @@ static __device__ void soft_max_f32_parallelize_cols_single_row(const float * __ } // Reduce divisor within CTA - tmp_expf = block_reduce(tmp_expf, shared_vals); + tmp_expf = block_reduce(tmp_expf, shared_vals_sum); // Store CTA-level sum to GMEM if (tid == 0) { @@ -223,7 +229,7 @@ static __device__ void soft_max_f32_parallelize_cols_single_row(const float * __ } else { tmp_expf = 0.0f; } - tmp_expf = block_reduce(tmp_expf, shared_vals); + tmp_expf = block_reduce(tmp_expf, shared_vals_sum); // Divide dividend by global sum + store data for (int col = col_start; col < p.ncols;) { @@ -310,9 +316,11 @@ __launch_bounds__(8*WARP_SIZE, 1) static __global__ void soft_max_f32_paralleliz // https://docs.nvidia.com/cuda/cuda-programming-guide/05-appendices/device-callable-apis.html#grid-synchronization // https://docs.nvidia.com/cuda/cuda-programming-guide/05-appendices/device-callable-apis.html#class-cluster-group { + __shared__ float shared_vals[2][32]; + for (int rowx = 0; rowx < p.ne01 * p.ne02 * p.ne03; rowx++) { soft_max_f32_parallelize_cols_single_row(x + int64_t(rowx) * p.ncols, dst + int64_t(rowx) * p.ncols, tmp_maxs, - tmp_sums, p); + tmp_sums, shared_vals[0], shared_vals[1], p); } } diff --git a/ggml/src/ggml-cuda/vecdotq.cuh b/ggml/src/ggml-cuda/vecdotq.cuh index 36d89c89e320..0f039c735b6b 100644 --- a/ggml/src/ggml-cuda/vecdotq.cuh +++ b/ggml/src/ggml-cuda/vecdotq.cuh @@ -734,48 +734,28 @@ static __device__ __forceinline__ float vec_dot_q2_0_q8_1( // Q8_1: 32 elements per block with individual scales // iqs selects which of the 2 chunks of 32 elements to process (0-1) - const float d2 = bq2_0->d; + const float d2 = bq2_0->d; + const int16_t * qs = (const int16_t *) bq2_0->qs + iqs * 4; // Process only the chunk specified by iqs const block_q8_1 * bq8_1_chunk = bq8_1 + iqs; - // Load 64 bits (8 bytes) for this chunk from Q2_0: bytes [8*iqs, 8*iqs+8) - const int offset = iqs * 8; - const int v0 = bq2_0->qs[offset + 0] | (bq2_0->qs[offset + 1] << 8) | - (bq2_0->qs[offset + 2] << 16) | (bq2_0->qs[offset + 3] << 24); - const int v1 = bq2_0->qs[offset + 4] | (bq2_0->qs[offset + 5] << 8) | - (bq2_0->qs[offset + 6] << 16) | (bq2_0->qs[offset + 7] << 24); - - // Unpack 32 2-bit codes into 8 int32s, each holding 4 signed int8 symbols in {-1,0,1,2}. - // Stored code c in {0,1,2,3} -> symbol s = c - 1. - int vi_bytes[8]; -#pragma unroll - for (int j = 0; j < 4; ++j) { - const int shift = j * 8; - const int codes = (v0 >> shift) & 0xFF; - const int c0 = ((codes >> 0) & 0x3) - 1; - const int c1 = ((codes >> 2) & 0x3) - 1; - const int c2 = ((codes >> 4) & 0x3) - 1; - const int c3 = ((codes >> 6) & 0x3) - 1; - vi_bytes[j] = (c0 & 0xFF) | ((c1 & 0xFF) << 8) | ((c2 & 0xFF) << 16) | ((c3 & 0xFF) << 24); - } + int sumi = 0; #pragma unroll for (int j = 0; j < 4; ++j) { - const int shift = j * 8; - const int codes = (v1 >> shift) & 0xFF; - const int c0 = ((codes >> 0) & 0x3) - 1; - const int c1 = ((codes >> 2) & 0x3) - 1; - const int c2 = ((codes >> 4) & 0x3) - 1; - const int c3 = ((codes >> 6) & 0x3) - 1; - vi_bytes[4 + j] = (c0 & 0xFF) | ((c1 & 0xFF) << 8) | ((c2 & 0xFF) << 16) | ((c3 & 0xFF) << 24); - } + const int q = qs[j]; + const int u = get_int_b4(bq8_1_chunk->qs, j*2+0); + const int v = get_int_b4(bq8_1_chunk->qs, j*2+1); - // Compute dot product for this 32-element chunk - int sumi = 0; -#pragma unroll - for (int j = 0; j < 8; ++j) { - const int u = get_int_b4(bq8_1_chunk->qs, j); - sumi = ggml_cuda_dp4a(vi_bytes[j], u, sumi); + // unpack even and odd crumbs into byte values + const int qe = __byte_perm(0x020100FF, 0x020100FF, q >> 0); + const int qo = __byte_perm(0x020100FF, 0x020100FF, q >> 2); + // unshuffle values + const int qx = __byte_perm(qe, qo, 0x5140); + const int qy = __byte_perm(qe, qo, 0x7362); + + sumi = ggml_cuda_dp4a(u, qx, sumi); + sumi = ggml_cuda_dp4a(v, qy, sumi); } // Apply Q2_0's single scale and this chunk's Q8_1 scale diff --git a/ggml/src/ggml-metal/ggml-metal-device.cpp b/ggml/src/ggml-metal/ggml-metal-device.cpp index 16e98eb519ea..c153bd82177b 100644 --- a/ggml/src/ggml-metal/ggml-metal-device.cpp +++ b/ggml/src/ggml-metal/ggml-metal-device.cpp @@ -477,6 +477,41 @@ ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_soft_max(ggml_me return res; } +ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_lightning_indexer( + ggml_metal_library_t lib, + const ggml_tensor * op) { + GGML_ASSERT(op->op == GGML_OP_LIGHTNING_INDEXER); + + char name[256]; + + snprintf(name, 256, "kernel_lightning_indexer_%s", ggml_type_name(op->src[1]->type)); + + ggml_metal_pipeline_with_params res = ggml_metal_library_get_pipeline(lib, name); + if (!res.pipeline) { + res = ggml_metal_library_compile_pipeline(lib, name, name, nullptr); + } + + return res; +} + +ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_dsv4_hc(ggml_metal_library_t lib, ggml_op op) { + const char * name = nullptr; + + switch (op) { + case GGML_OP_DSV4_HC_COMB: name = "kernel_dsv4_hc_comb_f32"; break; + case GGML_OP_DSV4_HC_PRE: name = "kernel_dsv4_hc_pre_f32"; break; + case GGML_OP_DSV4_HC_POST: name = "kernel_dsv4_hc_post_f32"; break; + default: GGML_ABORT("fatal error"); + } + + ggml_metal_pipeline_with_params res = ggml_metal_library_get_pipeline(lib, name); + if (!res.pipeline) { + res = ggml_metal_library_compile_pipeline(lib, name, name, nullptr); + } + + return res; +} + ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_ssm_conv(ggml_metal_library_t lib, const ggml_tensor * op) { GGML_ASSERT(op->src[0]->type == GGML_TYPE_F32); GGML_ASSERT(op->src[1]->type == GGML_TYPE_F32); @@ -2117,6 +2152,23 @@ ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_opt_step_sgd(ggm return res; } +ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_silu_back(ggml_metal_library_t lib, const ggml_tensor * op) { + assert(op->op == GGML_OP_SILU_BACK); + + char base[256]; + char name[256]; + + snprintf(base, 256, "kernel_silu_back_%s", ggml_type_name(op->src[0]->type)); + snprintf(name, 256, "%s", base); + + ggml_metal_pipeline_with_params res = ggml_metal_library_get_pipeline(lib, name); + if (!res.pipeline) { + res = ggml_metal_library_compile_pipeline(lib, base, name, nullptr); + } + + return res; +} + ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_memset(ggml_metal_library_t lib, const ggml_tensor * op) { GGML_ASSERT(op->type == GGML_TYPE_I64); diff --git a/ggml/src/ggml-metal/ggml-metal-device.h b/ggml/src/ggml-metal/ggml-metal-device.h index 91b841b67b7d..7e1deeaa2102 100644 --- a/ggml/src/ggml-metal/ggml-metal-device.h +++ b/ggml/src/ggml-metal/ggml-metal-device.h @@ -117,6 +117,7 @@ struct ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_diag struct ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_repeat (ggml_metal_library_t lib, enum ggml_type tsrc); struct ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_concat (ggml_metal_library_t lib, enum ggml_type tsrc); struct ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_unary (ggml_metal_library_t lib, const struct ggml_tensor * op); +struct ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_silu_back (ggml_metal_library_t lib, const struct ggml_tensor * op); struct ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_glu (ggml_metal_library_t lib, const struct ggml_tensor * op); struct ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_sum (ggml_metal_library_t lib, const struct ggml_tensor * op); struct ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_sum_rows (ggml_metal_library_t lib, const struct ggml_tensor * op); @@ -124,6 +125,8 @@ struct ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_cumsum_bl struct ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_cumsum_add (ggml_metal_library_t lib, const struct ggml_tensor * op); struct ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_tri (ggml_metal_library_t lib, const struct ggml_tensor * op); struct ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_soft_max (ggml_metal_library_t lib, const struct ggml_tensor * op); +struct ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_lightning_indexer (ggml_metal_library_t lib, const struct ggml_tensor * op); +struct ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_dsv4_hc (ggml_metal_library_t lib, enum ggml_op op); struct ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_ssm_conv (ggml_metal_library_t lib, const struct ggml_tensor * op); struct ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_ssm_conv_batched (ggml_metal_library_t lib, const struct ggml_tensor * op, int ssm_conv_bs); struct ggml_metal_pipeline_with_params ggml_metal_library_get_pipeline_ssm_scan (ggml_metal_library_t lib, const struct ggml_tensor * op); diff --git a/ggml/src/ggml-metal/ggml-metal-device.m b/ggml/src/ggml-metal/ggml-metal-device.m index 7d2a686850d5..2dc6eb8fdbc0 100644 --- a/ggml/src/ggml-metal/ggml-metal-device.m +++ b/ggml/src/ggml-metal/ggml-metal-device.m @@ -2,6 +2,7 @@ #import "ggml-impl.h" #import "ggml-backend-impl.h" +#import "ggml-metal-impl.h" #include @@ -1137,6 +1138,14 @@ bool ggml_metal_device_supports_op(ggml_metal_device_t dev, const struct ggml_te default: return false; } + case GGML_OP_SILU_BACK: + return (op->src[0]->type == GGML_TYPE_F32) && + (op->src[1]->type == GGML_TYPE_F32) && + (op->type == GGML_TYPE_F32) && + ggml_is_contiguous(op->src[0]) && + ggml_is_contiguous(op->src[1]) && + ggml_is_contiguous(op) && + ggml_are_same_shape(op->src[0], op->src[1]); case GGML_OP_GLU: switch (ggml_get_glu_op(op)) { case GGML_GLU_OP_REGLU: @@ -1181,6 +1190,7 @@ bool ggml_metal_device_supports_op(ggml_metal_device_t dev, const struct ggml_te case GGML_OP_MUL: case GGML_OP_DIV: case GGML_OP_ADD_ID: + return ggml_is_contiguous_rows(op->src[0]) && ggml_is_contiguous_rows(op->src[1]) && (op->src[0]->type == GGML_TYPE_F32 || op->src[0]->type == GGML_TYPE_F16) && (op->src[0]->type == op->src[1]->type); case GGML_OP_ACC: return ggml_is_contiguous_rows(op->src[0]) && ggml_is_contiguous_rows(op->src[1]) && op->src[0]->type == GGML_TYPE_F32; case GGML_OP_REPEAT: @@ -1299,6 +1309,72 @@ bool ggml_metal_device_supports_op(ggml_metal_device_t dev, const struct ggml_te return false; } return has_simdgroup_mm; // TODO: over-restricted for vec-kernels + case GGML_OP_LIGHTNING_INDEXER: + if (op->src[0]->ne[0] != OP_LIGHTNING_INDEXER_DK || + op->src[0]->ne[1] != OP_LIGHTNING_INDEXER_NH) { + return false; + } + if (!has_simdgroup_mm || + op->src[0]->type != GGML_TYPE_F32 || + op->src[2]->type != GGML_TYPE_F32 || + op->src[3]->type != GGML_TYPE_F16 || + op->type != GGML_TYPE_F32 || + !ggml_is_contiguous_rows(op->src[0]) || + !ggml_is_contiguous_rows(op->src[1]) || + !ggml_is_contiguous_rows(op->src[2]) || + !ggml_is_contiguous_rows(op->src[3])) { + return false; + } + switch (op->src[1]->type) { + case GGML_TYPE_F32: + case GGML_TYPE_F16: + case GGML_TYPE_Q4_0: + case GGML_TYPE_Q4_1: + case GGML_TYPE_Q5_0: + case GGML_TYPE_Q5_1: + case GGML_TYPE_Q8_0: + return true; + case GGML_TYPE_BF16: + return has_bfloat; + default: + return false; + } + case GGML_OP_DSV4_HC_COMB: + return has_simdgroup_reduction && + op->src[0]->type == GGML_TYPE_F32 && + op->src[1]->type == GGML_TYPE_F32 && + op->src[2]->type == GGML_TYPE_F32 && + op->type == GGML_TYPE_F32 && + op->src[0]->ne[0] == 24 && + op->src[1]->ne[0] >= 3 && + op->src[2]->ne[0] == 24 && + ggml_is_contiguous_rows(op->src[0]) && + ggml_is_contiguous_rows(op->src[1]) && + ggml_is_contiguous_rows(op->src[2]); + case GGML_OP_DSV4_HC_PRE: + return has_simdgroup_reduction && + op->src[0]->type == GGML_TYPE_F32 && + op->src[1]->type == GGML_TYPE_F32 && + op->type == GGML_TYPE_F32 && + op->src[0]->ne[1] == 4 && + op->src[1]->ne[0] == 4 && + ggml_is_contiguous_rows(op->src[0]) && + ggml_is_contiguous_rows(op->src[1]); + case GGML_OP_DSV4_HC_POST: + return has_simdgroup_reduction && + op->src[0]->type == GGML_TYPE_F32 && + op->src[1]->type == GGML_TYPE_F32 && + op->src[2]->type == GGML_TYPE_F32 && + op->src[3]->type == GGML_TYPE_F32 && + op->type == GGML_TYPE_F32 && + op->src[1]->ne[1] == 4 && + op->src[2]->ne[0] == 4 && + op->src[3]->ne[0] == 4 && + op->src[3]->ne[1] == 4 && + ggml_is_contiguous_rows(op->src[0]) && + ggml_is_contiguous_rows(op->src[1]) && + ggml_is_contiguous_rows(op->src[2]) && + ggml_is_contiguous_rows(op->src[3]); case GGML_OP_SSM_CONV: case GGML_OP_SSM_SCAN: return has_simdgroup_reduction; diff --git a/ggml/src/ggml-metal/ggml-metal-impl.h b/ggml/src/ggml-metal/ggml-metal-impl.h index 9f350aad5b74..e173b91c0c5c 100644 --- a/ggml/src/ggml-metal/ggml-metal-impl.h +++ b/ggml/src/ggml-metal/ggml-metal-impl.h @@ -112,6 +112,13 @@ #define OP_FLASH_ATTN_EXT_VEC_NQPSG 1 #define OP_FLASH_ATTN_EXT_VEC_NCPSG 32 +#define OP_LIGHTNING_INDEXER_DK 128 +#define OP_LIGHTNING_INDEXER_NH 64 +#define OP_LIGHTNING_INDEXER_NHPTG 8 +#define OP_LIGHTNING_INDEXER_NKPSG 8 +#define OP_LIGHTNING_INDEXER_NSG 8 +#define OP_LIGHTNING_INDEXER_NBPTG 8 + #define OP_UNARY_NUM_SCALE 10 #define OP_UNARY_NUM_FILL 11 #define OP_UNARY_NUM_CLAMP 12 @@ -1171,6 +1178,66 @@ typedef struct { int64_t val; } ggml_metal_kargs_memset; +typedef struct { + int32_t n_kv; + int32_t n_batch; + int32_t mask_ne3; + uint64_t nb1; + uint64_t nb3; + uint64_t nbq1; + uint64_t nbq2; + uint64_t nbq3; + uint64_t nbk2; + uint64_t nbk3; + uint64_t nbw1; + uint64_t nbw3; + uint64_t nbm1; + uint64_t nbm3; +} ggml_metal_kargs_lightning_indexer; + +typedef struct { + int32_t n_tokens; + int32_t n_iter; + uint64_t nb_m0; + uint64_t nb_m1; + uint64_t nb_s0; + uint64_t nb_b0; + uint64_t nb_d0; + uint64_t nb_d1; + uint64_t nb_d2; + float eps; +} ggml_metal_kargs_dsv4_hc_comb; + +typedef struct { + int32_t n_embd; + int32_t n_tokens; + uint64_t nb_x0; + uint64_t nb_x1; + uint64_t nb_x2; + uint64_t nb_w0; + uint64_t nb_w1; + uint64_t nb_d0; + uint64_t nb_d1; +} ggml_metal_kargs_dsv4_hc_pre; + +typedef struct { + int32_t n_embd; + int32_t n_tokens; + uint64_t nb_x0; + uint64_t nb_x1; + uint64_t nb_r0; + uint64_t nb_r1; + uint64_t nb_r2; + uint64_t nb_p0; + uint64_t nb_p1; + uint64_t nb_c0; + uint64_t nb_c1; + uint64_t nb_c2; + uint64_t nb_d0; + uint64_t nb_d1; + uint64_t nb_d2; +} ggml_metal_kargs_dsv4_hc_post; + typedef struct { int32_t ne00; int32_t ne01; @@ -1222,4 +1289,8 @@ typedef struct { int64_t np; } ggml_metal_kargs_opt_step_sgd; +typedef struct { + int64_t ne; +} ggml_metal_kargs_silu_back; + #endif // GGML_METAL_IMPL diff --git a/ggml/src/ggml-metal/ggml-metal-ops.cpp b/ggml/src/ggml-metal/ggml-metal-ops.cpp index 76626a451836..c5d7619c12fa 100644 --- a/ggml/src/ggml-metal/ggml-metal-ops.cpp +++ b/ggml/src/ggml-metal/ggml-metal-ops.cpp @@ -299,6 +299,10 @@ static int ggml_metal_op_encode_impl(ggml_metal_op_t ctx, int idx) { { n_fuse = ggml_metal_op_unary(ctx, idx); } break; + case GGML_OP_SILU_BACK: + { + n_fuse = ggml_metal_op_silu_back(ctx, idx); + } break; case GGML_OP_GLU: { n_fuse = ggml_metal_op_glu(ctx, idx); @@ -316,6 +320,16 @@ static int ggml_metal_op_encode_impl(ggml_metal_op_t ctx, int idx) { { n_fuse = ggml_metal_op_cumsum(ctx, idx); } break; + case GGML_OP_LIGHTNING_INDEXER: + { + n_fuse = ggml_metal_op_lightning_indexer(ctx, idx); + } break; + case GGML_OP_DSV4_HC_COMB: + case GGML_OP_DSV4_HC_PRE: + case GGML_OP_DSV4_HC_POST: + { + n_fuse = ggml_metal_op_dsv4_hc(ctx, idx); + } break; case GGML_OP_SOFT_MAX: { n_fuse = ggml_metal_op_soft_max(ctx, idx); @@ -1297,6 +1311,203 @@ int ggml_metal_op_diag(ggml_metal_op_t ctx, int idx) { return 1; } +int ggml_metal_op_lightning_indexer(ggml_metal_op_t ctx, int idx) { + ggml_tensor * op = ctx->node(idx); + + ggml_metal_encoder_t enc = ctx->enc; + + GGML_ASSERT(op->op == GGML_OP_LIGHTNING_INDEXER); + + const ggml_tensor * q = op->src[0]; + const ggml_tensor * k = op->src[1]; + const ggml_tensor * w = op->src[2]; + const ggml_tensor * m = op->src[3]; + + GGML_ASSERT(q->type == GGML_TYPE_F32); + GGML_ASSERT(k->type == GGML_TYPE_F32 || + k->type == GGML_TYPE_F16 || + k->type == GGML_TYPE_BF16 || + k->type == GGML_TYPE_Q4_0 || + k->type == GGML_TYPE_Q4_1 || + k->type == GGML_TYPE_Q5_0 || + k->type == GGML_TYPE_Q5_1 || + k->type == GGML_TYPE_Q8_0); + GGML_ASSERT(w->type == GGML_TYPE_F32); + GGML_ASSERT(m->type == GGML_TYPE_F16); + GGML_ASSERT(op->type == GGML_TYPE_F32); + + GGML_ASSERT(q->ne[0] == OP_LIGHTNING_INDEXER_DK); + GGML_ASSERT(q->ne[1] == OP_LIGHTNING_INDEXER_NH); + + ggml_metal_kargs_lightning_indexer args = { + /*.n_kv =*/ (int32_t) k->ne[2], + /*.n_batch =*/ (int32_t) q->ne[2], + /*.mask_ne3 =*/ (int32_t) m->ne[3], + /*.nb1 =*/ op->nb[1], + /*.nb3 =*/ op->nb[3], + /*.nbq1 =*/ q->nb[1], + /*.nbq2 =*/ q->nb[2], + /*.nbq3 =*/ q->nb[3], + /*.nbk2 =*/ k->nb[2], + /*.nbk3 =*/ k->nb[3], + /*.nbw1 =*/ w->nb[1], + /*.nbw3 =*/ w->nb[3], + /*.nbm1 =*/ m->nb[1], + /*.nbm3 =*/ m->nb[3], + }; + + ggml_metal_encoder_set_buffer(enc, ggml_metal_get_buffer_id(q), 1); + ggml_metal_encoder_set_buffer(enc, ggml_metal_get_buffer_id(k), 2); + ggml_metal_encoder_set_buffer(enc, ggml_metal_get_buffer_id(w), 3); + ggml_metal_encoder_set_buffer(enc, ggml_metal_get_buffer_id(m), 4); + ggml_metal_encoder_set_buffer(enc, ggml_metal_get_buffer_id(op), 5); + + const int nsg = OP_LIGHTNING_INDEXER_NSG; + const int nkptg = OP_LIGHTNING_INDEXER_NKPSG*nsg; + const int nbptg = OP_LIGHTNING_INDEXER_NBPTG; + + auto pipeline = ggml_metal_library_get_pipeline_lightning_indexer(ctx->lib, op); + ggml_metal_encoder_set_pipeline(enc, pipeline); + ggml_metal_encoder_set_bytes(enc, &args, sizeof(args), 0); + ggml_metal_encoder_dispatch_threadgroups(enc, + (k->ne[2] + nkptg - 1)/nkptg, + (q->ne[2] + nbptg - 1)/nbptg, + q->ne[3], 32, nsg, 1); + + return 1; +} + +int ggml_metal_op_dsv4_hc(ggml_metal_op_t ctx, int idx) { + ggml_tensor * op = ctx->node(idx); + + ggml_metal_encoder_t enc = ctx->enc; + auto pipeline = ggml_metal_library_get_pipeline_dsv4_hc(ctx->lib, op->op); + + ggml_metal_encoder_set_pipeline(enc, pipeline); + + switch (op->op) { + case GGML_OP_DSV4_HC_COMB: + { + const ggml_tensor * mixes = op->src[0]; + const ggml_tensor * scale = op->src[1]; + const ggml_tensor * base = op->src[2]; + + GGML_ASSERT(mixes->type == GGML_TYPE_F32); + GGML_ASSERT(scale->type == GGML_TYPE_F32); + GGML_ASSERT(base->type == GGML_TYPE_F32); + GGML_ASSERT(op->type == GGML_TYPE_F32); + GGML_ASSERT(mixes->ne[0] == 24); + GGML_ASSERT(op->ne[0] == 4 && op->ne[1] == 4); + + ggml_metal_kargs_dsv4_hc_comb args = { + /*.n_tokens =*/ (int32_t) mixes->ne[1], + /*.n_iter =*/ ggml_get_op_params_i32(op, 1), + /*.nb_m0 =*/ mixes->nb[0], + /*.nb_m1 =*/ mixes->nb[1], + /*.nb_s0 =*/ scale->nb[0], + /*.nb_b0 =*/ base->nb[0], + /*.nb_d0 =*/ op->nb[0], + /*.nb_d1 =*/ op->nb[1], + /*.nb_d2 =*/ op->nb[2], + /*.eps =*/ ggml_get_op_params_f32(op, 0), + }; + + ggml_metal_encoder_set_bytes (enc, &args, sizeof(args), 0); + ggml_metal_encoder_set_buffer(enc, ggml_metal_get_buffer_id(mixes), 1); + ggml_metal_encoder_set_buffer(enc, ggml_metal_get_buffer_id(scale), 2); + ggml_metal_encoder_set_buffer(enc, ggml_metal_get_buffer_id(base), 3); + ggml_metal_encoder_set_buffer(enc, ggml_metal_get_buffer_id(op), 4); + + // One SIMDgroup owns one 4x4 Sinkhorn matrix. Packing up to four + // independent tokens per threadgroup keeps both decode and prompt + // dispatches compact without any threadgroup-memory synchronization. + const int nsg = std::min(4, args.n_tokens); + ggml_metal_encoder_dispatch_threadgroups( + enc, (args.n_tokens + nsg - 1)/nsg, 1, 1, 32, nsg, 1); + } break; + case GGML_OP_DSV4_HC_PRE: + { + const ggml_tensor * x = op->src[0]; + const ggml_tensor * weights = op->src[1]; + + GGML_ASSERT(x->type == GGML_TYPE_F32); + GGML_ASSERT(weights->type == GGML_TYPE_F32); + GGML_ASSERT(op->type == GGML_TYPE_F32); + GGML_ASSERT(x->ne[1] == 4); + + ggml_metal_kargs_dsv4_hc_pre args = { + /*.n_embd =*/ (int32_t) x->ne[0], + /*.n_tokens =*/ (int32_t) x->ne[2], + /*.nb_x0 =*/ x->nb[0], + /*.nb_x1 =*/ x->nb[1], + /*.nb_x2 =*/ x->nb[2], + /*.nb_w0 =*/ weights->nb[0], + /*.nb_w1 =*/ weights->nb[1], + /*.nb_d0 =*/ op->nb[0], + /*.nb_d1 =*/ op->nb[1], + }; + + ggml_metal_encoder_set_bytes (enc, &args, sizeof(args), 0); + ggml_metal_encoder_set_buffer(enc, ggml_metal_get_buffer_id(x), 1); + ggml_metal_encoder_set_buffer(enc, ggml_metal_get_buffer_id(weights), 2); + ggml_metal_encoder_set_buffer(enc, ggml_metal_get_buffer_id(op), 3); + + const int n_tiles = (args.n_embd + 31)/32; + const int nsg = std::min(4, n_tiles); + ggml_metal_encoder_dispatch_threadgroups( + enc, (n_tiles + nsg - 1)/nsg, args.n_tokens, 1, 32, nsg, 1); + } break; + case GGML_OP_DSV4_HC_POST: + { + const ggml_tensor * x = op->src[0]; + const ggml_tensor * residual = op->src[1]; + const ggml_tensor * post = op->src[2]; + const ggml_tensor * comb = op->src[3]; + + GGML_ASSERT(x->type == GGML_TYPE_F32); + GGML_ASSERT(residual->type == GGML_TYPE_F32); + GGML_ASSERT(post->type == GGML_TYPE_F32); + GGML_ASSERT(comb->type == GGML_TYPE_F32); + GGML_ASSERT(op->type == GGML_TYPE_F32); + GGML_ASSERT(residual->ne[1] == 4); + + ggml_metal_kargs_dsv4_hc_post args = { + /*.n_embd =*/ (int32_t) x->ne[0], + /*.n_tokens =*/ (int32_t) x->ne[1], + /*.nb_x0 =*/ x->nb[0], + /*.nb_x1 =*/ x->nb[1], + /*.nb_r0 =*/ residual->nb[0], + /*.nb_r1 =*/ residual->nb[1], + /*.nb_r2 =*/ residual->nb[2], + /*.nb_p0 =*/ post->nb[0], + /*.nb_p1 =*/ post->nb[1], + /*.nb_c0 =*/ comb->nb[0], + /*.nb_c1 =*/ comb->nb[1], + /*.nb_c2 =*/ comb->nb[2], + /*.nb_d0 =*/ op->nb[0], + /*.nb_d1 =*/ op->nb[1], + /*.nb_d2 =*/ op->nb[2], + }; + + ggml_metal_encoder_set_bytes (enc, &args, sizeof(args), 0); + ggml_metal_encoder_set_buffer(enc, ggml_metal_get_buffer_id(x), 1); + ggml_metal_encoder_set_buffer(enc, ggml_metal_get_buffer_id(residual), 2); + ggml_metal_encoder_set_buffer(enc, ggml_metal_get_buffer_id(post), 3); + ggml_metal_encoder_set_buffer(enc, ggml_metal_get_buffer_id(comb), 4); + ggml_metal_encoder_set_buffer(enc, ggml_metal_get_buffer_id(op), 5); + + const int n_tiles = (args.n_embd + 31)/32; + const int nsg = std::min(4, n_tiles); + ggml_metal_encoder_dispatch_threadgroups( + enc, (n_tiles + nsg - 1)/nsg, args.n_tokens, 1, 32, nsg, 1); + } break; + default: + GGML_ABORT("fatal error"); + } + + return 1; +} + int ggml_metal_op_soft_max(ggml_metal_op_t ctx, int idx) { ggml_tensor * op = ctx->node(idx); @@ -3197,9 +3408,6 @@ int ggml_metal_op_bin(ggml_metal_op_t ctx, int idx) { GGML_TENSOR_LOCALS( int32_t, ne, op, ne); GGML_TENSOR_LOCALS(uint64_t, nb, op, nb); - GGML_ASSERT(op->src[0]->type == GGML_TYPE_F32); - GGML_ASSERT(op->src[1]->type == GGML_TYPE_F32); - GGML_ASSERT(ggml_is_contiguous_rows(op->src[0])); GGML_ASSERT(ggml_is_contiguous_rows(op->src[1])); @@ -3339,6 +3547,36 @@ int ggml_metal_op_bin(ggml_metal_op_t ctx, int idx) { return n_fuse; } +int ggml_metal_op_silu_back(ggml_metal_op_t ctx, int idx) { + ggml_tensor * op = ctx->node(idx); + + ggml_metal_library_t lib = ctx->lib; + ggml_metal_encoder_t enc = ctx->enc; + + auto pipeline = ggml_metal_library_get_pipeline_silu_back(lib, op); + + const int64_t ne = ggml_nelements(op); + + ggml_metal_kargs_silu_back args = { + /*.ne =*/ ne, + }; + + int arg_idx{0}; + + ggml_metal_encoder_set_pipeline(enc, pipeline); + ggml_metal_encoder_set_bytes (enc, &args, sizeof(args), arg_idx++); + ggml_metal_encoder_set_buffer (enc, ggml_metal_get_buffer_id(op->src[0]), arg_idx++); + ggml_metal_encoder_set_buffer (enc, ggml_metal_get_buffer_id(op->src[1]), arg_idx++); + ggml_metal_encoder_set_buffer (enc, ggml_metal_get_buffer_id(op), arg_idx++); + + const int nth = std::min(ggml_metal_pipeline_max_theads_per_threadgroup(pipeline), ne); + const int64_t n = (ne + nth - 1) / nth; + + ggml_metal_encoder_dispatch_threadgroups(enc, n, 1, 1, nth, 1, 1); + + return 1; +} + int ggml_metal_op_l2_norm(ggml_metal_op_t ctx, int idx) { ggml_tensor * op = ctx->node(idx); diff --git a/ggml/src/ggml-metal/ggml-metal-ops.h b/ggml/src/ggml-metal/ggml-metal-ops.h index 2783ecb8b611..b03b59e0bd92 100644 --- a/ggml/src/ggml-metal/ggml-metal-ops.h +++ b/ggml/src/ggml-metal/ggml-metal-ops.h @@ -54,6 +54,8 @@ int ggml_metal_op_cumsum (ggml_metal_op_t ctx, int idx); int ggml_metal_op_get_rows (ggml_metal_op_t ctx, int idx); int ggml_metal_op_set_rows (ggml_metal_op_t ctx, int idx); int ggml_metal_op_diag (ggml_metal_op_t ctx, int idx); +int ggml_metal_op_lightning_indexer (ggml_metal_op_t ctx, int idx); +int ggml_metal_op_dsv4_hc (ggml_metal_op_t ctx, int idx); int ggml_metal_op_soft_max (ggml_metal_op_t ctx, int idx); int ggml_metal_op_ssm_conv (ggml_metal_op_t ctx, int idx); int ggml_metal_op_ssm_scan (ggml_metal_op_t ctx, int idx); @@ -70,6 +72,7 @@ int ggml_metal_op_mul_mat_id (ggml_metal_op_t ctx, int idx); int ggml_metal_op_add_id (ggml_metal_op_t ctx, int idx); int ggml_metal_op_flash_attn_ext (ggml_metal_op_t ctx, int idx); int ggml_metal_op_bin (ggml_metal_op_t ctx, int idx); +int ggml_metal_op_silu_back (ggml_metal_op_t ctx, int idx); int ggml_metal_op_l2_norm (ggml_metal_op_t ctx, int idx); int ggml_metal_op_group_norm (ggml_metal_op_t ctx, int idx); int ggml_metal_op_norm (ggml_metal_op_t ctx, int idx); diff --git a/ggml/src/ggml-metal/ggml-metal.metal b/ggml/src/ggml-metal/ggml-metal.metal index f14ee0792ba5..7d12cb0fe39b 100644 --- a/ggml/src/ggml-metal/ggml-metal.metal +++ b/ggml/src/ggml-metal/ggml-metal.metal @@ -1255,6 +1255,20 @@ template [[host_name("kernel_unary_f32_f32_4")]] kernel kernel_unary_t kernel_un template [[host_name("kernel_unary_f16_f16")]] kernel kernel_unary_t kernel_unary_impl; template [[host_name("kernel_unary_f16_f16_4")]] kernel kernel_unary_t kernel_unary_impl; +kernel void kernel_silu_back_f32( + constant ggml_metal_kargs_silu_back & args, + device const float * dy, + device const float * x, + device float * dx, + uint gid [[thread_position_in_grid]]) { + if (gid >= args.ne) { + return; + } + + const float s = 1.0f / (1.0f + exp(-x[gid])); + dx[gid] = dy[gid] * s * (1.0f + x[gid] * (1.0f - s)); +} + // OP: 0 - add, 1 - sub, 2 - mul, 3 - div constant short FC_bin_op [[function_constant(FC_BIN + 0)]]; constant short FC_bin_f [[function_constant(FC_BIN + 1)]]; @@ -1418,6 +1432,8 @@ typedef decltype(kernel_bin_fuse_impl) kernel_bin_fuse_t; template [[host_name("kernel_bin_fuse_f32_f32_f32")]] kernel kernel_bin_fuse_t kernel_bin_fuse_impl; template [[host_name("kernel_bin_fuse_f32_f32_f32_4")]] kernel kernel_bin_fuse_t kernel_bin_fuse_impl; +template [[host_name("kernel_bin_fuse_f16_f16_f16")]] kernel kernel_bin_fuse_t kernel_bin_fuse_impl; +template [[host_name("kernel_bin_fuse_f16_f16_f16_4")]] kernel kernel_bin_fuse_t kernel_bin_fuse_impl; kernel void kernel_add_id( constant ggml_metal_kargs_add_id & args, @@ -11278,3 +11294,310 @@ kernel void kernel_count_equal( typedef decltype(kernel_count_equal) kernel_count_equal_t; template [[host_name("kernel_count_equal_i32")]] kernel kernel_count_equal_t kernel_count_equal; + +template< + typename kd4x4_t, + short nl_k, + void (*deq_k)(device const kd4x4_t *, short, thread half4x4 &)> +kernel void kernel_lightning_indexer( + constant ggml_metal_kargs_lightning_indexer & args, + device const char * q, + device const char * k, + device const char * w, + device const char * m, + device char * dst, + uint3 tgpig[[threadgroup_position_in_grid]], + ushort tiitg[[thread_index_in_threadgroup]], + ushort tiisg[[thread_index_in_simdgroup]], + ushort sgitg[[simdgroup_index_in_threadgroup]]) { + constexpr short DK = OP_LIGHTNING_INDEXER_DK; + constexpr short NH = OP_LIGHTNING_INDEXER_NH; + constexpr short NHPTG = OP_LIGHTNING_INDEXER_NHPTG; + constexpr short NKPSG = OP_LIGHTNING_INDEXER_NKPSG; + constexpr short NSG = OP_LIGHTNING_INDEXER_NSG; + constexpr short NBPTG = OP_LIGHTNING_INDEXER_NBPTG; + + constexpr short DK4 = DK/4; + constexpr short DK8 = DK/8; + constexpr short DK16 = DK/16; + + constexpr short NK = NKPSG*NSG; // keys per threadgroup + constexpr short NTG = 32*NSG; // threads per threadgroup + + const int i_stream = tgpig.z; + const int i_kv_0 = tgpig.x*NK; // first key of this threadgroup + const int i_kv = i_kv_0 + sgitg*NKPSG; // first key of this simdgroup + + threadgroup half4x4 sk4x4[NK*DK16]; + threadgroup half * sk = (threadgroup half *) sk4x4; + + for (short i = tiitg; i < NK*DK16; i += NTG) { + const short ik = i/DK16; + const short i16 = i%DK16; + + half4x4 tmp; + + if (i_kv_0 + ik < args.n_kv) { + device const kd4x4_t * kr = (device const kd4x4_t *) (k + (i_kv_0 + ik)*args.nbk2 + i_stream*args.nbk3); + + deq_k(kr + i16/nl_k, i16%nl_k, tmp); + } else { + FOR_UNROLL (short j = 0; j < 4; ++j) { + tmp[j] = half4(0.0h); + } + } + + sk4x4[i] = tmp; + } + + threadgroup_barrier(mem_flags::mem_threadgroup); + + // K tile of this simdgroup, transposed to [DK, NKPSG] + simdgroup_half8x8 mk[DK8]; + + FOR_UNROLL (short i = 0; i < DK8; ++i) { + simdgroup_load(mk[i], sk + sgitg*NKPSG*DK + 8*i, DK, 0, true); + } + + threadgroup half4 sq4[NHPTG*DK4]; + threadgroup half * sq = (threadgroup half *) sq4; + + threadgroup float sw [NHPTG]; + threadgroup float sqk[NSG*NHPTG*NKPSG]; + + const int i_batch_0 = tgpig.y*NBPTG; + const int n_batch = min((int) NBPTG, args.n_batch - i_batch_0); + + for (short ib = 0; ib < n_batch; ++ib) { + const int i_batch = i_batch_0 + ib; + + device const char * pq = q + i_batch*args.nbq2 + i_stream*args.nbq3; + device const char * pw = w + i_batch*args.nbw1 + i_stream*args.nbw3; + + float score = 0.0f; + + FOR_UNROLL (short i_head = 0; i_head < NH; i_head += NHPTG) { + // stage the Q tile [DK, NHPTG] and the (prescaled) head weights + for (short i = tiitg; i < NHPTG*DK4; i += NTG) { + const short ih = i/DK4; + const short i4 = i%DK4; + + device const float4 * q4 = (device const float4 *) (pq + (i_head + ih)*args.nbq1); + + sq4[ih*DK4 + i4] = half4(q4[i4]); + } + + if (tiitg < NHPTG) { + sw[tiitg] = ((device const float *) pw)[i_head + tiitg]; + } + + threadgroup_barrier(mem_flags::mem_threadgroup); + + simdgroup_float8x8 mqk = make_filled_simdgroup_matrix(0.0f); + + FOR_UNROLL (short i = 0; i < DK8; ++i) { + simdgroup_half8x8 mq; + + simdgroup_load(mq, sq + 8*i, DK, 0, false); + simdgroup_multiply_accumulate(mqk, mq, mk[i], mqk); + } + + threadgroup float * pqk = sqk + sgitg*NHPTG*NKPSG; + + simdgroup_store(mqk, pqk, NKPSG, 0, false); + simdgroup_barrier(mem_flags::mem_threadgroup); + + // one lane per key: ReLU, apply the head weight and accumulate over the head tile + if (tiisg < NKPSG) { + FOR_UNROLL (short ih = 0; ih < NHPTG; ++ih) { + score += max(pqk[ih*NKPSG + tiisg], 0.0f)*sw[ih]; + } + } + + threadgroup_barrier(mem_flags::mem_threadgroup); + } + + if (tiisg < NKPSG) { + const int ik = i_kv + tiisg; + if (ik < args.n_kv) { + device const half * pm = (device const half *) (m + i_batch*args.nbm1 + (i_stream % args.mask_ne3)*args.nbm3); + device float * pd = (device float *) (dst + i_batch*args.nb1 + i_stream*args.nb3); + + pd[ik] = score + (float) pm[ik]; + } + } + } +} + +typedef decltype(kernel_lightning_indexer) kernel_lightning_indexer_t; + +template [[host_name("kernel_lightning_indexer_f32")]] kernel kernel_lightning_indexer_t kernel_lightning_indexer; +template [[host_name("kernel_lightning_indexer_f16")]] kernel kernel_lightning_indexer_t kernel_lightning_indexer; + +#if defined(GGML_METAL_HAS_BF16) +template [[host_name("kernel_lightning_indexer_bf16")]] kernel kernel_lightning_indexer_t kernel_lightning_indexer; +#endif + +template [[host_name("kernel_lightning_indexer_q4_0")]] kernel kernel_lightning_indexer_t kernel_lightning_indexer; +template [[host_name("kernel_lightning_indexer_q4_1")]] kernel kernel_lightning_indexer_t kernel_lightning_indexer; +template [[host_name("kernel_lightning_indexer_q5_0")]] kernel kernel_lightning_indexer_t kernel_lightning_indexer; +template [[host_name("kernel_lightning_indexer_q5_1")]] kernel kernel_lightning_indexer_t kernel_lightning_indexer; +template [[host_name("kernel_lightning_indexer_q8_0")]] kernel kernel_lightning_indexer_t kernel_lightning_indexer; + +kernel void kernel_dsv4_hc_comb_f32( + constant ggml_metal_kargs_dsv4_hc_comb & args, + device const char * mixes, + device const char * scale, + device const char * base, + device char * dst, + uint3 tgpig[[threadgroup_position_in_grid]], + ushort tiisg[[thread_index_in_simdgroup]], + ushort sgitg[[simdgroup_index_in_threadgroup]], + ushort3 ntg[[threads_per_threadgroup]]) { + constexpr ushort hc = 4; + constexpr ushort comb_offset = 2*hc; + + const int it = tgpig.x*ntg.y + sgitg; + if (it >= args.n_tokens) { + return; + } + + float scale_lane = 0.0f; + if (tiisg == 0) { + scale_lane = *(device const float *) (scale + 2*args.nb_s0); + } + const float scale_comb = simd_shuffle(scale_lane, 0); + + float v = 0.0f; + if (tiisg < hc*hc) { + v = *(device const float *) (mixes + (comb_offset + tiisg)*args.nb_m0 + it*args.nb_m1)*scale_comb + + *(device const float *) (base + (comb_offset + tiisg)*args.nb_b0); + } + + // Softmax across destinations (the four contiguous lanes for each source). + float vmax = max(v, simd_shuffle_xor(v, 1)); + vmax = max(vmax, simd_shuffle_xor(vmax, 2)); + v = exp(v - vmax); + + float sum = v + simd_shuffle_xor(v, 1); + sum += simd_shuffle_xor(sum, 2); + v = v/sum + args.eps; + + // Normalize columns: equal destination indices are four lanes apart. + sum = v + simd_shuffle_xor(v, 4); + sum += simd_shuffle_xor(sum, 8); + v /= sum + args.eps; + + for (int i = 1; i < args.n_iter; ++i) { + sum = v + simd_shuffle_xor(v, 1); + sum += simd_shuffle_xor(sum, 2); + v /= sum + args.eps; + + sum = v + simd_shuffle_xor(v, 4); + sum += simd_shuffle_xor(sum, 8); + v /= sum + args.eps; + } + + if (tiisg < hc*hc) { + const ushort idst = tiisg & 3; + const ushort isrc = tiisg >> 2; + *(device float *) (dst + idst*args.nb_d0 + isrc*args.nb_d1 + it*args.nb_d2) = v; + } +} + +kernel void kernel_dsv4_hc_pre_f32( + constant ggml_metal_kargs_dsv4_hc_pre & args, + device const char * x, + device const char * weights, + device char * dst, + uint3 tgpig[[threadgroup_position_in_grid]], + ushort tiisg[[thread_index_in_simdgroup]], + ushort sgitg[[simdgroup_index_in_threadgroup]], + ushort3 ntg[[threads_per_threadgroup]]) { + constexpr ushort hc = 4; + + const int it = tgpig.y; + const int i0 = ((int) tgpig.x*ntg.y + sgitg)*32 + tiisg; + + float weight_lane = 0.0f; + if (tiisg < hc) { + weight_lane = *(device const float *) (weights + tiisg*args.nb_w0 + it*args.nb_w1); + } + + float w[hc]; + FOR_UNROLL (ushort ih = 0; ih < hc; ++ih) { + w[ih] = simd_shuffle(weight_lane, ih); + } + + if (i0 >= args.n_embd) { + return; + } + + device const char * xb = x + i0*args.nb_x0 + it*args.nb_x2; + float result = 0.0f; + FOR_UNROLL (ushort ih = 0; ih < hc; ++ih) { + result = fma(*(device const float *) (xb + ih*args.nb_x1), w[ih], result); + } + + *(device float *) (dst + i0*args.nb_d0 + it*args.nb_d1) = result; +} + +kernel void kernel_dsv4_hc_post_f32( + constant ggml_metal_kargs_dsv4_hc_post & args, + device const char * x, + device const char * residual, + device const char * post, + device const char * comb, + device char * dst, + uint3 tgpig[[threadgroup_position_in_grid]], + ushort tiisg[[thread_index_in_simdgroup]], + ushort sgitg[[simdgroup_index_in_threadgroup]], + ushort3 ntg[[threads_per_threadgroup]]) { + constexpr ushort hc = 4; + + const int it = tgpig.y; + const int i0 = ((int) tgpig.x*ntg.y + sgitg)*32 + tiisg; + + float coeff_lane = 0.0f; + if (tiisg < hc) { + coeff_lane = *(device const float *) (post + tiisg*args.nb_p0 + it*args.nb_p1); + } else if (tiisg < hc + hc*hc) { + const ushort idx = tiisg - hc; + const ushort idst = idx & 3; + const ushort isrc = idx >> 2; + coeff_lane = *(device const float *) (comb + idst*args.nb_c0 + isrc*args.nb_c1 + it*args.nb_c2); + } + + float post_reg[hc]; + float comb_reg[hc][hc]; + FOR_UNROLL (ushort idst = 0; idst < hc; ++idst) { + post_reg[idst] = simd_shuffle(coeff_lane, idst); + } + FOR_UNROLL (ushort isrc = 0; isrc < hc; ++isrc) { + FOR_UNROLL (ushort idst = 0; idst < hc; ++idst) { + comb_reg[isrc][idst] = simd_shuffle(coeff_lane, hc + idst + hc*isrc); + } + } + + if (i0 >= args.n_embd) { + return; + } + + const float xv = *(device const float *) (x + i0*args.nb_x0 + it*args.nb_x1); + float result[hc]; + FOR_UNROLL (ushort idst = 0; idst < hc; ++idst) { + result[idst] = xv*post_reg[idst]; + } + + device const char * rb = residual + i0*args.nb_r0 + it*args.nb_r2; + FOR_UNROLL (ushort isrc = 0; isrc < hc; ++isrc) { + const float rv = *(device const float *) (rb + isrc*args.nb_r1); + FOR_UNROLL (ushort idst = 0; idst < hc; ++idst) { + result[idst] = fma(rv, comb_reg[isrc][idst], result[idst]); + } + } + + FOR_UNROLL (ushort idst = 0; idst < hc; ++idst) { + *(device float *) (dst + i0*args.nb_d0 + idst*args.nb_d1 + it*args.nb_d2) = result[idst]; + } +} diff --git a/ggml/src/ggml-opencl/ggml-opencl.cpp b/ggml/src/ggml-opencl/ggml-opencl.cpp index d07b8fe41a31..fc0fce0d780a 100644 --- a/ggml/src/ggml-opencl/ggml-opencl.cpp +++ b/ggml/src/ggml-opencl/ggml-opencl.cpp @@ -7065,7 +7065,7 @@ static inline bool use_flat_gemv_for_large_m_q4_K(const ggml_tensor *tensor) { return tensor->ne[1] >= 32768 && tensor->ne[2] == 1 && tensor->ne[3] == 1; } -static inline bool use_flat_gemv_for_large_m_q6_K(const ggml_tensor *tensor) { +static inline bool use_flat_gemv_for_large_m_q6_K(const ggml_backend_opencl_context *backend_ctx, const ggml_tensor *tensor) { // gemv_noshuffle variant perf drops for large M, use flat variant for large M. // threshold is well above typical hidden/FFN dims, but below typical vocab sizes. // q6_K flat gemv is worse for smaller K; 2048 seems to be a reasonable threshold. @@ -7083,7 +7083,15 @@ static inline bool use_flat_gemv_for_large_m_q6_K(const ggml_tensor *tensor) { if ((tensor->ne[1] % 128 != 0) && tensor->ne[2] == 1 && tensor->ne[3] == 1) { return true; } - return tensor->ne[1] >= 32768 && tensor->ne[0] >= 2048 && tensor->ne[2] == 1 && tensor->ne[3] == 1; + + // The gemv_noshuffle slowdown tracks TOTAL weight size, not ne0 alone; ne0 >= 2048 is a + // proxy for "large weight" that misses a narrow-hidden vocab-scale lm_head. + // Add a direct size escape so such weights also take the flat path, without changing + // which weights ne0 >= 2048 already routes there. + // The size escape is not taken on the A7X since its compiler miscompiles the flat K-quant GEMV + return tensor->ne[1] >= 32768 + && (tensor->ne[0] >= 2048 || (backend_ctx->adreno_gen != ADRENO_GPU_GEN::A7X && ggml_nbytes(tensor) >= (256ull << 20))) + && tensor->ne[2] == 1 && tensor->ne[3] == 1; } static bool ggml_opencl_supports_op(ggml_backend_dev_t dev, const struct ggml_tensor * op) { @@ -7495,6 +7503,7 @@ static ggml_backend_i ggml_backend_opencl_i = { ggml_backend_t ggml_backend_opencl_init(void) { ggml_backend_dev_t dev = ggml_backend_reg_dev_get(ggml_backend_opencl_reg(), 0); ggml_backend_opencl_context *backend_ctx = ggml_cl_init(dev); + backend_ctx->ref_count++; ggml_backend_t backend = new ggml_backend { /* .guid = */ ggml_backend_opencl_guid(), @@ -9402,7 +9411,7 @@ static void ggml_backend_opencl_buffer_set_tensor(ggml_backend_buffer_t buffer, cl_kernel kernel; #ifdef GGML_OPENCL_USE_ADRENO_KERNELS kernel = backend_ctx->kernel_convert_block_q6_K; - if (use_adreno_kernels(backend_ctx, tensor) && !use_flat_gemv_for_large_m_q6_K(tensor)) { + if (use_adreno_kernels(backend_ctx, tensor) && !use_flat_gemv_for_large_m_q6_K(backend_ctx, tensor)) { kernel = backend_ctx->kernel_convert_block_q6_K_noshuffle; } #else @@ -9435,7 +9444,7 @@ static void ggml_backend_opencl_buffer_set_tensor(ggml_backend_buffer_t buffer, tensor->extra = extra; #ifdef GGML_OPENCL_USE_ADRENO_KERNELS - if (use_adreno_kernels(backend_ctx, tensor) && !use_flat_gemv_for_large_m_q6_K(tensor)) { + if (use_adreno_kernels(backend_ctx, tensor) && !use_flat_gemv_for_large_m_q6_K(backend_ctx, tensor)) { cl_int M = tensor->ne[1]; // ne01 cl_int K = tensor->ne[0]; // ne00 @@ -10472,7 +10481,7 @@ static void ggml_backend_opencl_buffer_get_tensor(ggml_backend_buffer_t buffer, CL_CHECK(clReleaseMemObject(data_device)); return; } - if (use_adreno_kernels(backend_ctx, tensor) && !use_flat_gemv_for_large_m_q6_K(tensor)) { + if (use_adreno_kernels(backend_ctx, tensor) && !use_flat_gemv_for_large_m_q6_K(backend_ctx, tensor)) { static ggml_cl_buffer buf_trans_ql; static ggml_cl_buffer buf_trans_qh; static ggml_cl_buffer buf_trans_s; @@ -18894,7 +18903,7 @@ static void ggml_cl_mul_mat(ggml_backend_t backend, const ggml_tensor * src0, co } // q6_K x fp32 - if (src0t == GGML_TYPE_Q6_K && src1t == GGML_TYPE_F32 && !use_flat_gemv_for_large_m_q6_K(src0)) { + if (src0t == GGML_TYPE_Q6_K && src1t == GGML_TYPE_F32 && !use_flat_gemv_for_large_m_q6_K(backend_ctx, src0)) { ggml_cl_mul_mat_q6_K_f32_adreno(backend, src0, src1, dst); return; } @@ -24259,7 +24268,7 @@ static void ggml_cl_glu(ggml_backend_t backend, const ggml_tensor * src0, const } const size_t nrows = ggml_nrows(src0); - size_t nth = 512; + size_t nth = backend_ctx->max_workgroup_size < 512 ? backend_ctx->max_workgroup_size : 512; size_t global_work_size[] = {nrows*nth, 1, 1}; size_t local_work_size[] = {nth, 1, 1}; diff --git a/ggml/src/ggml-sycl/common.hpp b/ggml/src/ggml-sycl/common.hpp index 160331191d10..619933e0fda7 100644 --- a/ggml/src/ggml-sycl/common.hpp +++ b/ggml/src/ggml-sycl/common.hpp @@ -235,6 +235,7 @@ struct sycl_device_info { int max_wg_per_cu; // max work groups per compute unit - refer to // cudaOccupancyMaxActiveBlocksPerMultiprocessor bool vmm; // virtual memory support + bool l0_device_type_valid; bool l0_discrete_gpu; // Level Zero backend and not an integrated GPU size_t vmm_granularity; // granularity of virtual memory size_t total_vram; diff --git a/ggml/src/ggml-sycl/concat.cpp b/ggml/src/ggml-sycl/concat.cpp index 93e00d65fcd3..1ad242fcafbb 100644 --- a/ggml/src/ggml-sycl/concat.cpp +++ b/ggml/src/ggml-sycl/concat.cpp @@ -127,7 +127,15 @@ static void concat_T_sycl_non_cont( int64_t ne2, int64_t ne3, uint64_t nb0, uint64_t nb1, uint64_t nb2, uint64_t nb3, int32_t dim) { sycl::range<3> gridDim(ne3, ne2, ne1); - stream->parallel_for(sycl::nd_range<3>(gridDim, sycl::range<3>(1, 1, 1)), [=](sycl::nd_item<3> item_ct1) { + + // Avoid oversubscribing device when there is not enough elements along the innermost dim to + // fill a full SYCL_CONCAT_BLOCK_SIZE. For larger # of elements, the full SYCL_CONCAT_BLOCK_SIZE + // is used. + const int64_t ne0_pad = GGML_PAD(ne0, WARP_SIZE); + const int64_t block_ne0 = ne0_pad < SYCL_CONCAT_BLOCK_SIZE ? ne0_pad : (int64_t) SYCL_CONCAT_BLOCK_SIZE; + sycl::range<3> blockDim(1, 1, block_ne0); + + stream->parallel_for(sycl::nd_range<3>(gridDim * blockDim, blockDim), [=](sycl::nd_item<3> item_ct1) { int64_t i3 = item_ct1.get_group(0); int64_t i2 = item_ct1.get_group(1); int64_t i1 = item_ct1.get_group(2); diff --git a/ggml/src/ggml-sycl/cpy.cpp b/ggml/src/ggml-sycl/cpy.cpp index 5d0f9a89fd33..55e076172237 100644 --- a/ggml/src/ggml-sycl/cpy.cpp +++ b/ggml/src/ggml-sycl/cpy.cpp @@ -8,7 +8,6 @@ #include "ggml-sycl/presets.hpp" #include "ggml.h" - static void cpy_1_f32_f32(const char * cxi, char * cdsti) { const float * xi = (const float *) cxi; float * dsti = (float *) cdsti; @@ -151,6 +150,20 @@ static void cpy_blck_q8_0_f32(const char * cxi, char * cdsti) { } } +static void cpy_blck_q2_0_f32(const char * cxi, char * cdsti) { + const block_q2_0 * xi = (const block_q2_0 *) cxi; + float * cdstf = (float *) cdsti; + + const float d = xi->d; + + for (int j = 0; j < QK2_0; ++j) { + const int byte_index = j / 4; + const int bit_offset = (j % 4) * 2; + const int q = (xi->qs[byte_index] >> bit_offset) & 0x3; + cdstf[j] = (float) (q - 1) * d; + } +} + template static void cpy_blck_q_f32(const char * cxi, char * cdsti) { @@ -256,7 +269,7 @@ static void ggml_cpy_f16_f32_sycl(const char * cx, char * cdst, const int ne, co stream->parallel_for( sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_f16(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); @@ -274,7 +287,7 @@ static void ggml_cpy_f32_f32_sycl(const char * cx, char * cdst, const int ne, co stream->parallel_for( sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_f16(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); @@ -292,7 +305,7 @@ static void ggml_cpy_f32_f16_sycl(const char * cx, char * cdst, const int ne, co stream->parallel_for( sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_f16(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); @@ -308,7 +321,7 @@ static void ggml_cpy_f32_i32_sycl(const char * cx, char * cdst, const int ne, co stream->parallel_for( sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_f16(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); @@ -324,7 +337,7 @@ static void ggml_cpy_i32_f32_sycl(const char * cx, char * cdst, const int ne, co stream->parallel_for( sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_f16(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); @@ -338,7 +351,7 @@ static void ggml_cpy_f32_q8_0_sycl(const char * cx, char * cdst, const int ne, c GGML_ASSERT(ne % QK8_0 == 0); const int num_blocks = ne / QK8_0; stream->parallel_for(sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); @@ -350,12 +363,25 @@ static void ggml_cpy_q8_0_f32_sycl(const char * cx, char * cdst, const int ne, c const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ne; stream->parallel_for(sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_f32(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } +static void ggml_cpy_q2_0_f32_sycl(const char * cx, char * cdst, const int ne, const int ne00, const int ne01, + const int ne02, const int nb00, const int nb01, const int nb02, const int nb03, + const int ne10, const int ne11, const int ne12, const int nb10, const int nb11, + const int nb12, const int nb13, queue_ptr stream) { + const int num_blocks = ne; + stream->parallel_for( + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { + cpy_q_f32(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, + ne12, nb10, nb11, nb12, nb13, item_ct1); + }); +} + static void ggml_cpy_f32_q4_0_sycl(const char * cx, char * cdst, const int ne, const int ne00, const int ne01, const int ne02, const int nb00, const int nb01, const int nb02, const int nb03, const int ne10, const int ne11, const int ne12, const int nb10, const int nb11, @@ -363,7 +389,7 @@ static void ggml_cpy_f32_q4_0_sycl(const char * cx, char * cdst, const int ne, c GGML_ASSERT(ne % QK4_0 == 0); const int num_blocks = ne / QK4_0; stream->parallel_for(sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); @@ -375,7 +401,8 @@ static void ggml_cpy_q4_0_f32_sycl(const char * cx, char * cdst, const int ne, c const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ne; stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_f32, QK4_0>(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); @@ -389,7 +416,7 @@ static void ggml_cpy_f32_q4_1_sycl(const char * cx, char * cdst, const int ne, c GGML_ASSERT(ne % QK4_1 == 0); const int num_blocks = ne / QK4_1; stream->parallel_for(sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); @@ -401,7 +428,8 @@ static void ggml_cpy_q4_1_f32_sycl(const char * cx, char * cdst, const int ne, c const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ne; stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_f32, QK4_1>(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); @@ -415,7 +443,7 @@ static void ggml_cpy_f32_q5_0_sycl(const char * cx, char * cdst, const int ne, c GGML_ASSERT(ne % QK5_0 == 0); const int num_blocks = ne / QK5_0; stream->parallel_for(sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { cpy_f32_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); @@ -427,7 +455,8 @@ static void ggml_cpy_q5_0_f32_sycl(const char * cx, char * cdst, const int ne, c const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ne; stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_f32, QK5_0>(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); @@ -441,7 +470,7 @@ static void ggml_cpy_f32_q5_1_sycl(const char * cx, char * cdst, const int ne, c GGML_ASSERT(ne % QK5_1 == 0); const int num_blocks = ne / QK5_1; stream->parallel_for(sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); @@ -453,7 +482,8 @@ static void ggml_cpy_q5_1_f32_sycl(const char * cx, char * cdst, const int ne, c const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ne; stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_f32, QK5_1>(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); @@ -466,7 +496,8 @@ static void ggml_cpy_mxfp4_f32_sycl(const char * cx, char * cdst, const int ne, const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ne; stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { cpy_q_f32, QK_MXFP4>(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); @@ -480,7 +511,8 @@ static void ggml_cpy_f32_iq4_nl_sycl(const char * cx, char * cdst, const int ne, GGML_ASSERT(ne % QK4_NL == 0); const int num_blocks = ne / QK4_NL; stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { cpy_f32_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); @@ -526,7 +558,7 @@ static void ggml_cpy_f16_q4_0_sycl(const char * cx, char * cdst, const int ne, c GGML_ASSERT(ne % QK4_0 == 0); const int num_blocks = ne / QK4_0; stream->parallel_for(sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); @@ -540,7 +572,7 @@ static void ggml_cpy_f16_q4_1_sycl(const char * cx, char * cdst, const int ne, c GGML_ASSERT(ne % QK4_1 == 0); const int num_blocks = ne / QK4_1; stream->parallel_for(sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); @@ -554,7 +586,7 @@ static void ggml_cpy_f16_q5_0_sycl(const char * cx, char * cdst, const int ne, c GGML_ASSERT(ne % QK5_0 == 0); const int num_blocks = ne / QK5_0; stream->parallel_for(sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks), sycl::range<3>(1, 1, 1)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); @@ -564,6 +596,7 @@ static void ggml_cpy_f16_q5_0_sycl(const char * cx, char * cdst, const int ne, c static bool ggml_sycl_is_quantized_type(enum ggml_type type) { switch (type) { case GGML_TYPE_Q1_0: + case GGML_TYPE_Q2_0: case GGML_TYPE_Q4_0: case GGML_TYPE_Q4_1: case GGML_TYPE_Q5_0: @@ -594,6 +627,7 @@ static bool ggml_sycl_is_quantized_type(enum ggml_type type) { static bool ggml_sycl_can_quantize_rows_sycl(enum ggml_type type) { switch (type) { case GGML_TYPE_Q1_0: + case GGML_TYPE_Q2_0: case GGML_TYPE_Q4_0: case GGML_TYPE_Q4_1: case GGML_TYPE_Q5_0: @@ -651,7 +685,8 @@ static void ggml_sycl_quantize_rows_q(const char * cx, char * cdst, const int64_ constexpr int block_size = 256; const int64_t grid_size = ceil_div(total_blocks, (int64_t) block_size); - stream->parallel_for(sycl::nd_range<1>(grid_size * block_size, block_size), [=](sycl::nd_item<1> item_ct1) { + stream->parallel_for(sycl::nd_range<1>(grid_size * block_size, block_size), + [=](sycl::nd_item<1> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { const int64_t block_idx = item_ct1.get_global_linear_id(); if (block_idx >= total_blocks) { return; @@ -708,6 +743,11 @@ static void ggml_sycl_quantize_rows_sycl(const char * cx, char * cdst, const ggm nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, stream); break; + case GGML_TYPE_Q2_0: + ggml_sycl_quantize_rows_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, + nb02, nb03, ne10, ne11, ne12, nb10, nb11, + nb12, nb13, stream); + break; case GGML_TYPE_Q5_1: ggml_sycl_quantize_rows_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, @@ -760,7 +800,7 @@ static void ggml_cpy_f16_f16_sycl(const char * cx, char * cdst, const int ne, co stream->parallel_for( sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_f16(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); @@ -779,7 +819,7 @@ static void ggml_cpy_i16_i16_sycl(const char * cx, char * cdst, const int ne, co stream->parallel_for( sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_f16(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); @@ -798,7 +838,7 @@ static void ggml_cpy_i32_i32_sycl(const char * cx, char * cdst, const int ne, co stream->parallel_for( sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_f16(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); @@ -812,7 +852,8 @@ static void ggml_cpy_q8_0_q8_0(const char * cx, char * cdst, const int ne, const const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), - sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -825,7 +866,8 @@ static void ggml_cpy_q5_0_q5_0(const char * cx, char * cdst, const int ne, const const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), - sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -839,7 +881,8 @@ static void ggml_cpy_q5_1_q5_1(const char * cx, char * cdst, const int ne, const stream->parallel_for( sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), - sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -851,7 +894,8 @@ static void ggml_cpy_q4_0_q4_0(const char * cx, char * cdst, const int ne, const const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -864,7 +908,8 @@ static void ggml_cpy_q4_1_q4_1(const char * cx, char * cdst, const int ne, const const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -875,18 +920,32 @@ static void ggml_cpy_q1_0_q1_0(const char * cx, char * cdst, const int ne, const const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } +static void ggml_cpy_q2_0_q2_0(const char * cx, char * cdst, const int ne, const int ne00, const int ne01, + const int ne02, const int nb00, const int nb01, const int nb02, const int nb03, + const int ne10, const int ne11, const int ne12, const int nb10, const int nb11, + const int nb12, const int nb13, queue_ptr stream) { + const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); + stream->parallel_for( + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ + cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); + }); +} + static void ggml_cpy_mxfp4_mxfp4(const char * cx, char * cdst, const int ne, const int ne00, const int ne01, const int ne02, const int nb00, const int nb01, const int nb02, const int nb03, const int ne10, const int ne11, const int ne12, const int nb10, const int nb11, const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]] { cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -897,7 +956,8 @@ static void ggml_cpy_nvfp4_nvfp4(const char * cx, char * cdst, const int ne, con const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -908,7 +968,8 @@ static void ggml_cpy_q2_K_q2_K(const char * cx, char * cdst, const int ne, const const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -919,7 +980,8 @@ static void ggml_cpy_q3_K_q3_K(const char * cx, char * cdst, const int ne, const const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -930,7 +992,8 @@ static void ggml_cpy_q4_K_q4_K(const char * cx, char * cdst, const int ne, const const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -941,7 +1004,8 @@ static void ggml_cpy_q5_K_q5_K(const char * cx, char * cdst, const int ne, const const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -952,7 +1016,8 @@ static void ggml_cpy_q6_K_q6_K(const char * cx, char * cdst, const int ne, const const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -963,7 +1028,8 @@ static void ggml_cpy_iq2_xxs_iq2_xxs(const char * cx, char * cdst, const int ne, const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -974,7 +1040,8 @@ static void ggml_cpy_iq2_xs_iq2_xs(const char * cx, char * cdst, const int ne, c const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -985,7 +1052,8 @@ static void ggml_cpy_iq2_s_iq2_s(const char * cx, char * cdst, const int ne, con const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -996,7 +1064,8 @@ static void ggml_cpy_iq3_xxs_iq3_xxs(const char * cx, char * cdst, const int ne, const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -1007,7 +1076,8 @@ static void ggml_cpy_iq1_s_iq1_s(const char * cx, char * cdst, const int ne, con const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -1018,7 +1088,8 @@ static void ggml_cpy_iq1_m_iq1_m(const char * cx, char * cdst, const int ne, con const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -1029,7 +1100,8 @@ static void ggml_cpy_iq4_nl_iq4_nl(const char * cx, char * cdst, const int ne, c const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -1040,7 +1112,8 @@ static void ggml_cpy_iq3_s_iq3_s(const char * cx, char * cdst, const int ne, con const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -1051,7 +1124,8 @@ static void ggml_cpy_iq4_xs_iq4_xs(const char * cx, char * cdst, const int ne, c const int nb12, const int nb13, queue_ptr stream) { const int num_blocks = ceil_div(ne, SYCL_CPY_BLOCK_SIZE); stream->parallel_for( - sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), [=](sycl::nd_item<3> item_ct1) { + sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_q_q(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); } @@ -1065,7 +1139,7 @@ static void ggml_cpy_f32_bf16_sycl(const char * cx, char * cdst, const int ne, c stream->parallel_for( sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_f16(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); @@ -1079,7 +1153,7 @@ static void ggml_cpy_bf16_f32_sycl(const char * cx, char * cdst, const int ne, c stream->parallel_for( sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_f16(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); @@ -1093,7 +1167,7 @@ static void ggml_cpy_bf16_bf16_sycl(const char * cx, char * cdst, const int ne, stream->parallel_for( sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_f16(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); @@ -1107,7 +1181,7 @@ static void ggml_cpy_f16_bf16_sycl(const char * cx, char * cdst, const int ne, c stream->parallel_for( sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_f16(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); @@ -1121,7 +1195,7 @@ static void ggml_cpy_bf16_f16_sycl(const char * cx, char * cdst, const int ne, c stream->parallel_for( sycl::nd_range<3>(sycl::range<3>(1, 1, num_blocks) * sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE), sycl::range<3>(1, 1, SYCL_CPY_BLOCK_SIZE)), - [=](sycl::nd_item<3> item_ct1) { + [=](sycl::nd_item<3> item_ct1) [[sycl::reqd_sub_group_size(WARP_SIZE)]]{ cpy_f32_f16(cx, cdst, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, item_ct1); }); @@ -1213,6 +1287,9 @@ void ggml_sycl_cpy(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, co } else if (src0->type == GGML_TYPE_Q8_0 && src1->type == GGML_TYPE_F32) { ggml_cpy_q8_0_f32_sycl(src0_ddc, src1_ddc, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, main_stream); + } else if (src0->type == GGML_TYPE_Q2_0 && src1->type == GGML_TYPE_F32) { + ggml_cpy_q2_0_f32_sycl(src0_ddc, src1_ddc, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, + nb10, nb11, nb12, nb13, main_stream); } else if (src0->type == GGML_TYPE_F32 && src1->type == GGML_TYPE_Q5_0) { ggml_cpy_f32_q5_0_sycl(src0_ddc, src1_ddc, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, main_stream); @@ -1243,6 +1320,8 @@ void ggml_sycl_cpy(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, co ggml_cpy_q4_1_q4_1(src0_ddc, src1_ddc, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, main_stream); } else if (src0->type == GGML_TYPE_Q1_0 && src1->type == GGML_TYPE_Q1_0) { ggml_cpy_q1_0_q1_0(src0_ddc, src1_ddc, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, main_stream); + } else if (src0->type == GGML_TYPE_Q2_0 && src1->type == GGML_TYPE_Q2_0) { + ggml_cpy_q2_0_q2_0(src0_ddc, src1_ddc, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, main_stream); } else if (src0->type == GGML_TYPE_MXFP4 && src1->type == GGML_TYPE_MXFP4) { ggml_cpy_mxfp4_mxfp4(src0_ddc, src1_ddc, ne, ne00, ne01, ne02, nb00, nb01, nb02, nb03, ne10, ne11, ne12, nb10, nb11, nb12, nb13, main_stream); } else if (src0->type == GGML_TYPE_NVFP4 && src1->type == GGML_TYPE_NVFP4) { diff --git a/ggml/src/ggml-sycl/cpy.hpp b/ggml/src/ggml-sycl/cpy.hpp index c4cfd961da2a..34bae1b2dd18 100644 --- a/ggml/src/ggml-sycl/cpy.hpp +++ b/ggml/src/ggml-sycl/cpy.hpp @@ -70,6 +70,39 @@ inline void cpy_blck_f32_q1_0(const char * cxi, char * cdsti) { } } +inline int round_nearest_int(float x) { + return (int)(x >= 0.0f ? x + 0.5f : x - 0.5f); +} + +inline void cpy_blck_f32_q2_0(const char * cxi, char * cdsti) { + const float * xi = (const float *) cxi; + block_q2_0 * dsti = (block_q2_0 *) cdsti; + + float amax = 0.0f; + + for (int j = 0; j < QK2_0; ++j) { + amax = sycl::fmax(amax, sycl::fabs((float) xi[j])); + } + + const float d = amax; + const float id = d > 0.0f ? 1.0f / d : 0.0f; + + dsti->d = d; + + for (int j = 0; j < QK2_0 / 4; ++j) { + dsti->qs[j] = 0; + } + + for (int j = 0; j < QK2_0; ++j) { + int q = round_nearest_int(xi[j] * id) + 1; + q = dpct::max(0, dpct::min(3, q)); + + const int byte_index = j / 4; + const int bit_offset = (j % 4) * 2; + dsti->qs[byte_index] |= (uint8_t) q << bit_offset; + } +} + inline int best_index_mxfp4(const float x, const float e) { int best_index = 0; float best_err = sycl::fabs((float) (kvalues_mxfp4[0] * e - x)); diff --git a/ggml/src/ggml-sycl/fattn-mkl.cpp b/ggml/src/ggml-sycl/fattn-mkl.cpp new file mode 100644 index 000000000000..fc22b7bdb8c5 --- /dev/null +++ b/ggml/src/ggml-sycl/fattn-mkl.cpp @@ -0,0 +1,690 @@ +// Flash attention via oneMKL GEMM (XMX-accelerated). +// Uses column_major::gemm for Q*K^T and S*V matmuls +// with an online softmax SYCL kernel. +// +// All GQA query heads sharing a KV head are batched into single +// GEMM calls, amortizing MKL launch overhead across K and V reuse. +// + +#include "common.hpp" +#include "fattn-common.hpp" +#include "fattn-buffers.hpp" +#include "convert.hpp" +#include "fattn.hpp" + +#include +#include +#include + +#define MKL_FA_CHUNK_SIZE_KV 8192 + +// Number of query rows processed per tile. The score buffers (KQ_f32, S_f16) +// are sized q_tile_rows * chunk_size, so this bounds their footprint +// regardless of batch size (n_query_rows = n_queries * gqa_ratio). A typical +// single-ubatch prefill (e.g. ubatch 1024 * gqa 8 = 8192 rows) is exactly one +// tile, so it runs with no extra iterations. Larger batches tile and stay +// bounded. Override with GGML_SYCL_MKL_FA_Q_TILE. +#define MKL_FA_Q_TILE 8192 + +#define MKL_FA_WG_SIZE 256 + +using oneapi::mkl::transpose; +using oneapi::mkl::blas::column_major::gemm; + +// --------------------------------------------------------------------------- +// Helpers +// --------------------------------------------------------------------------- + +// Pack all GQA Q heads for one KV head into fp16, applying q_scale. +// Launches one kernel per GQA group — each kernel copies exactly +// n_queries * DKQ elements using the per-group dst offset and +// per-head source stride. +static void mkl_fa_pack_q_fp16( + dpct::queue_ptr stream, + sycl::half * __restrict dst, + const float * __restrict q_src, + int n_queries, int n_query_rows, int DKQ, + int gqa_ratio, int kvh_base_head, + float q_scale, int64_t q_row_stride, int64_t q_head_stride, + int64_t wg_size) { + + for (int iqg = 0; iqg < gqa_ratio; iqg++) { + int iqh = kvh_base_head + iqg; + sycl::half * dst_g = dst + (int64_t)iqg * n_queries * DKQ; + + const int64_t n_elem = (int64_t)n_queries * DKQ; + const int64_t wg = ((n_elem + wg_size - 1) / wg_size) * wg_size; + + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for(sycl::nd_range<1>(wg, wg_size), + [=](sycl::nd_item<1> item) { + int64_t e = item.get_global_id(0); + if (e >= n_elem) return; + + int64_t q = e / DKQ; + int64_t d = e - q * DKQ; + + // Stride-aware source offset: handles permuted, + // sliced, or contiguous Q tensor layouts. + int64_t src_off = d + + q * q_row_stride + + (int64_t)iqh * q_head_stride; + + dst_g[e] = sycl::half( + q_src[src_off] * q_scale); + }); + }); + } +} + +// Zero-initialize the online softmax state arrays. +// KQ_max → -inf, KQ_sum → 0, VKQ_accum → 0. +// Merged into one kernel to avoid per-array launch overhead. +static void mkl_fa_init_softmax_state( + dpct::queue_ptr stream, + float * kmax, float * ksum, float * vacc, + int n_query_rows, int DV, int64_t wg_size) { + + const float neg_inf = -1e30f; + const int64_t n_maxsum = n_query_rows; + const int64_t n_vacc = (int64_t)n_query_rows * DV; + const int64_t total = (n_vacc > n_maxsum) ? n_vacc : n_maxsum; + const int64_t wg = ((total + wg_size - 1) / wg_size) * wg_size; + + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for(sycl::nd_range<1>(wg, wg_size), + [=](sycl::nd_item<1> item) { + int64_t i = item.get_global_id(0); + if (i < n_maxsum) { + kmax[i] = neg_inf; + ksum[i] = 0.0f; + } + if (i < n_vacc) { + vacc[i] = 0.0f; + } + }); + }); +} + +// Online softmax over one KV chunk for a tile of GQA query rows. +// The tile spans absolute rows [q0, q0 + q_rows). Score buffers +// (KQ_f32/S_f16) are indexed RELATIVE to the tile; the persistent state +// (VKQ_accum/KQ_max/KQ_sum) and mask are indexed by ABSOLUTE row. +// For each row: find local max → rescale previous VKQ_accum → +// compute exp(s - max) → write S_f16 → update running max/sum. +static void mkl_fa_online_softmax_chunk( + dpct::queue_ptr stream, + float * __restrict KQ_f32, + sycl::half * __restrict S_f16, + float * __restrict KQ_max, + float * __restrict KQ_sum, + float * __restrict VKQ_accum, + int q0, int q_rows, int n_queries, int DV, + int chunk_size, int chunk_start, + int kvh_head, int gqa_ratio, + const sycl::half * mask_data, int64_t mask_head_stride, + int64_t mask_row_stride, int mask_n_heads, + float logit_softcap, int64_t wg_size) { + + const int64_t wg = ((q_rows + wg_size - 1) / wg_size) * wg_size; + + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for(sycl::nd_range<1>(wg, wg_size), + [=](sycl::nd_item<1> item) { + int jc_rel = item.get_global_id(0); + if (jc_rel >= q_rows) return; + int jc_abs = q0 + jc_rel; + + const int gqa_group = jc_abs / n_queries; + const int q_row = jc_abs % n_queries; + + // Score buffers are tile-local (relative index). + const float * __restrict KQ_row = KQ_f32 + + jc_rel * (int64_t)chunk_size; + // Persistent accumulator is full-sized (absolute index). + float * __restrict vkq = VKQ_accum + + jc_abs * (int64_t)DV; + + const sycl::half * mask_h = nullptr; + int64_t m_stride = 0; + if (mask_data) { + int m_head = (mask_n_heads > 1) + ? (kvh_head + gqa_group) : 0; + mask_h = mask_data + (int64_t)m_head * mask_head_stride; + m_stride = mask_row_stride; + } + + // Row-wise local maximum (softcap before mask) + float local_max = -1e30f; + for (int i = 0; i < chunk_size; i++) { + float s = KQ_row[i]; + if (logit_softcap != 0.0f) { + s = logit_softcap * sycl::tanh(s); + } + if (mask_h) { + s += (float)mask_h[q_row * m_stride + + (chunk_start + i)]; + } + if (s > local_max) local_max = s; + } + + // Rescale previous accumulator by exp(old_max - new_max) + float old_max = KQ_max[jc_abs]; + float new_max = (old_max > local_max) ? old_max : local_max; + float rescale = (old_max < -1e29f) ? 1.0f + : sycl::native::exp(old_max - new_max); + + for (int v = 0; v < DV; v++) { + vkq[v] *= rescale; + } + + // Softmax and write S_f16 (tile-local index) + float local_sum = 0.0f; + sycl::half * __restrict S_row = S_f16 + + jc_rel * (int64_t)chunk_size; + + for (int i = 0; i < chunk_size; i++) { + float s = KQ_row[i]; + if (logit_softcap != 0.0f) { + s = logit_softcap * sycl::tanh(s); + } + if (mask_h) { + s += (float)mask_h[q_row * m_stride + + (chunk_start + i)]; + } + float val = sycl::native::exp(s - new_max); + S_row[i] = sycl::half(val); + local_sum += val; + } + + KQ_sum[jc_abs] = KQ_sum[jc_abs] * rescale + local_sum; + KQ_max[jc_abs] = new_max; + }); + }); +} + +// Write one GQA group's normalized output to its destination head. +static void mkl_fa_normalize_head( + dpct::queue_ptr stream, + float * __restrict dst_batch, + const float * __restrict VKQ_accum, + const float * __restrict KQ_sum, + int iqh, int n_queries, int DV, int n_q_heads, + int64_t src_offset, int64_t wg_size) { + + const int64_t wg = ((n_queries + wg_size - 1) / wg_size) * wg_size; + + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for(sycl::nd_range<1>(wg, wg_size), + [=](sycl::nd_item<1> item) { + int jc = item.get_global_id(0); + if (jc >= n_queries) return; + + int ksum_idx = (int)(src_offset / DV) + jc; + float inv_sum = 1.0f / KQ_sum[ksum_idx]; + const float * __restrict src = VKQ_accum + + src_offset + jc * (int64_t)DV; + // Interleaved dst layout (matching TILE): + // rows alternate between heads, then increment query. + // offset = (query * n_q_heads + head) * DV + float * __restrict dst_row = dst_batch + + ((int64_t)jc * n_q_heads + iqh) * (int64_t)DV; + + for (int v = 0; v < DV; v++) { + dst_row[v] = src[v] * inv_sum; + } + }); + }); +} + +// --------------------------------------------------------------------------- +// Per-chunk dequant +// +// Rather than dequantizing all of K/V up front (footprint scales with +// context), we dequant one KV-head chunk at a time into a dense +// [this_chunk x D] fp16 buffer (row-major, lda = D). The source address of +// element (head=ikvh, row=chunk_start+r, col=c) decomposes into independent +// linear terms head_off(ikvh) + row_off(chunk_start) + (r,c), so slicing a +// chunk is a clean pointer offset in every layout case. The true-Gemma- +// interleave vs padded-seq-view distinction is resolved once when the +// descriptor is built; slicing does not reintroduce it. +// --------------------------------------------------------------------------- +enum mkl_fa_kv_desc_mode { + MKL_FA_KV_MODE_F16_DENSE = 0, + MKL_FA_KV_MODE_F16_INTERLEAVED = 1, + MKL_FA_KV_MODE_QUANT_CONTIG = 2, + MKL_FA_KV_MODE_QUANT_NC = 3, +}; + +struct mkl_fa_kv_desc { + const char * data = nullptr; + ggml_type type = GGML_TYPE_F16; + int64_t D = 0; // ne[0] + int64_t nb1 = 0; // byte stride, seq dim + int64_t nb2 = 0; // byte stride, head dim + mkl_fa_kv_desc_mode mode = MKL_FA_KV_MODE_F16_DENSE; + int64_t ts = 0; // type size (mode 3 base offset) + int64_t s01 = 0; // nc row stride in blocks (mode 3) + int64_t s02 = 0; // nc head stride in blocks (mode 3) +}; + +static mkl_fa_kv_desc mkl_fa_make_desc(const ggml_tensor * T, bool interleaved, int n_kv_heads) { + mkl_fa_kv_desc d; + d.data = (const char *)T->data; + d.type = T->type; + d.D = T->ne[0]; + d.nb1 = (int64_t)T->nb[1]; + d.nb2 = (int64_t)T->nb[2]; + d.ts = (int64_t)ggml_type_size(T->type); + + if (T->type == GGML_TYPE_F16) { + d.mode = interleaved ? MKL_FA_KV_MODE_F16_INTERLEAVED + : MKL_FA_KV_MODE_F16_DENSE; + } else if (ggml_is_contiguously_allocated(T) && !interleaved) { + d.mode = MKL_FA_KV_MODE_QUANT_CONTIG; + } else { + d.mode = MKL_FA_KV_MODE_QUANT_NC; + const int64_t bs = (int64_t)ggml_blck_size(T->type); + const int64_t blk_per_row = T->ne[0] / bs; + // True Gemma interleave packs heads within a row (nb[2] < ne[1]*nb[1]) + // → reconstruct physical strides. Padded seq-views (nb[2] > ne[1]*nb[1]) + // already have correct physical strides. + const bool gemma = interleaved && + ((int64_t)T->nb[2] < (int64_t)T->ne[1] * (int64_t)T->nb[1]); + if (gemma) { + d.s01 = (int64_t)n_kv_heads * blk_per_row; + d.s02 = blk_per_row; + } else { + d.s01 = d.nb1 / d.ts; + d.s02 = d.nb2 / d.ts; + } + } + return d; +} + +// Dequant one KV-head chunk into a dense [this_chunk x D] fp16 buffer. +static void mkl_fa_dequant_chunk( + dpct::queue_ptr stream, const mkl_fa_kv_desc & d, ggml_tensor * dst_ctx, + sycl::half * out, int ikvh, int chunk_start, int this_chunk) { + + const int64_t D = d.D; + switch (d.mode) { + case MKL_FA_KV_MODE_F16_DENSE: { + const char * base = d.data + (int64_t)ikvh * d.nb2 + + (int64_t)chunk_start * d.nb1; + stream->memcpy(out, base, (size_t)this_chunk * D * sizeof(sycl::half)); + break; + } + case MKL_FA_KV_MODE_F16_INTERLEAVED: { + const char * base = d.data + (int64_t)ikvh * d.nb2 + + (int64_t)chunk_start * d.nb1; + const int64_t row_halfs = d.nb1 / (int64_t)sizeof(sycl::half); + const sycl::half * src = (const sycl::half *)base; + stream->parallel_for( + sycl::range<2>((size_t)this_chunk, (size_t)D), + [=](sycl::item<2> it) { + int64_t r = it.get_id(0); + int64_t c = it.get_id(1); + out[r * D + c] = src[r * row_halfs + c]; + }); + break; + } + case MKL_FA_KV_MODE_QUANT_CONTIG: { + const char * base = d.data + (int64_t)ikvh * d.nb2 + + (int64_t)chunk_start * d.nb1; + to_fp16_sycl_t to_fp16 = ggml_get_to_fp16_sycl(d.type, dst_ctx); + to_fp16(base, out, (int64_t)this_chunk * D, stream); + break; + } + default: { // MKL_FA_KV_MODE_QUANT_NC + to_fp16_nc_sycl_t to_fp16 = ggml_get_to_fp16_nc_sycl(d.type); + const int64_t base_blocks = (int64_t)ikvh * d.s02 + + (int64_t)chunk_start * d.s01; + const char * base = d.data + base_blocks * d.ts; + // ne02 = ne03 = 1 → s02/s03 inert; head+chunk offset carried by base. + to_fp16(base, out, D, this_chunk, 1, 1, d.s01, d.s02, d.s02, stream); + break; + } + } +} + +// --------------------------------------------------------------------------- +// MKL Flash Attention orchestrator +// +// Pipeline: dequantize K/V → for each KV head: +// pack GQA Q heads → MKL GEMM KQ → online softmax → +// MKL GEMM VKQ → accumulate → normalize → scatter to dst +// --------------------------------------------------------------------------- +void ggml_sycl_flash_attn_ext_mkl(ggml_backend_sycl_context & ctx, ggml_tensor * dst) { + + const ggml_tensor * Q = dst->src[0]; + const ggml_tensor * K = dst->src[1]; + const ggml_tensor * V = dst->src[2]; + const ggml_tensor * mask = dst->src[3]; + ggml_tensor * KQV = dst; + + GGML_ASSERT(Q->type == GGML_TYPE_F32); + GGML_ASSERT(KQV->type == GGML_TYPE_F32); + + // --- Op params --- + float scale = 1.0f, max_bias = 0.0f, logit_softcap = 0.0f; + memcpy(&scale, (const float *)KQV->op_params + 0, sizeof(float)); + memcpy(&max_bias, (const float *)KQV->op_params + 1, sizeof(float)); + memcpy(&logit_softcap, (const float *)KQV->op_params + 2, sizeof(float)); + + const float q_scale = scale; + + // --- Dimensions --- + const int DKQ = (int)K->ne[0]; + const int DV = (int)V->ne[0]; + const int n_queries = (int)Q->ne[1]; + const int n_q_heads = (int)Q->ne[2]; + const int n_kv_heads = (int)K->ne[2]; + const int n_batch = (int)Q->ne[3]; + const int n_kv = (int)K->ne[1]; + const int gqa_ratio = n_q_heads / n_kv_heads; + const int n_query_rows = n_queries * gqa_ratio; + + GGML_ASSERT(n_q_heads % n_kv_heads == 0); + GGML_ASSERT(max_bias == 0.0f); // ALiBi not supported + GGML_ASSERT(Q->ne[3] == K->ne[3] || K->ne[3] == 1); + + const int chunk_size = std::min(MKL_FA_CHUNK_SIZE_KV, n_kv); + + // Query rows are processed in tiles of q_tile_rows so the score buffers + // (KQ_f32/S_f16 = q_tile_rows * chunk_size) stay bounded regardless of + // batch size. n_query_rows <= Q_TILE is a single tile (no extra work). + static int q_tile_env = ggml_sycl_get_env("GGML_SYCL_MKL_FA_Q_TILE", MKL_FA_Q_TILE); + const int q_tile_rows = std::max(1, std::min(q_tile_env, n_query_rows)); + + const int64_t wg_size = MKL_FA_WG_SIZE; + + // --- Debug output (gated by GGML_SYCL_MKL_FA_DEBUG=1) --- + static int mkl_call_count = 0; + mkl_call_count++; + static int mkl_debug = ggml_sycl_get_env("GGML_SYCL_MKL_FA_DEBUG", 0); + const bool do_print = (mkl_debug == 1); + + const int64_t q_row_stride = Q->nb[1] / sizeof(float); + const int64_t q_head_stride = Q->nb[2] / sizeof(float); + + const bool V_is_K_view = V->view_src + && (V->view_src == K || (V->view_src == K->view_src + && V->view_offs == K->view_offs)); + + // Early interleaved detection for debug output. + // True interleaved detection happens after dequant (nb12_fp16 == nb11_fp16), + // but we can pre-detect on the original tensor strides. + const bool k_early_interleaved = + ((int64_t)K->ne[1] * K->nb[1] != K->nb[2]); + const bool v_early_interleaved = + !V_is_K_view && ((int64_t)V->ne[1] * V->nb[1] != V->nb[2]); + + if (do_print) { + GGML_LOG_INFO("[MKL-FA] #%d D=%d DV=%d n_q=%d n_kv=%d " + "n_qh=%d n_kvh=%d gqa=%d batch=%d K=%s V=%s " + "chunk=%d buf=%.1fMB%s%s\n", + mkl_call_count, DKQ, DV, n_queries, n_kv, + n_q_heads, n_kv_heads, gqa_ratio, n_batch, + ggml_type_name(K->type), ggml_type_name(V->type), + chunk_size, + (double)((int64_t)n_query_rows * chunk_size * sizeof(float)) + / (1024.0 * 1024.0), + k_early_interleaved ? " K_ILV" : "", + v_early_interleaved ? " V_ILV" : ""); + GGML_LOG_INFO("[MKL-FA] #%d Q-nb1=%lld Q-nb2=%lld " + "q_rs=%lld q_hs=%lld dst_rs=%lld dst_hs=%lld\n", + mkl_call_count, + (long long)Q->nb[1], (long long)Q->nb[2], + (long long)q_row_stride, (long long)q_head_stride, + (long long)(KQV->nb[1] / sizeof(float)), + (long long)(KQV->nb[2] / sizeof(float))); + } + + // --- Stream and allocators --- + dpct::queue_ptr stream = ctx.stream(); + +#define MKL_TAKE_TIME(t0) auto t0 = std::chrono::steady_clock::now() +#define MKL_ACCUM(acc, t0) do { if (do_print) { \ + acc += (int64_t)std::chrono::duration_cast \ + (std::chrono::steady_clock::now() - (t0)).count(); \ +} } while(0) + + int64_t gemm_kq_time_us = 0; + int64_t gemm_vkq_time_us = 0; + int64_t softmax_time_us = 0; + int64_t dequant_time_us = 0; + + MKL_TAKE_TIME(t_deq); + + // --- K/V dequant descriptors --- + // Dequant is done per-chunk inside the KV loop (footprint independent of + // context). Output is always dense row-major fp16 [this_chunk x D], lda=D. + // Interleaved detection: ne[1]*nb[1] != nb[2] means heads are interleaved. + const bool k_interleaved = + ((int64_t)K->ne[1] * K->nb[1] != K->nb[2]) && K->ne[2] > 1; + const bool v_interleaved = + ((int64_t)V->ne[1] * V->nb[1] != V->nb[2]) && V->ne[2] > 1; + + const mkl_fa_kv_desc K_desc = mkl_fa_make_desc(K, k_interleaved, n_kv_heads); + const mkl_fa_kv_desc V_desc = V_is_K_view + ? K_desc : mkl_fa_make_desc(V, v_interleaved, n_kv_heads); + + MKL_ACCUM(dequant_time_us, t_deq); + + // --- Resolve mask pointers --- + const sycl::half * mask_data = nullptr; + int64_t mask_head_stride = 0; + int64_t mask_row_stride = 0; + int mask_n_heads = 0; + + if (mask) { + // Use actual fp16 device size (2 bytes), NOT sizeof(sycl::half) + // which may be 4 on the host in oneAPI. + mask_head_stride = mask->nb[2] / 2; + mask_row_stride = mask->nb[1] / 2; + mask_n_heads = (int)mask->ne[2]; + } + + // --- Allocate intermediates from pool --- + ggml_sycl_pool & pool = ctx.pool(); + + ggml_sycl_pool_alloc KQ_f32(pool); // [q_tile_rows x chunk] + ggml_sycl_pool_alloc S_f16(pool); // [q_tile_rows x chunk] + ggml_sycl_pool_alloc VKQ_chunk(pool); // [q_tile_rows x DV] + ggml_sycl_pool_alloc VKQ_accum(pool); // [n_query_rows x DV] (full) + ggml_sycl_pool_alloc KQ_max(pool); // [n_query_rows] (full) + ggml_sycl_pool_alloc KQ_sum(pool); // [n_query_rows] (full) + ggml_sycl_pool_alloc Q_head_f16(pool); // [n_query_rows x DKQ] (full) + ggml_sycl_pool_alloc K_chunk_f16(pool); // [chunk x DKQ] (per-chunk dequant) + ggml_sycl_pool_alloc V_chunk_f16(pool); // [chunk x DV] (per-chunk dequant) + + KQ_f32.alloc((size_t)q_tile_rows * chunk_size); + S_f16.alloc((size_t)q_tile_rows * chunk_size); + VKQ_chunk.alloc((size_t)q_tile_rows * DV); + VKQ_accum.alloc((size_t)n_query_rows * DV); + KQ_max.alloc(n_query_rows); + KQ_sum.alloc(n_query_rows); + Q_head_f16.alloc((size_t)n_query_rows * DKQ); + K_chunk_f16.alloc((size_t)chunk_size * DKQ); + + sycl::half * V_chunk_f16_ptr; + if (V_is_K_view) { + V_chunk_f16_ptr = K_chunk_f16.ptr; // V aliases K (DV == DKQ) + } else { + V_chunk_f16.alloc((size_t)chunk_size * DV); + V_chunk_f16_ptr = V_chunk_f16.ptr; + } + + sycl::half * Q_head_f16_ptr = Q_head_f16.ptr; + float * KQ_f32_ptr = KQ_f32.ptr; + sycl::half * S_f16_ptr = S_f16.ptr; + float * VKQ_chunk_ptr = VKQ_chunk.ptr; + float * VKQ_accum_ptr = VKQ_accum.ptr; + float * KQ_max_ptr = KQ_max.ptr; + float * KQ_sum_ptr = KQ_sum.ptr; + sycl::half * K_chunk_f16_ptr = K_chunk_f16.ptr; + + const float alpha = 1.0f; + const float beta = 0.0f; + + for (int ib = 0; ib < n_batch; ib++) { + const float * Q_batch = (const float *)Q->data + + ib * (Q->nb[3] / sizeof(float)); + float * dst_batch = (float *)KQV->data + + ib * (KQV->nb[3] / sizeof(float)); + + const sycl::half * mask_batch = nullptr; + if (mask) { + int m_batch = (mask->ne[3] > 1) ? ib : 0; + mask_batch = (const sycl::half *)mask->data + + m_batch * (mask->nb[3] / 2); // 2 = actual fp16 device size + } + + for (int ikvh = 0; ikvh < n_kv_heads; ikvh++) { + int kvh_base_head = ikvh * gqa_ratio; + + // 1. Pack all GQA Q heads into fp16 (full n_query_rows) + mkl_fa_pack_q_fp16(stream, + Q_head_f16_ptr, Q_batch, + n_queries, n_query_rows, DKQ, + gqa_ratio, kvh_base_head, + q_scale, q_row_stride, q_head_stride, wg_size); + + // 2. Initialize softmax state (full n_query_rows) + mkl_fa_init_softmax_state(stream, + KQ_max_ptr, KQ_sum_ptr, VKQ_accum_ptr, + n_query_rows, DV, wg_size); + + // Sync before MKL GEMM (MKL may use an internal queue) + stream->wait(); + + // 3. KV chunk loop (OUTER): dequant each chunk once, then tile queries. + for (int chunk_start = 0; chunk_start < n_kv; chunk_start += chunk_size) { + int this_chunk = std::min(chunk_size, n_kv - chunk_start); + + // 3a. Dequant this KV chunk to dense fp16 (once per chunk) + { + MKL_TAKE_TIME(t0); + mkl_fa_dequant_chunk(stream, K_desc, KQV, + K_chunk_f16_ptr, ikvh, chunk_start, this_chunk); + if (!V_is_K_view) { + mkl_fa_dequant_chunk(stream, V_desc, KQV, + V_chunk_f16_ptr, ikvh, chunk_start, this_chunk); + } + stream->wait(); // dequant must be ready before MKL GEMM + MKL_ACCUM(dequant_time_us, t0); + } + + // 3b. Query tile loop (INNER) — bounds KQ_f32/S_f16 footprint. + for (int q0 = 0; q0 < n_query_rows; q0 += q_tile_rows) { + int q_rows = std::min(q_tile_rows, n_query_rows - q0); + + // GEMM: KQ = Q_tile × K_chunk^T + { + MKL_TAKE_TIME(t0); + sycl::event ev = gemm(*stream, + transpose::trans, transpose::nontrans, + this_chunk, q_rows, DKQ, + alpha, + K_chunk_f16_ptr, DKQ, + Q_head_f16_ptr + (int64_t)q0 * DKQ, DKQ, + beta, + KQ_f32_ptr, this_chunk); + try { ev.wait_and_throw(); } catch (sycl::exception & e) { + GGML_LOG_INFO("[MKL-FA] GEMM KQ: %s\n", e.what()); + GGML_ABORT("MKL GEMM KQ failed"); + } + MKL_ACCUM(gemm_kq_time_us, t0); + } + // Online softmax over this chunk for this query tile + { + MKL_TAKE_TIME(t0); + mkl_fa_online_softmax_chunk(stream, + KQ_f32_ptr, S_f16_ptr, + KQ_max_ptr, KQ_sum_ptr, VKQ_accum_ptr, + q0, q_rows, n_queries, DV, + this_chunk, chunk_start, + kvh_base_head, gqa_ratio, + mask_batch, mask_head_stride, + mask_row_stride, mask_n_heads, + logit_softcap, wg_size); + stream->wait(); // S_f16 must be ready for GEMM + MKL_ACCUM(softmax_time_us, t0); + } + + // GEMM: VKQ_chunk = S × V_chunk + { + MKL_TAKE_TIME(t0); + sycl::event ev = gemm(*stream, + transpose::nontrans, transpose::nontrans, + DV, q_rows, this_chunk, + alpha, + V_chunk_f16_ptr, DV, + S_f16_ptr, this_chunk, + beta, + VKQ_chunk_ptr, DV); + try { ev.wait_and_throw(); } catch (sycl::exception & e) { + GGML_LOG_INFO("[MKL-FA] GEMM VKQ: %s\n", e.what()); + GGML_ABORT("MKL GEMM VKQ failed"); + } + MKL_ACCUM(gemm_vkq_time_us, t0); + } + // VKQ_accum[q0..] += VKQ_chunk + { + const int64_t n_total = (int64_t)q_rows * DV; + const int64_t wg = ((n_total + wg_size - 1) / wg_size) + * wg_size; + float * accum = VKQ_accum_ptr + (int64_t)q0 * DV; + stream->submit([&](sycl::handler & cgh) { + cgh.parallel_for(sycl::nd_range<1>(wg, wg_size), + [=](sycl::nd_item<1> item) { + int64_t i = item.get_global_id(0); + if (i < n_total) { + accum[i] += VKQ_chunk_ptr[i]; + } + }); + }); + } + } + } + + // 4. Normalize and scatter each GQA head to dst + for (int iqg = 0; iqg < gqa_ratio; iqg++) { + int iqh = kvh_base_head + iqg; + int64_t src_offset = (int64_t)iqg * n_queries * DV; + mkl_fa_normalize_head(stream, + dst_batch, VKQ_accum_ptr, KQ_sum_ptr, + iqh, n_queries, DV, n_q_heads, + src_offset, wg_size); + } + } + } + +#undef MKL_TAKE_TIME +#undef MKL_ACCUM + + if (do_print) { + const int64_t v_chunk_elems = V_is_K_view ? 0 : (int64_t)chunk_size * DV; + double total_mb = (double)( + (int64_t)q_tile_rows * chunk_size * sizeof(float) // KQ_f32 + + (int64_t)q_tile_rows * chunk_size * sizeof(sycl::half) // S_f16 + + (int64_t)q_tile_rows * DV * sizeof(float) // VKQ_chunk + + (int64_t)n_query_rows * DV * sizeof(float) // VKQ_accum + + (int64_t)n_query_rows * sizeof(float) // KQ_max + + (int64_t)n_query_rows * sizeof(float) // KQ_sum + + (int64_t)n_query_rows * DKQ * sizeof(sycl::half) // Q_head_f16 + + (int64_t)chunk_size * DKQ * sizeof(sycl::half) // K_chunk_f16 + + v_chunk_elems * (int64_t)sizeof(sycl::half) // V_chunk_f16 + ) / (1024.0 * 1024.0); + GGML_LOG_INFO("[MKL-FA] #%d n_kv=%d n_q=%d q_tile=%d time_us: " + "dequant=%lld GEMM_KQ=%lld softmax=%lld GEMM_VKQ=%lld " + "buf_mb=%.1f\n", + mkl_call_count, n_kv, n_queries, q_tile_rows, + (long long)dequant_time_us, + (long long)gemm_kq_time_us, + (long long)softmax_time_us, + (long long)gemm_vkq_time_us, + total_mb); + } +} diff --git a/ggml/src/ggml-sycl/fattn-onednn.cpp b/ggml/src/ggml-sycl/fattn-onednn.cpp index 8465e12248f4..fd17a25d5edd 100644 --- a/ggml/src/ggml-sycl/fattn-onednn.cpp +++ b/ggml/src/ggml-sycl/fattn-onednn.cpp @@ -2,11 +2,13 @@ #include #include #include +#include #include #include #include "fattn-onednn.hpp" #include "fattn-tile.hpp" +#include "convert.hpp" // set minimum query length to treat as prefill (32) #define GGML_SYCL_FA_ONEDNN_MIN_Q 32 @@ -33,10 +35,30 @@ bool ggml_sycl_flash_attn_ext_onednn_supported(const ggml_tensor * dst) { const ggml_tensor * mask = dst->src[3]; const ggml_tensor * sinks = dst->src[4]; - // gate for f16 KV only for now - // need to implement quantized KV + // F16 KV: native SDPA at any KV length. + // Non-F16: dequant to F16 then SDPA at prefill lengths. Only the + // standard quantized KV cache types (Q4_0-Q8_0) and F32 are accepted + // because their to_fp16_sycl conversion is verified. BF16 and IQ* + // are excluded: BF16 needs a strided conversion kernel that does not + // exist yet; IQ types are model-weight-only quants with no dequant + // registration and are never used as KV caches. if (K->type != GGML_TYPE_F16 || V->type != GGML_TYPE_F16) { - return false; + auto kt = K->type, vt = V->type; + bool k_ok = kt == GGML_TYPE_F32 || kt == GGML_TYPE_Q4_0 || kt == GGML_TYPE_Q4_1 || + kt == GGML_TYPE_Q5_0 || kt == GGML_TYPE_Q5_1 || kt == GGML_TYPE_Q8_0; + bool v_ok = vt == GGML_TYPE_F32 || vt == GGML_TYPE_Q4_0 || vt == GGML_TYPE_Q4_1 || + vt == GGML_TYPE_Q5_0 || vt == GGML_TYPE_Q5_1 || vt == GGML_TYPE_Q8_0; + if (!k_ok || !v_ok) { + return false; + } + if (Q->ne[1] < 32 || K->ne[1] < 1024) { + return false; + } + for (const ggml_tensor * t : {K, V}) { + if (t->type == GGML_TYPE_F16 && t->nb[1] % (t->ne[0] * 2) != 0) { + return false; + } + } } // Optional KV-length ceiling (GGML_SYCL_FA_ONEDNN_MAX_KV, 0 = unlimited). Escape hatch: // very long sequences make the fused SDPA slow enough to risk the xe driver watchdog on @@ -205,13 +227,101 @@ void ggml_sycl_flash_attn_ext_onednn(ggml_backend_sycl_context & ctx, ggml_tenso dnnl::engine eng = ctx.engine_dnnl(stream); dnnl::stream strm = ctx.stream_dnnl(stream); - // cont/cast inputs to contiguous f16 (head-major) -- the layout the fast systolic path wants. - ggml_sycl_pool_alloc Qf(ctx.pool(), (size_t) H * q * d); - ggml_sycl_pool_alloc Kf(ctx.pool(), (size_t) Hkv * seq * d); - ggml_sycl_pool_alloc Vf(ctx.pool(), (size_t) Hkv * seq * d); - cont_to_f16_sycl ((const char *) Q->data, Qf.get(), d, q, H, mb, Q->nb[1], Q->nb[2], Q->nb[3], stream); - cont_to_f16_sycl((const char *) K->data, Kf.get(), d, seq, Hkv, mb, K->nb[1], K->nb[2], K->nb[3], stream); - cont_to_f16_sycl((const char *) V->data, Vf.get(), d, seq, Hkv, mb, V->nb[1], V->nb[2], V->nb[3], stream); + // Q: always f32 -- copy to dense f16. + ggml_sycl_pool_alloc Qf(ctx.pool(), (size_t) H * q * d); + cont_to_f16_sycl((const char *) Q->data, Qf.get(), d, q, H, mb, Q->nb[1], Q->nb[2], Q->nb[3], stream); + + // K/V: use pool-alloc for both F16 and dequant paths. + sycl::half * K_ptr = nullptr; + sycl::half * V_ptr = nullptr; + std::optional> Kf_pool; + std::optional> Vf_pool; + + if (K->type == GGML_TYPE_F16 && V->type == GGML_TYPE_F16) { + Kf_pool.emplace(ctx.pool(), (size_t) Hkv * seq * d); + Vf_pool.emplace(ctx.pool(), (size_t) Hkv * seq * d); + cont_to_f16_sycl((const char *) K->data, Kf_pool->get(), d, seq, Hkv, mb, K->nb[1], K->nb[2], K->nb[3], stream); + cont_to_f16_sycl((const char *) V->data, Vf_pool->get(), d, seq, Hkv, mb, V->nb[1], V->nb[2], V->nb[3], stream); + K_ptr = Kf_pool->get(); + V_ptr = Vf_pool->get(); + } else if (ggml_is_quantized(K->type)) { + // Quantized K/V: dequant to dense F16 using pool, same lifetime as F16 path. + Kf_pool.emplace(ctx.pool(), ggml_nelements(K)); + K_ptr = Kf_pool->get(); + { + const char * K_data = (const char *)K->data; + const bool k_non_dense = ((int64_t)K->ne[1] * K->nb[1] != K->nb[2]) && K->ne[2] > 1; + const bool k_gemma = k_non_dense && + ((int64_t)K->nb[2] < (int64_t)K->ne[1] * (int64_t)K->nb[1]); + if (ggml_is_contiguously_allocated(K) && !k_non_dense) { + to_fp16_sycl_t to_fp16 = ggml_get_to_fp16_sycl(K->type, dst); + to_fp16(K_data, K_ptr, ggml_nelements(K), stream); + } else { + const size_t bs = ggml_blck_size(K->type); + const size_t ts = ggml_type_size(K->type); + to_fp16_nc_sycl_t to_fp16 = ggml_get_to_fp16_nc_sycl(K->type); + int64_t s01, s02, s03; + if (k_gemma) { + const int64_t blk_per_row = (int64_t)K->ne[0] / bs; + s01 = (int64_t)Hkv * blk_per_row; + s02 = blk_per_row; + s03 = (int64_t)K->ne[1] * s01; + } else { + s01 = (int64_t)K->nb[1] / ts; + s02 = (int64_t)K->nb[2] / ts; + s03 = (int64_t)K->nb[3] / ts; + } + to_fp16(K_data, K_ptr, + K->ne[0], K->ne[1], K->ne[2], K->ne[3], + s01, s02, s03, stream); + } + } + // Quantized V: always dequant separately. Even when K and V share + // the same underlying allocation (V is a view of K with the same + // data pointer), their logical values differ because the quantized + // elements at different positions/offsets represent different K/V + // data. Master's F16 path also never aliases K and V. + Vf_pool.emplace(ctx.pool(), ggml_nelements(V)); + V_ptr = Vf_pool->get(); + { + const char * V_data = (const char *)V->data; + const bool v_non_dense = ((int64_t)V->ne[1] * V->nb[1] != V->nb[2]) && V->ne[2] > 1; + const bool v_gemma = v_non_dense && + ((int64_t)V->nb[2] < (int64_t)V->ne[1] * (int64_t)V->nb[1]); + if (ggml_is_contiguously_allocated(V) && !v_non_dense) { + to_fp16_sycl_t to_fp16 = ggml_get_to_fp16_sycl(V->type, dst); + to_fp16(V_data, V_ptr, ggml_nelements(V), stream); + } else { + const size_t bs = ggml_blck_size(V->type); + const size_t ts = ggml_type_size(V->type); + to_fp16_nc_sycl_t to_fp16 = ggml_get_to_fp16_nc_sycl(V->type); + int64_t s01, s02, s03; + if (v_gemma) { + const int64_t blk_per_row = (int64_t)V->ne[0] / bs; + s01 = (int64_t)V->ne[2] * blk_per_row; + s02 = blk_per_row; + s03 = (int64_t)V->ne[1] * s01; + } else { + s01 = (int64_t)V->nb[1] / ts; + s02 = (int64_t)V->nb[2] / ts; + s03 = (int64_t)V->nb[3] / ts; + } + to_fp16(V_data, V_ptr, + V->ne[0], V->ne[1], V->ne[2], V->ne[3], + s01, s02, s03, stream); + } + } + } else { + // F32: strided copy to dense F16 via cont_to_f16_sycl. + Kf_pool.emplace(ctx.pool(), ggml_nelements(K)); + K_ptr = Kf_pool->get(); + cont_to_f16_sycl((const char *) K->data, K_ptr, K->ne[0], K->ne[1], K->ne[2], K->ne[3], + K->nb[1], K->nb[2], K->nb[3], stream); + Vf_pool.emplace(ctx.pool(), ggml_nelements(V)); + V_ptr = Vf_pool->get(); + cont_to_f16_sycl((const char *) V->data, V_ptr, V->ne[0], V->ne[1], V->ne[2], V->ne[3], + V->nb[1], V->nb[2], V->nb[3], stream); + } // divide-by-(1/scale) reproduces ggml's score *= kq_scale on the proven probe graph. // @@ -244,8 +354,8 @@ void ggml_sycl_flash_attn_ext_onednn(ggml_backend_sycl_context & ctx, ggml_tenso auto id2ptr = [&](size_t r) -> void * { if (r == E.id_q) return Qf.get(); - if (r == E.id_k) return Kf.get(); - if (r == E.id_v) return Vf.get(); + if (r == E.id_k) return K_ptr; + if (r == E.id_v) return V_ptr; if (r == E.id_scale) return scale_dev; if (r == E.id_mask) return (void *) mask->data; return nullptr; diff --git a/ggml/src/ggml-sycl/fattn.cpp b/ggml/src/ggml-sycl/fattn.cpp index 1772b9c8584d..a85eb721f6af 100644 --- a/ggml/src/ggml-sycl/fattn.cpp +++ b/ggml/src/ggml-sycl/fattn.cpp @@ -97,10 +97,12 @@ static void ggml_sycl_flash_attn_ext_vec(ggml_backend_sycl_context & ctx, ggml_t enum best_fattn_kernel { BEST_FATTN_KERNEL_NONE = 0, BEST_FATTN_KERNEL_VEC = 100, - BEST_FATTN_KERNEL_ONEDNN = 150, // added enum for onednn==150 + BEST_FATTN_KERNEL_ONEDNN = 150, // oneDNN SDPA: native F16 (PR #25222) BEST_FATTN_KERNEL_TILE = 200, + BEST_FATTN_KERNEL_MKL = 300, }; + static best_fattn_kernel ggml_sycl_get_best_fattn_kernel(const int device, const ggml_tensor * dst) { GGML_UNUSED(device); #ifndef SYCL_FLASH_ATTN @@ -115,6 +117,7 @@ static best_fattn_kernel ggml_sycl_get_best_fattn_kernel(const int device, const const ggml_tensor * K = dst->src[1]; const ggml_tensor * V = dst->src[2]; const ggml_tensor * mask = dst->src[3]; + const ggml_tensor * sinks = dst->src[4]; const int gqa_ratio = Q->ne[2] / K->ne[2]; GGML_ASSERT(Q->ne[2] % K->ne[2] == 0); @@ -122,7 +125,56 @@ static best_fattn_kernel ggml_sycl_get_best_fattn_kernel(const int device, const float max_bias = 0.0f; memcpy(&max_bias, (const float *) KQV->op_params + 1, sizeof(float)); + float logit_softcap = 0.0f; + memcpy(&logit_softcap, (const float *) KQV->op_params + 2, sizeof(float)); + bool gqa_opt_applies = gqa_ratio >= 2 && mask && max_bias == 0.0f && K->ne[1] % FATTN_KQ_STRIDE == 0; + + // XMX-accelerated path: oneDNN SDPA (native F16 and dequant+non-F16). + // ONEDNN requires min 32 query tokens — short-circuit decode to avoid + // calling _supported() on every decode FA call. + if (Q->ne[1] >= 32 + && ggml_sycl_flash_attn_ext_onednn_supported(dst)) { + return BEST_FATTN_KERNEL_ONEDNN; + } + + // MKL path: XMX-accelerated GEMM for prompt processing (all KV cache types). + // The MKL kernel converts non-F16 K/V to F16 via to_fp16_sycl before GEMM, + // so quantized, F16, BF16, and F32 caches all benefit from XMX acceleration. + // Activates automatically when flash-attn is enabled (--flash-attn on or -fa) + // and n_kv >= 1024. Falls through to TILE/VEC for ALiBi, logit softcap, + // and mismatched batch dimensions (unsupported by the MKL kernel). + // Set GGML_SYCL_ENABLE_MKL_FA=0 to force TILE/VEC path for A/B testing. + // Example: GGML_SYCL_ENABLE_MKL_FA=0 llama-cli -m model.gguf -fa -ngl 99 ... + // Note: MKL GEMM calls are incompatible with SYCL graph capture replay. + static int mkl_enable = ggml_sycl_get_env("GGML_SYCL_ENABLE_MKL_FA", 1); + // MKL is validated for the mainstream GQA envelope: grouped-query + // (gqa_ratio >= 2), head_dim a multiple of 64 in [64,512] with matching + // K/V head size, mask, no sinks/ALiBi/softcap. Gemma's global layers use + // head_dim 512, so the cap must include it. Head sizes not a multiple of + // 64 (72/80/96), MHA (gqa_ratio == 1), and MLA (DKQ != DV, e.g. 576/512) + // fall through to TILE/VEC; see follow-up work. + if (mkl_enable == 1 && mask && !sinks && gqa_ratio >= 2 && + Q->ne[0] >= 64 && Q->ne[0] <= 512 && Q->ne[0] % 64 == 0 && + Q->ne[0] == V->ne[0] && + Q->ne[1] >= 32 && K->ne[1] >= 1024 && + max_bias == 0.0f && logit_softcap == 0.0f && + (Q->ne[3] == K->ne[3] || K->ne[3] == 1)) { + // F16 K/V strides must be a multiple of ne[0]*2 (the natural row size + // in bytes). This passes both dense (nb1 == ne0*2) and interleaved + // (nb1 == H * ne0*2). Only pathological test strides like nb1=32 or + // nb1=75 for ne0=40 fall through to TILE. + bool kv_strides_ok = true; + for (const ggml_tensor * t : {K, V}) { + if (t->type == GGML_TYPE_F16 && t->nb[1] % (t->ne[0] * 2) != 0) { + kv_strides_ok = false; + break; + } + } + if (kv_strides_ok) { + return BEST_FATTN_KERNEL_MKL; + } + } for (const ggml_tensor * t : {Q, K, V, mask}) { if (t == nullptr || ggml_is_quantized(t->type)) { continue; @@ -170,6 +222,7 @@ static best_fattn_kernel ggml_sycl_get_best_fattn_kernel(const int device, const switch (K->type) { case GGML_TYPE_F32: case GGML_TYPE_F16: + case GGML_TYPE_BF16: break; case GGML_TYPE_Q4_1: case GGML_TYPE_Q5_0: @@ -188,8 +241,11 @@ static best_fattn_kernel ggml_sycl_get_best_fattn_kernel(const int device, const return BEST_FATTN_KERNEL_NONE; } - // For small batch sizes the vector kernel may be preferable over the kernels optimized for large batch sizes: - const bool can_use_vector_kernel = Q->ne[0] <= 512 && Q->ne[0] % 64 == 0 && K->ne[1] % FATTN_KQ_STRIDE == 0; + // For small batch sizes the vector kernel may be preferable over the kernels optimized for large batch sizes. + // BF16 is excluded: the VEC kernel has no BF16 template (it needs GGML_SYCL_FA_ALL_QUANTS for non-F16/Q4_0/Q8_0). + const bool has_bf16 = (K->type == GGML_TYPE_BF16 || V->type == GGML_TYPE_BF16); + const bool can_use_vector_kernel = Q->ne[0] <= 512 && Q->ne[0] % 64 == 0 && K->ne[1] % FATTN_KQ_STRIDE == 0 + && !has_bf16; // Fused-XMX path: oneDNN Graph SDPA (flash attention). Strictly // additive -- taken only when statically supported, otherwise falls through to VEC/TILE below. @@ -216,7 +272,40 @@ static best_fattn_kernel ggml_sycl_get_best_fattn_kernel(const int device, const void ggml_sycl_flash_attn_ext(ggml_backend_sycl_context & ctx, ggml_tensor * dst) { ggml_sycl_set_device(ctx.device); - switch (ggml_sycl_get_best_fattn_kernel(ggml_sycl_get_device(), dst)) { + + // n_kv watchdog: log when n_kv differs from the last FA call with + // the same D — helps detect cache-truncation issues. + static int nkv_debug = ggml_sycl_get_env("GGML_SYCL_MKL_FA_DEBUG", 0); + if (nkv_debug == 1) { + const ggml_tensor * K_dbg = dst->src[1]; + const ggml_tensor * V_dbg = dst->src[2]; + static int64_t last_nkv_d256 = 0, last_nkv_d512 = 0; + static int fa_call_seq = 0; + fa_call_seq++; + int64_t cur_nkv = K_dbg->ne[1]; + int Dk = (int)K_dbg->ne[0]; + const char * kname = "TILE"; + best_fattn_kernel k = ggml_sycl_get_best_fattn_kernel(ctx.device, dst); + if (k == BEST_FATTN_KERNEL_MKL) kname = "MKL"; + if (k == BEST_FATTN_KERNEL_ONEDNN) kname = "ONEDNN"; + if (k == BEST_FATTN_KERNEL_VEC) kname = "VEC"; + int64_t delta = 0; + if (Dk == 256) { + delta = cur_nkv - last_nkv_d256; + last_nkv_d256 = cur_nkv; + } else if (Dk == 512) { + delta = cur_nkv - last_nkv_d512; + last_nkv_d512 = cur_nkv; + } + GGML_LOG_INFO("[FA-DISP] #%d %s D=%d n_kv=%lld delta=%lld " + "V_ne1=%lld\n", + fa_call_seq, kname, Dk, + (long long)cur_nkv, (long long)delta, + (long long)V_dbg->ne[1]); + } + + const best_fattn_kernel fk = ggml_sycl_get_best_fattn_kernel(ggml_sycl_get_device(), dst); + switch (fk) { case BEST_FATTN_KERNEL_NONE: GGML_ABORT("Not support Flash-Attention"); case BEST_FATTN_KERNEL_ONEDNN: @@ -232,7 +321,54 @@ void ggml_sycl_flash_attn_ext(ggml_backend_sycl_context & ctx, ggml_tensor * dst case BEST_FATTN_KERNEL_VEC: ggml_sycl_flash_attn_ext_vec(ctx, dst); break; + case BEST_FATTN_KERNEL_MKL: + ggml_sycl_flash_attn_ext_mkl(ctx, dst); + break; } + + // --- Output fingerprint (GGML_SYCL_MKL_FA_DIAG=1) --- + // Copy first 64 float output values to host for fingerprinting. + // Compare MKL vs TILE (GGML_SYCL_ENABLE_MKL_FA=0) to detect divergence. + // Only fingerprints the first 6 FA calls with n_kv >= 1024. + static int fa_diag = ggml_sycl_get_env("GGML_SYCL_MKL_FA_DIAG", 0); + static int fa_diag_count = 0; + if (fa_diag == 1 && fa_diag_count < 6) { + const ggml_tensor * K_diag = dst->src[1]; + const ggml_tensor * V_diag = dst->src[2]; + const ggml_tensor * Q_diag = dst->src[0]; + if (K_diag->ne[1] >= 1024) { + fa_diag_count++; + float diag_buf[64]; + dpct::queue_ptr q = ctx.stream(); + q->memcpy(diag_buf, dst->data, 64 * sizeof(float)); + q->wait(); + const char * kname = "???"; + best_fattn_kernel kb = ggml_sycl_get_best_fattn_kernel(ctx.device, dst); + if (kb == BEST_FATTN_KERNEL_ONEDNN) kname = "ONEDNN"; + if (kb == BEST_FATTN_KERNEL_MKL) kname = "MKL"; + if (kb == BEST_FATTN_KERNEL_TILE) kname = "TILE"; + if (kb == BEST_FATTN_KERNEL_VEC) kname = "VEC"; + GGML_LOG_INFO("[FA-DIAG] #%d %s D=%d n_kv=%lld n_q=%lld " + "n_qh=%lld n_kvh=%lld K=%s V=%s " + "nb1=%zu nb2=%zu first 64 floats:\n", + fa_diag_count, kname, + (int)K_diag->ne[0], (long long)K_diag->ne[1], + (long long)Q_diag->ne[1], + (long long)Q_diag->ne[2], (long long)K_diag->ne[2], + ggml_type_name(K_diag->type), + ggml_type_name(V_diag->type), + K_diag->nb[1], K_diag->nb[2]); + for (int i = 0; i < 64; i += 8) { + GGML_LOG_INFO(" [%2d] %08x %08x %08x %08x %08x %08x %08x %08x\n", + i, + *(unsigned *)&diag_buf[i+0], *(unsigned *)&diag_buf[i+1], + *(unsigned *)&diag_buf[i+2], *(unsigned *)&diag_buf[i+3], + *(unsigned *)&diag_buf[i+4], *(unsigned *)&diag_buf[i+5], + *(unsigned *)&diag_buf[i+6], *(unsigned *)&diag_buf[i+7]); + } + } + } + } bool ggml_sycl_flash_attn_ext_supported(int device, const ggml_tensor * dst) { diff --git a/ggml/src/ggml-sycl/fattn.hpp b/ggml/src/ggml-sycl/fattn.hpp index f2a8ffc97dee..c093970a3fed 100644 --- a/ggml/src/ggml-sycl/fattn.hpp +++ b/ggml/src/ggml-sycl/fattn.hpp @@ -19,4 +19,6 @@ void ggml_sycl_flash_attn_ext(ggml_backend_sycl_context & ctx, ggml_tensor * dst bool ggml_sycl_flash_attn_ext_supported(int device, const ggml_tensor * dst); +void ggml_sycl_flash_attn_ext_mkl(ggml_backend_sycl_context & ctx, ggml_tensor * dst); + #endif // GGML_SYCL_FATTN_HPP diff --git a/ggml/src/ggml-sycl/ggml-sycl.cpp b/ggml/src/ggml-sycl/ggml-sycl.cpp index 07ddfda88764..d91e41f9575a 100644 --- a/ggml/src/ggml-sycl/ggml-sycl.cpp +++ b/ggml/src/ggml-sycl/ggml-sycl.cpp @@ -167,7 +167,10 @@ static ggml_sycl_device_info ggml_sycl_init() { ze_device_properties_t props = {}; props.stype = ZE_STRUCTURE_TYPE_DEVICE_PROPERTIES; ze_result_t r = zeDeviceGetProperties(ze_dev, &props); - info.devices[i].l0_discrete_gpu = r == ZE_RESULT_SUCCESS && !(props.flags & ZE_DEVICE_PROPERTY_FLAG_INTEGRATED); + if (r == ZE_RESULT_SUCCESS) { + info.devices[i].l0_device_type_valid = true; + info.devices[i].l0_discrete_gpu = !(props.flags & ZE_DEVICE_PROPERTY_FLAG_INTEGRATED); + } } #endif } @@ -5606,7 +5609,11 @@ static void ggml_backend_sycl_device_get_memory(ggml_backend_dev_t dev, size_t * } static enum ggml_backend_dev_type ggml_backend_sycl_device_get_type(ggml_backend_dev_t dev) { - GGML_UNUSED(dev); + ggml_backend_sycl_device_context * ctx = (ggml_backend_sycl_device_context *)dev->context; + const sycl_device_info & info = ggml_sycl_info().devices[ctx->device]; + if (info.l0_device_type_valid && !info.l0_discrete_gpu) { + return GGML_BACKEND_DEVICE_TYPE_IGPU; + } return GGML_BACKEND_DEVICE_TYPE_GPU; } diff --git a/ggml/src/ggml-vulkan/ggml-vulkan.cpp b/ggml/src/ggml-vulkan/ggml-vulkan.cpp index e32dd7a56a2f..2418ba6d1786 100644 --- a/ggml/src/ggml-vulkan/ggml-vulkan.cpp +++ b/ggml/src/ggml-vulkan/ggml-vulkan.cpp @@ -610,6 +610,13 @@ static constexpr std::initializer_list topk_moe_sigmoid_norm_bias{ GGML GGML_OP_RESHAPE, GGML_OP_SUM_ROWS, GGML_OP_CLAMP, GGML_OP_DIV, GGML_OP_RESHAPE }; +static constexpr std::initializer_list topk_moe_sqrt_softplus_norm_bias{ GGML_OP_UNARY, GGML_OP_SQRT, + GGML_OP_RESHAPE, GGML_OP_ADD, + GGML_OP_ARGSORT, GGML_OP_VIEW, + GGML_OP_GET_ROWS, GGML_OP_RESHAPE, + GGML_OP_SUM_ROWS, GGML_OP_CLAMP, + GGML_OP_DIV, GGML_OP_RESHAPE }; + static constexpr std::initializer_list topk_moe_early_softmax { GGML_OP_SOFT_MAX, GGML_OP_RESHAPE, GGML_OP_ARGSORT, GGML_OP_VIEW, GGML_OP_GET_ROWS }; @@ -673,6 +680,22 @@ static constexpr std::initializer_list> topk_moe_sigmoid_norm {10, 0, 9 }, // reshape->src[0] == div }; +static constexpr std::initializer_list> topk_moe_sqrt_softplus_norm_bias_edges { + { 1, 0, 0 }, // sqrt->src[0] == softplus + { 2, 0, 1 }, // reshape->src[0] == sqrt + { 3, 0, 1 }, // add->src[0] == sqrt + { 4, 0, 3 }, // argsort->src[0] == add + { 5, 0, 4 }, // view->src[0] == argsort + { 6, 0, 2 }, // get_rows->src[0] == reshape + { 6, 1, 5 }, // get_rows->src[1] == view + { 7, 0, 6 }, // reshape->src[0] == get_rows + { 8, 0, 7 }, // sum_rows->src[0] == reshape + { 9, 0, 8 }, // clamp->src[0] == sum_rows + {10, 0, 7 }, // div->src[0] == reshape + {10, 1, 9 }, // div->src[1] == clamp + {11, 0,10 }, // reshape->src[0] == div +}; + // same as early_softmax_norm but ending after the get_rows static constexpr std::initializer_list> topk_moe_early_softmax_edges { { 1, 0, 0 }, // reshape->src[0] == softmax @@ -701,6 +724,7 @@ enum topk_moe_mode { TOPK_MOE_EARLY_SOFTMAX_NORM, TOPK_MOE_LATE_SOFTMAX, TOPK_MOE_SIGMOID_NORM_BIAS, + TOPK_MOE_SQRT_SOFTPLUS_NORM_BIAS, TOPK_MOE_COUNT, }; @@ -998,9 +1022,11 @@ struct vk_device_struct { vk_pipeline pipeline_snake_f32; vk_pipeline pipeline_snake_f16; vk_pipeline pipeline_snake_bf16; + vk_pipeline pipeline_pool1d_f32; vk_pipeline pipeline_pool2d_f32; vk_pipeline pipeline_rwkv_wkv6_f32; vk_pipeline pipeline_rwkv_wkv7_f32; + vk_pipeline pipeline_gated_linear_attn_f32; // [size_idx][kda] where size_idx: 0=d16, 1=d32, 2=d64, 3=d128 vk_pipeline pipeline_gated_delta_net[4][2]; vk_pipeline pipeline_ssm_scan_f32_d128; @@ -1687,6 +1713,17 @@ struct vk_op_snake_push_constants { uint32_t ne1; }; +struct vk_op_pool1d_push_constants { + uint32_t IL; + uint32_t OL; + uint32_t OC; + uint32_t pelements; + uint32_t op; + int32_t k0; + int32_t s0; + int32_t p0; +}; + struct vk_op_pool2d_push_constants { uint32_t IW; uint32_t IH; uint32_t OW; uint32_t OH; @@ -1711,6 +1748,13 @@ struct vk_op_rwkv_wkv7_push_constants { uint32_t C; uint32_t H; }; +struct vk_op_gated_linear_attn_push_constants { + uint32_t B; + uint32_t T; + uint32_t C; + uint32_t H; + float scale; +}; struct vk_op_gated_delta_net_push_constants { uint32_t H; uint32_t n_tokens; @@ -1934,6 +1978,7 @@ struct ggml_vk_garbage_collector { static void ggml_vk_preallocate_buffers(ggml_backend_vk_context * ctx, vk_context subctx); static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested = nullptr); static void ggml_pipeline_allocate_descriptor_sets(ggml_backend_vk_context * ctx); +static bool ggml_vk_intel_windows_driver_equals_or_newer_than(uint32_t driver_version, uint32_t threshold_major, uint32_t threshold_minor); static bool vk_memory_logger_enabled = false; @@ -5552,8 +5597,11 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) { ggml_vk_create_pipeline(device, device->pipeline_argmax_f32, "argmax_f32", argmax_f32_len, argmax_f32_data, "main", 2, sizeof(vk_op_push_constants), {1, 1, 1}, { device->subgroup_size }, 1); ggml_vk_create_pipeline(device, device->pipeline_sum_rows_f32, "sum_rows_f32", sum_rows_f32_len, sum_rows_f32_data, "main", 2, sizeof(vk_op_sum_rows_push_constants), {1, 1, 1}, { device->subgroup_size }, 1); - // Intel Arc B390 was observed segfaulting with this shader. - if (device->subgroup_basic && device->subgroup_shuffle && device->vendor_id != VK_VENDOR_ID_INTEL) { + // Intel Windows driver older than 32.0.101.8860 will crash when using fwht kernels on Xe2+ GPUS so we gate that here + const bool can_use_fwht = device->driver_id != vk::DriverId::eIntelProprietaryWindows || + device->architecture != vk_device_architecture::INTEL_XE2 || + (device->architecture == vk_device_architecture::INTEL_XE2 && ggml_vk_intel_windows_driver_equals_or_newer_than(device->properties.driverVersion, 101, 8860)); + if (can_use_fwht && device->subgroup_basic && device->subgroup_shuffle) { int idx = 0; for (uint32_t n : {64, 128, 256, 512}) { if (device->subgroup_size <= n) { @@ -5561,8 +5609,7 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) { } ++idx; } - } else if (device->driver_id != vk::DriverId::eIntelProprietaryWindows) { - // Disabled on Intel Windows due to a driver bug: https://github.com/ggml-org/llama.cpp/pull/23964#issuecomment-4598226147 + } else if (can_use_fwht) { int idx = 0; for (uint32_t n : {64, 128, 256, 512}) { const uint32_t block_size = std::min(device->subgroup_size, n); @@ -5619,12 +5666,15 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) { ggml_vk_create_pipeline(device, device->pipeline_snake_f16, "snake_f16", snake_f16_len, snake_f16_data, "main", 4, sizeof(vk_op_snake_push_constants), {256, 1, 1}, {}, 1); ggml_vk_create_pipeline(device, device->pipeline_snake_bf16, "snake_bf16", snake_bf16_len, snake_bf16_data, "main", 4, sizeof(vk_op_snake_push_constants), {256, 1, 1}, {}, 1); + ggml_vk_create_pipeline(device, device->pipeline_pool1d_f32, "pool1d_f32", pool1d_f32_len, pool1d_f32_data, "main", 2, sizeof(vk_op_pool1d_push_constants), {512, 1, 1}, {}, 1); ggml_vk_create_pipeline(device, device->pipeline_pool2d_f32, "pool2d_f32", pool2d_f32_len, pool2d_f32_data, "main", 2, sizeof(vk_op_pool2d_push_constants), {512, 1, 1}, {}, 1); ggml_vk_create_pipeline(device, device->pipeline_rwkv_wkv6_f32, "rwkv_wkv6_f32", rwkv_wkv6_f32_len, rwkv_wkv6_f32_data, "main", 7, sizeof(vk_op_rwkv_wkv6_push_constants), {1, 1, 1}, {device->subgroup_size}, 1); ggml_vk_create_pipeline(device, device->pipeline_rwkv_wkv7_f32, "rwkv_wkv7_f32", rwkv_wkv7_f32_len, rwkv_wkv7_f32_data, "main", 8, sizeof(vk_op_rwkv_wkv7_push_constants), {1, 1, 1}, {device->subgroup_size}, 1); + ggml_vk_create_pipeline(device, device->pipeline_gated_linear_attn_f32, "gated_linear_attn_f32", gated_linear_attn_f32_len, gated_linear_attn_f32_data, "main", 6, sizeof(vk_op_gated_linear_attn_push_constants), {1, 1, 1}, {}, 1); + { const uint32_t gdn_sizes[] = {16, 32, 64, 128}; const char * gdn_names[][2] = { @@ -11332,6 +11382,11 @@ static vk_pipeline ggml_vk_op_get_pipeline(ggml_backend_vk_context * ctx, const case GGML_TYPE_BF16: return ctx->device->pipeline_col2im_1d_bf16; default: return nullptr; } + case GGML_OP_POOL_1D: + if (src0->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32) { + return ctx->device->pipeline_pool1d_f32; + } + return nullptr; case GGML_OP_POOL_2D: if (src0->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32) { return ctx->device->pipeline_pool2d_f32; @@ -11347,6 +11402,11 @@ static vk_pipeline ggml_vk_op_get_pipeline(ggml_backend_vk_context * ctx, const return ctx->device->pipeline_rwkv_wkv7_f32; } return nullptr; + case GGML_OP_GATED_LINEAR_ATTN: + if (src0->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32) { + return ctx->device->pipeline_gated_linear_attn_f32; + } + return nullptr; case GGML_OP_GATED_DELTA_NET: if (src0->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32) { const uint32_t S_v = dst->src[2]->ne[0]; @@ -11854,6 +11914,13 @@ static void ggml_vk_op_f32(ggml_backend_vk_context * ctx, vk_context& subctx, co { elements = { uint32_t(dst->ne[0]), uint32_t(dst->ne[1]), 1 }; } break; + case GGML_OP_POOL_1D: + { + const uint32_t N = dst->ne[3] * dst->ne[2]; + const uint32_t OC = dst->ne[1]; + const uint32_t OL = dst->ne[0]; + elements = { N * OC * OL, 1, 1}; + } break; case GGML_OP_POOL_2D: { const uint32_t N = dst->ne[3]; @@ -12370,6 +12437,41 @@ static void ggml_vk_rwkv_wkv7(ggml_backend_vk_context * ctx, vk_context& subctx, ); } +static void ggml_vk_gated_linear_attn(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_tensor * dst) { + const size_t seq_length = dst->src[0]->ne[2]; + const size_t n_embed = dst->ne[0]; + const size_t n_heads = dst->src[0]->ne[1]; + const size_t n_seqs = dst->src[4]->ne[1]; + + float scale; + memcpy(&scale, dst->op_params, sizeof(float)); + + GGML_ASSERT(dst->buffer != nullptr); + + vk_pipeline pipeline = ggml_vk_op_get_pipeline(ctx, dst->src[0], dst->src[1], dst->src[2], dst, dst->op); + GGML_ASSERT(pipeline != nullptr); + + ggml_pipeline_request_descriptor_sets(ctx, pipeline, 1); + + vk_subbuffer dst_buf = ggml_vk_tensor_subbuffer(ctx, dst); + vk_subbuffer src_buf[5] = {}; + for (int i = 0; i < 5; i++) { + src_buf[i] = ggml_vk_tensor_subbuffer(ctx, dst->src[i]); + } + + const vk_op_gated_linear_attn_push_constants pc = { + (uint32_t)n_seqs, + (uint32_t)seq_length, + (uint32_t)n_embed, + (uint32_t)n_heads, + scale, + }; + + ggml_vk_dispatch_pipeline(ctx, subctx, pipeline, + {src_buf[0], src_buf[1], src_buf[2], src_buf[3], src_buf[4], dst_buf}, + pc, { (uint32_t)(n_seqs * n_heads), 1, 1 }); +} + static void ggml_vk_gated_delta_net(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_tensor * dst) { const ggml_tensor * src_q = dst->src[0]; const ggml_tensor * src_v = dst->src[2]; @@ -13175,12 +13277,16 @@ static void ggml_vk_soft_max_back(ggml_backend_vk_context * ctx, vk_context& sub static void ggml_vk_topk_moe(ggml_backend_vk_context * ctx, vk_context& subctx, ggml_cgraph * cgraph, int node_idx) { topk_moe_mode mode = ctx->fused_topk_moe_mode; + const bool has_bias = mode == TOPK_MOE_SIGMOID_NORM_BIAS || mode == TOPK_MOE_SQRT_SOFTPLUS_NORM_BIAS; ggml_tensor * logits = cgraph->nodes[node_idx + 0]->src[0]; - ggml_tensor * bias = (mode == TOPK_MOE_SIGMOID_NORM_BIAS) ? cgraph->nodes[node_idx + 2]->src[1] : logits; + ggml_tensor * bias = mode == TOPK_MOE_SIGMOID_NORM_BIAS ? cgraph->nodes[node_idx + 2]->src[1] : + mode == TOPK_MOE_SQRT_SOFTPLUS_NORM_BIAS ? cgraph->nodes[node_idx + 3]->src[1] : + logits; ggml_tensor * weights = cgraph->nodes[node_idx + ctx->num_additional_fused_ops]; - ggml_tensor * ids = (mode == TOPK_MOE_SIGMOID_NORM_BIAS) ? cgraph->nodes[node_idx + 4] : - (mode == TOPK_MOE_LATE_SOFTMAX) ? cgraph->nodes[node_idx + 1] : - cgraph->nodes[node_idx + 3]; + ggml_tensor * ids = mode == TOPK_MOE_SIGMOID_NORM_BIAS ? cgraph->nodes[node_idx + 4] : + mode == TOPK_MOE_SQRT_SOFTPLUS_NORM_BIAS ? cgraph->nodes[node_idx + 5] : + mode == TOPK_MOE_LATE_SOFTMAX ? cgraph->nodes[node_idx + 1] : + cgraph->nodes[node_idx + 3]; GGML_ASSERT(logits->type == GGML_TYPE_F32); GGML_ASSERT(bias->type == GGML_TYPE_F32); @@ -13220,16 +13326,24 @@ static void ggml_vk_topk_moe(ggml_backend_vk_context * ctx, vk_context& subctx, pc.clamp_min = ggml_get_op_params_f32(clamp, 0); pc.clamp_max = ggml_get_op_params_f32(clamp, 1); } + if (mode == TOPK_MOE_SQRT_SOFTPLUS_NORM_BIAS) { + ggml_tensor * clamp = cgraph->nodes[node_idx + 9]; + GGML_ASSERT(clamp->op == GGML_OP_CLAMP); + pc.clamp_min = ggml_get_op_params_f32(clamp, 0); + pc.clamp_max = ggml_get_op_params_f32(clamp, 1); + } #define GATING_FUNC_SOFTMAX 0 #define GATING_FUNC_SIGMOID 1 #define GATING_FUNC_SOFTMAX_WEIGHT 2 - - pc.gating_func = mode == TOPK_MOE_SIGMOID_NORM_BIAS ? GATING_FUNC_SIGMOID : - mode == TOPK_MOE_LATE_SOFTMAX ? GATING_FUNC_SOFTMAX_WEIGHT : - GATING_FUNC_SOFTMAX; - pc.has_bias = mode == TOPK_MOE_SIGMOID_NORM_BIAS; - pc.with_norm = mode == TOPK_MOE_EARLY_SOFTMAX_NORM || mode == TOPK_MOE_SIGMOID_NORM_BIAS; +#define GATING_FUNC_SQRT_SOFTPLUS 3 + + pc.gating_func = mode == TOPK_MOE_SIGMOID_NORM_BIAS ? GATING_FUNC_SIGMOID : + mode == TOPK_MOE_SQRT_SOFTPLUS_NORM_BIAS ? GATING_FUNC_SQRT_SOFTPLUS : + mode == TOPK_MOE_LATE_SOFTMAX ? GATING_FUNC_SOFTMAX_WEIGHT : + GATING_FUNC_SOFTMAX; + pc.has_bias = has_bias; + pc.with_norm = mode == TOPK_MOE_EARLY_SOFTMAX_NORM || has_bias; if (ctx->fused_topk_moe_scale) { GGML_ASSERT(weights->op == GGML_OP_SCALE); pc.output_scale = ggml_get_op_params_f32(weights, 0); @@ -13773,6 +13887,29 @@ static void ggml_vk_snake_dispatch_fused(ggml_backend_vk_context * ctx, vk_conte ggml_vk_dispatch_pipeline(ctx, subctx, pipeline, { x_buf, a_buf, inv_b_buf, dst_buf }, pc, elements); } +static void ggml_vk_pool_1d(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst) { + uint32_t op = static_cast(dst->op_params[0]); + const int32_t k0 = dst->op_params[1]; + const int32_t s0 = dst->op_params[2]; + const int32_t p0 = dst->op_params[3]; + + const uint32_t IL = src0->ne[0]; + + const uint32_t N = dst->ne[3] * dst->ne[2]; + + const uint32_t OC = dst->ne[1]; + const uint32_t OL = dst->ne[0]; + + const uint32_t parallel_elements = N * OC * OL; + + ggml_vk_op_f32(ctx, subctx, src0, nullptr, nullptr, nullptr, dst, GGML_OP_POOL_1D, { + IL, OL, OC, + parallel_elements, + op, + k0, s0, p0, + }); +} + static void ggml_vk_pool_2d(ggml_backend_vk_context * ctx, vk_context& subctx, const ggml_tensor * src0, ggml_tensor * dst) { uint32_t op = static_cast(dst->op_params[0]); const int32_t k1 = dst->op_params[1]; @@ -15284,6 +15421,10 @@ static bool ggml_vk_build_graph(ggml_backend_vk_context * ctx, ggml_cgraph * cgr case GGML_OP_CONV_TRANSPOSE_1D: ggml_vk_conv_transpose_1d(ctx, compute_ctx, src0, src1, node); + break; + case GGML_OP_POOL_1D: + ggml_vk_pool_1d(ctx, compute_ctx, src0, node); + break; case GGML_OP_POOL_2D: ggml_vk_pool_2d(ctx, compute_ctx, src0, node); @@ -15330,6 +15471,11 @@ static bool ggml_vk_build_graph(ggml_backend_vk_context * ctx, ggml_cgraph * cgr break; + case GGML_OP_GATED_LINEAR_ATTN: + ggml_vk_gated_linear_attn(ctx, compute_ctx, node); + + break; + case GGML_OP_GATED_DELTA_NET: ggml_vk_gated_delta_net(ctx, compute_ctx, node); @@ -16311,6 +16457,20 @@ static bool ggml_vk_can_fuse_topk_moe(ggml_backend_vk_context * ctx, const struc return false; } break; + case TOPK_MOE_SQRT_SOFTPLUS_NORM_BIAS: + softmax = cgraph->nodes[node_idx + 0]; // really softplus + weights = cgraph->nodes[node_idx + 11]; + get_rows = cgraph->nodes[node_idx + 6]; + argsort = cgraph->nodes[node_idx + 4]; + if (ggml_get_unary_op(softmax) != GGML_UNARY_OP_SOFTPLUS) { + return false; + } + // bias is expected to be 1D + if (ggml_nrows(cgraph->nodes[node_idx + 3]->src[1]) != 1 || + !ggml_is_contiguous(cgraph->nodes[node_idx + 3]->src[1])) { + return false; + } + break; case TOPK_MOE_EARLY_SOFTMAX: softmax = cgraph->nodes[node_idx + 0]; weights = cgraph->nodes[node_idx + 4]; @@ -16334,7 +16494,9 @@ static bool ggml_vk_can_fuse_topk_moe(ggml_backend_vk_context * ctx, const struc probs = probs->src[0]; ggml_tensor * selection_probs = argsort->src[0]; - if (probs != selection_probs && mode != TOPK_MOE_SIGMOID_NORM_BIAS) { + if (probs != selection_probs && + mode != TOPK_MOE_SIGMOID_NORM_BIAS && + mode != TOPK_MOE_SQRT_SOFTPLUS_NORM_BIAS) { return false; } @@ -16702,7 +16864,7 @@ static ggml_status ggml_backend_vk_graph_compute(ggml_backend_t backend, ggml_cg // the fused result in an elementwise-way. This affects whether the memory for // the src is allowed to overlap the memory for the destination. // The array is sized to handle the largest fusion (asserted later). - bool op_srcs_fused_elementwise[12]; + bool op_srcs_fused_elementwise[13]; ctx->fused_topk_moe_mode = TOPK_MOE_COUNT; ctx->fused_topk_moe_scale = false; @@ -16813,6 +16975,15 @@ static ggml_status ggml_backend_vk_graph_compute(ggml_backend_t backend, ggml_cg ctx->fused_topk_moe_mode = TOPK_MOE_SIGMOID_NORM_BIAS; fusion_string = "TOPK_MOE_SIGMOID_NORM_BIAS"; std::fill_n(op_srcs_fused_elementwise, ctx->num_additional_fused_ops + 1, false); + } else if (ggml_can_fuse_subgraph(cgraph, i, topk_moe_sqrt_softplus_norm_bias, { i + 5, i + 11 }) && + ggml_check_edges(cgraph, i, topk_moe_sqrt_softplus_norm_bias_edges) && + ggml_vk_can_fuse_topk_moe(ctx, cgraph, i, TOPK_MOE_SQRT_SOFTPLUS_NORM_BIAS)) { + ctx->num_additional_fused_ops = topk_moe_sqrt_softplus_norm_bias.size() - 1; + // view of argsort writes to memory + ctx->fused_ops_write_mask |= 1 << 5; + ctx->fused_topk_moe_mode = TOPK_MOE_SQRT_SOFTPLUS_NORM_BIAS; + fusion_string = "TOPK_MOE_SQRT_SOFTPLUS_NORM_BIAS"; + std::fill_n(op_srcs_fused_elementwise, ctx->num_additional_fused_ops + 1, false); } else if (ggml_can_fuse_subgraph(cgraph, i, topk_moe_early_softmax, { i + 3, i + 4 }) && ggml_check_edges(cgraph, i, topk_moe_early_softmax_edges) && ggml_vk_can_fuse_topk_moe(ctx, cgraph, i, TOPK_MOE_EARLY_SOFTMAX)) { @@ -17079,6 +17250,9 @@ static void ggml_vk_graph_optimize(ggml_backend_t backend, struct ggml_cgraph * if (keep_pattern(topk_moe_sigmoid_norm_bias)) { continue; } + if (keep_pattern(topk_moe_sqrt_softplus_norm_bias)) { + continue; + } if (keep_pattern(topk_moe_early_softmax)) { continue; } @@ -17109,6 +17283,7 @@ static void ggml_vk_graph_optimize(ggml_backend_t backend, struct ggml_cgraph * // Don't pull forward nodes from fusion patterns if (match_pattern(topk_moe_early_softmax_norm, j) || match_pattern(topk_moe_sigmoid_norm_bias, j) || + match_pattern(topk_moe_sqrt_softplus_norm_bias, j) || match_pattern(topk_moe_early_softmax, j) || match_pattern(topk_moe_late_softmax, j) || match_pattern(snake_pattern, j)) { @@ -18001,11 +18176,16 @@ static bool ggml_backend_vk_device_supports_op(ggml_backend_dev_t dev, const ggm case GGML_OP_CONV_2D_DW: return (op->src[0]->type == GGML_TYPE_F32 || op->src[0]->type == GGML_TYPE_F16) && op->src[1]->type == GGML_TYPE_F32; + case GGML_OP_POOL_1D: + return ggml_is_contiguous(op->src[0]) && op->src[0]->type == GGML_TYPE_F32; case GGML_OP_POOL_2D: return ggml_is_contiguous(op->src[0]) && op->src[0]->type == GGML_TYPE_F32; case GGML_OP_RWKV_WKV6: case GGML_OP_RWKV_WKV7: return true; // all inputs are contiguous, see ggml.c + case GGML_OP_GATED_LINEAR_ATTN: + // the shader block size is hardcoded to head_size 64 + return op->src[0]->type == GGML_TYPE_F32 && op->type == GGML_TYPE_F32 && op->src[0]->ne[0] == 64; case GGML_OP_GATED_DELTA_NET: { const uint32_t S_v = op->src[2]->ne[0]; @@ -18466,6 +18646,22 @@ static uint32_t ggml_vk_intel_shader_core_count(const vk::PhysicalDevice& vkdev) } } +static bool ggml_vk_intel_windows_driver_equals_or_newer_than(uint32_t driver_version, uint32_t threshold_major, uint32_t threshold_minor) { +#if defined(_WIN32) + // Intel Windows encodes xxx.yyyy as [31:14].[13:0]. + const uint32_t major = driver_version >> 14; + const uint32_t minor = driver_version & 0x3fff; + + return major > threshold_major || (major == threshold_major && minor >= threshold_minor); +#else + GGML_UNUSED(driver_version); + GGML_UNUSED(threshold_major); + GGML_UNUSED(threshold_minor); + return true; +#endif +} + + // checks #ifdef GGML_VULKAN_CHECK_RESULTS @@ -18920,6 +19116,13 @@ static void ggml_vk_check_results_0(ggml_backend_vk_context * ctx, ggml_cgraph * const int32_t oc = tensor->op_params[1]; const int32_t p0 = tensor->op_params[2]; tensor_clone = ggml_col2im_1d(ggml_ctx, src_clone[0], stride, oc, p0); + } else if (tensor->op == GGML_OP_POOL_1D) { + enum ggml_op_pool op = static_cast(tensor->op_params[0]); + const int32_t k0 = tensor->op_params[1]; + const int32_t s0 = tensor->op_params[2]; + const int32_t p0 = tensor->op_params[3]; + + tensor_clone = ggml_pool_1d(ggml_ctx, src_clone[0], op, k0, s0, p0); } else if (tensor->op == GGML_OP_POOL_2D) { enum ggml_op_pool op = static_cast(tensor->op_params[0]); const int32_t k0 = tensor->op_params[1]; @@ -18972,6 +19175,10 @@ static void ggml_vk_check_results_0(ggml_backend_vk_context * ctx, ggml_cgraph * } else if (tensor->op == GGML_OP_RWKV_WKV7) { tensor_clone = ggml_rwkv_wkv7(ggml_ctx, src_clone[0], src_clone[1], src_clone[2], src_clone[3], src_clone[4], src_clone[5], src_clone[6]); + } else if (tensor->op == GGML_OP_GATED_LINEAR_ATTN) { + const float * op_params = (const float *)tensor->op_params; + tensor_clone = ggml_gated_linear_attn(ggml_ctx, src_clone[0], src_clone[1], + src_clone[2], src_clone[3], src_clone[4], op_params[0]); } else if (tensor->op == GGML_OP_GATED_DELTA_NET) { tensor_clone = ggml_gated_delta_net(ggml_ctx, src_clone[0], src_clone[1], src_clone[2], src_clone[3], src_clone[4], src_clone[5], diff --git a/ggml/src/ggml-vulkan/vulkan-shaders/gla.comp b/ggml/src/ggml-vulkan/vulkan-shaders/gla.comp new file mode 100644 index 000000000000..b3387616b642 --- /dev/null +++ b/ggml/src/ggml-vulkan/vulkan-shaders/gla.comp @@ -0,0 +1,82 @@ +#version 450 + +#extension GL_EXT_control_flow_attributes : require + +#define BLOCK_SIZE 64 +layout(local_size_x = BLOCK_SIZE, local_size_y = 1, local_size_z = 1) in; + +layout(push_constant) uniform Parameters { + uint B; + uint T; + uint C; + uint H; + float scale; +}; + +layout(binding = 0) readonly buffer KBuf { A_TYPE k[]; }; +layout(binding = 1) readonly buffer VBuf { A_TYPE v[]; }; +layout(binding = 2) readonly buffer QBuf { A_TYPE q[]; }; +layout(binding = 3) readonly buffer GBuf { A_TYPE g[]; }; +layout(binding = 4) readonly buffer StateBuf { A_TYPE state_in[]; }; +layout(binding = 5) buffer DstBuf { A_TYPE dst[]; }; + +shared A_TYPE _k[BLOCK_SIZE], _q[BLOCK_SIZE], _g[BLOCK_SIZE]; + +void main() { + const uint head_size = BLOCK_SIZE; + const uint batch_id = gl_WorkGroupID.x / H; + const uint head_id = gl_WorkGroupID.x % H; + const uint tid = gl_LocalInvocationID.x; + + const uint state_size = C * head_size; + const uint n_seq_tokens = T / B; + + if (batch_id >= B || head_id >= H) { + return; + } + + // state[i] holds column tid of this head's state matrix: S[i][tid] + A_TYPE state[BLOCK_SIZE]; + [[unroll]] for (uint i = 0; i < head_size; i++) { + state[i] = state_in[batch_id * state_size + head_id * head_size * head_size + + i * head_size + tid]; + } + + const uint start_t = batch_id * n_seq_tokens * C + head_id * head_size + tid; + const uint end_t = (batch_id + 1) * n_seq_tokens * C + head_id * head_size + tid; + + for (uint t = start_t; t < end_t; t += C) { + barrier(); + _k[tid] = k[t]; + _q[tid] = q[t]; + _g[tid] = g[t]; + barrier(); + + const A_TYPE v_val = v[t]; + A_TYPE y = 0.0; + + [[unroll]] for (uint i = 0; i < head_size; i += 4) { + vec4 k_vec = vec4(_k[i], _k[i+1], _k[i+2], _k[i+3]); + vec4 q_vec = vec4(_q[i], _q[i+1], _q[i+2], _q[i+3]); + vec4 g_vec = vec4(_g[i], _g[i+1], _g[i+2], _g[i+3]); + vec4 s_vec = vec4(state[i], state[i+1], state[i+2], state[i+3]); + + vec4 kv = k_vec * v_val; + + s_vec = s_vec * g_vec + kv; + y += dot(q_vec, s_vec); + + state[i] = s_vec.x; + state[i+1] = s_vec.y; + state[i+2] = s_vec.z; + state[i+3] = s_vec.w; + } + + dst[t] = y * scale; + } + + [[unroll]] for (uint i = 0; i < head_size; i++) { + dst[T * C + batch_id * state_size + head_id * head_size * head_size + + i * head_size + tid] = state[i]; + } +} diff --git a/ggml/src/ggml-vulkan/vulkan-shaders/pool1d.comp b/ggml/src/ggml-vulkan/vulkan-shaders/pool1d.comp new file mode 100644 index 000000000000..bb87631ce363 --- /dev/null +++ b/ggml/src/ggml-vulkan/vulkan-shaders/pool1d.comp @@ -0,0 +1,65 @@ +#version 450 + +#include "types.glsl" + +#extension GL_EXT_shader_16bit_storage : require + +layout(push_constant) uniform parameter { + uint IL; + uint OL; + uint OC; + uint pelements; + uint op; + int k0; + int s0; + int p0; +} p; + +#define BLOCK_SIZE 512 +#define FLT_MAX 3.402823466e+38F +#define OP_POOL_MAX 0u +#define OP_POOL_AVG 1u + +layout (local_size_x = BLOCK_SIZE, local_size_y = 1, local_size_z = 1) in; + +layout(binding = 0) readonly buffer X {A_TYPE data_a[];}; +layout(binding = 1) writeonly buffer D {D_TYPE data_d[];}; + +void main() { + const uint idx = gl_GlobalInvocationID.x; + if (idx >= p.pelements) { + return; + } + + const uint nc = idx / p.OL; + const uint cur_ol = idx % p.OL; + + const int start = int(cur_ol) * p.s0 - p.p0; + const int bl = max(start, 0); + const int el = min(max(start + p.k0, 0), int(p.IL)); + + const int window_size = el - bl; + const float scale = window_size > 0 ? 1.0 / float(window_size) : 0.0; + float res; + + if (p.op == OP_POOL_AVG) { + res = 0.0; + } else if (p.op == OP_POOL_MAX) { + res = -FLT_MAX; + } else { + return; + } + + #pragma unroll + for (uint i = bl; i < el; i++) { + const float cur = D_TYPE(data_a[nc * p.IL + i]); + + if (p.op == OP_POOL_AVG) { + res += cur * scale; + } else if (p.op == OP_POOL_MAX) { + res = max(res, cur); + } + } + + data_d[nc * p.OL + cur_ol] = res; +} diff --git a/ggml/src/ggml-vulkan/vulkan-shaders/topk_moe.comp b/ggml/src/ggml-vulkan/vulkan-shaders/topk_moe.comp index ef2f202ec9b6..d219201fda0a 100644 --- a/ggml/src/ggml-vulkan/vulkan-shaders/topk_moe.comp +++ b/ggml/src/ggml-vulkan/vulkan-shaders/topk_moe.comp @@ -10,6 +10,7 @@ #define GATING_FUNC_SOFTMAX 0 #define GATING_FUNC_SIGMOID 1 #define GATING_FUNC_SOFTMAX_WEIGHT 2 +#define GATING_FUNC_SQRT_SOFTPLUS 3 layout (push_constant) uniform parameter { @@ -120,6 +121,13 @@ void main() { const uint expert = i + lane; probs[i / WARP_SIZE] = (n_experts % WARP_SIZE == 0 || expert < n_experts) ? 1.f / (1.f + exp(-probs[i / WARP_SIZE])) : -INFINITY; } + } else if (gating_func == GATING_FUNC_SQRT_SOFTPLUS) { + [[unroll]] + for (uint i = 0; i < n_experts; i += WARP_SIZE) { + const uint expert = i + lane; + const float val = probs[i / WARP_SIZE]; + probs[i / WARP_SIZE] = (n_experts % WARP_SIZE == 0 || expert < n_experts) ? sqrt(val > 20.0f ? val : log(1.0f + exp(val))) : -INFINITY; + } } float selection_probs[experts_per_thread]; diff --git a/ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp b/ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp index 3e6b39576e6d..c93d6eecee1b 100644 --- a/ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp +++ b/ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp @@ -1052,10 +1052,13 @@ void process_shaders() { string_to_spv("snake_f16", "snake.comp", {{"DATA_A_F16", "1"}, {"A_TYPE", "float16_t"}, {"D_TYPE", "float16_t"}}); string_to_spv("snake_bf16", "snake.comp", {{"DATA_A_BF16", "1"}, {"DATA_D_BF16", "1"}, {"A_TYPE", "uint16_t"}, {"D_TYPE", "uint16_t"}}); + string_to_spv("pool1d_f32", "pool1d.comp", merge_maps(base_dict, {{"A_TYPE", "float"}, {"D_TYPE", "float"}})); string_to_spv("pool2d_f32", "pool2d.comp", merge_maps(base_dict, {{"A_TYPE", "float"}, {"D_TYPE", "float"}})); string_to_spv("rwkv_wkv6_f32", "wkv6.comp", merge_maps(base_dict, {{"A_TYPE", "float"}})); + string_to_spv("gated_linear_attn_f32", "gla.comp", merge_maps(base_dict, {{"A_TYPE", "float"}})); + string_to_spv("rwkv_wkv7_f32", "wkv7.comp", merge_maps(base_dict, {{"A_TYPE", "float"}})); string_to_spv("gated_delta_net_f32", "gated_delta_net.comp", merge_maps(base_dict, {{"FLOAT_TYPE", "float"}, {"USE_SUBGROUP_ADD", "1"}, {"USE_SUBGROUP_CLUSTERED", "1"}})); diff --git a/ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp b/ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp index babaddb6542d..66c1c3c8977e 100644 --- a/ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp +++ b/ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp @@ -2774,6 +2774,10 @@ class ggml_webgpu_shader_lib { defines.push_back("TYPE_F32"); variant += "_f32"; break; + case GGML_TYPE_F16: + defines.push_back("TYPE_F16"); + variant += "_f16"; + break; case GGML_TYPE_I32: defines.push_back("TYPE_I32"); variant += "_i32"; diff --git a/ggml/src/ggml-webgpu/ggml-webgpu.cpp b/ggml/src/ggml-webgpu/ggml-webgpu.cpp index 370f05dfe67a..c001cda7d116 100644 --- a/ggml/src/ggml-webgpu/ggml-webgpu.cpp +++ b/ggml/src/ggml-webgpu/ggml-webgpu.cpp @@ -4290,7 +4290,8 @@ static bool ggml_backend_webgpu_device_supports_op(ggml_backend_dev_t dev, const supports_op = (src0->type == GGML_TYPE_F32 || src0->type == GGML_TYPE_I32); break; case GGML_OP_REPEAT: - supports_op = (src0->type == GGML_TYPE_F32 || src0->type == GGML_TYPE_I32 || src0->type == GGML_TYPE_I16); + supports_op = (src0->type == GGML_TYPE_F32 || src0->type == GGML_TYPE_F16 || src0->type == GGML_TYPE_I32 || + src0->type == GGML_TYPE_I16); break; case GGML_OP_CPY: case GGML_OP_CONT: diff --git a/ggml/src/ggml-webgpu/wgsl-shaders/repeat.wgsl b/ggml/src/ggml-webgpu/wgsl-shaders/repeat.wgsl index 6e2a1a8b614d..43b883e67945 100644 --- a/ggml/src/ggml-webgpu/wgsl-shaders/repeat.wgsl +++ b/ggml/src/ggml-webgpu/wgsl-shaders/repeat.wgsl @@ -27,6 +27,9 @@ struct Params { #ifdef TYPE_I32 #define DataType i32 #endif +#ifdef TYPE_F16 +#define DataType f16 +#endif #ifdef TYPE_I16 // same size (16-bit) is sufficient for repeat #define DataType f16 diff --git a/ggml/src/ggml-zendnn/CMakeLists.txt b/ggml/src/ggml-zendnn/CMakeLists.txt index e4ba9cfbd0fc..87d721f6d78a 100644 --- a/ggml/src/ggml-zendnn/CMakeLists.txt +++ b/ggml/src/ggml-zendnn/CMakeLists.txt @@ -28,7 +28,7 @@ if (NOT ZENDNN_ROOT OR ZENDNN_ROOT STREQUAL "" OR ZENDNN_ROOT STREQUAL "OFF") ExternalProject_Add( zendnn GIT_REPOSITORY https://github.com/amd/ZenDNN.git - GIT_TAG 253b94ce0d7e9284c265fefb485714944caff9d3 # ZenDNN-2026-WW19 + GIT_TAG 1f399a75cc0993778374a51bea49b64a57879595 # ZenDNN-2026-WW28 PREFIX ${ZENDNN_PREFIX} SOURCE_DIR ${ZENDNN_SOURCE_DIR} BINARY_DIR ${ZENDNN_BUILD_DIR} diff --git a/ggml/src/ggml-zendnn/ggml-zendnn.cpp b/ggml/src/ggml-zendnn/ggml-zendnn.cpp index 3c33dcb11a03..e6a9b51b7925 100644 --- a/ggml/src/ggml-zendnn/ggml-zendnn.cpp +++ b/ggml/src/ggml-zendnn/ggml-zendnn.cpp @@ -30,6 +30,29 @@ zendnnl::common::data_type_t ggml_to_zendnn_type() { } } +/** + * Builds the matmul_params shared by ggml_zendnn_matmul() and ggml_zendnn_group_matmul(): + * dtype selection plus, for Q8_0 weights, dynamic-quant setup. Callers still need to set + * quant_params.src_scale.dims themselves, since that depends on the batch size(s) in use. + */ +template +static zendnnl::lowoha::matmul::matmul_params ggml_zendnn_make_matmul_params(ggml_backend_zendnn_context * ctx) { + zendnnl::lowoha::matmul::matmul_params params; + params.dtypes.src = ggml_to_zendnn_type(); + params.dtypes.wei = ggml_to_zendnn_type(); + params.dtypes.dst = ggml_to_zendnn_type(); + params.num_threads = ctx->n_threads; + + if constexpr (std::is_same_v) { + params.dtypes.compute = zendnnl::common::data_type_t::s8; + params.dynamic_quant = true; + params.quant_params.src_scale.buff = nullptr; + params.quant_params.src_scale.dt = zendnnl::common::data_type_t::bf16; + params.packing.pack_format_b = 1; + } + return params; +} + /** * ZenDNN matmul: computes C = B * A. * @@ -47,22 +70,12 @@ static bool ggml_zendnn_matmul(ggml_backend_zendnn_context * ctx, int64_t m, int const TA * A, int64_t lda, const TB * B, int64_t ldb, TC * C, int64_t ldc) { - zendnnl::lowoha::matmul::matmul_params params; - params.dtypes.src = ggml_to_zendnn_type(); - params.dtypes.wei = ggml_to_zendnn_type(); - params.dtypes.dst = ggml_to_zendnn_type(); - params.num_threads = ctx->n_threads; + zendnnl::lowoha::matmul::matmul_params params = ggml_zendnn_make_matmul_params(ctx); zendnnl::lowoha::matmul::matmul_batch_params_t batch_params; if constexpr (std::is_same_v) { - params.dtypes.compute = zendnnl::common::data_type_t::s8; - const int64_t num_groups = k / QK8_0; - params.dynamic_quant = true; - params.quant_params.src_scale.buff = nullptr; - params.quant_params.src_scale.dt = zendnnl::common::data_type_t::bf16; - params.quant_params.src_scale.dims = {n, num_groups}; - params.packing.pack_format_b = 1; + params.quant_params.src_scale.dims = {n, k / QK8_0}; } zendnnl::error_handling::status_t status = zendnnl::lowoha::matmul::matmul_direct( @@ -223,6 +236,99 @@ struct mmid_row_mapping { int32_t i2; }; +/** + * ZenDNN batched matmul: computes C[i] = B[i] * A[i] for every active expert i via a single + * group_matmul_direct() call. Batched analogue of ggml_zendnn_matmul() - see its docs for the + * per-expert A/B/C shape convention. m and k are shared by every expert; n (batch size) varies + * per expert, hence the vector. + */ +template +static bool ggml_zendnn_group_matmul(ggml_backend_zendnn_context * ctx, int64_t m, int64_t k, + const std::vector & n, + const std::vector & A, int64_t lda, + const std::vector & B, int64_t ldb, + const std::vector & C, int64_t ldc) { + + const int n_experts = n.size(); + + zendnnl::lowoha::matmul::matmul_params base_params = ggml_zendnn_make_matmul_params(ctx); + + std::vector layout(n_experts, 'r'); + std::vector trans_a(n_experts, false); + std::vector trans_b(n_experts, true); + std::vector batch_m(n_experts); + std::vector batch_n(n_experts, m); + std::vector batch_k(n_experts, k); + std::vector alpha(n_experts, 1.0f); + std::vector beta(n_experts, 0.0f); + std::vector bias(n_experts, nullptr); + std::vector lda_v(n_experts, lda); + std::vector ldb_v(n_experts, ldb); + std::vector ldc_v(n_experts, ldc); + std::vector is_wei_const(n_experts, true); + std::vector params(n_experts, base_params); + + for (int i = 0; i < n_experts; i++) { + batch_m[i] = n[i]; + + // src_scale.dims depends on this expert's row count, unlike the rest of base_params + if constexpr (std::is_same_v) { + params[i].quant_params.src_scale.dims = {n[i], k / QK8_0}; + } + } + + zendnnl::error_handling::status_t status = zendnnl::lowoha::matmul::group_matmul_direct( + layout, trans_a, trans_b, batch_m, batch_n, batch_k, alpha, + B, ldb_v, A, lda_v, bias, beta, + C, ldc_v, is_wei_const, params); + + if (status != zendnnl::error_handling::status_t::success) { + GGML_LOG_ERROR("%s, ZenDNN group matmul failed: status=%d\n", __func__, static_cast(status)); + return false; + } + return true; +} + +static bool ggml_zendnn_group_gemm(ggml_backend_zendnn_context * ctx, int64_t m, int64_t k, + const std::vector & n, + const std::vector & A, int64_t lda, + const std::vector & B, int64_t ldb, + const std::vector & C, int64_t ldc, + int Atype, int Btype, int Ctype) { + + assert(m >= 0); + for (size_t i = 0; i < n.size(); i++) { + assert(n[i] >= 0); + } + assert(k >= 0); + assert(lda >= k); + assert(ldb >= k); + assert(ldc >= m); + + // categorize types + switch (Atype) { + case GGML_TYPE_F32: + if (Btype != GGML_TYPE_F32 || Ctype != GGML_TYPE_F32) + return false; + return ggml_zendnn_group_matmul(ctx, m, k, n, A, lda, B, ldb, C, ldc); + case GGML_TYPE_BF16: + if (Btype != GGML_TYPE_BF16) + return false; + if (Ctype == GGML_TYPE_BF16) + return ggml_zendnn_group_matmul( + ctx, m, k, n, A, lda, B, ldb, C, ldc); + if (Ctype == GGML_TYPE_F32) + return ggml_zendnn_group_matmul(ctx, m, k, n, A, lda, B, ldb, C, ldc); + return false; + case GGML_TYPE_Q8_0: + if (Btype != GGML_TYPE_F32 || Ctype != GGML_TYPE_F32) + return false; + return ggml_zendnn_group_matmul(ctx, m, k, n, A, lda, B, ldb, C, ldc); + default: + return false; // unsupported type + } +} + static void ggml_zendnn_compute_forward_mul_mat_id( ggml_backend_zendnn_context * ctx, ggml_tensor * dst) { @@ -262,7 +368,8 @@ static void ggml_zendnn_compute_forward_mul_mat_id( std::vector matrix_row_counts(n_as, 0); std::vector> matrix_rows(n_as); - int64_t max_rows = 0; + int64_t total_rows = 0; + int n_active_experts = 0; // group rows by expert (preprocessing step) for (int64_t iid1 = 0; iid1 < ids->ne[1]; ++iid1) { for (int id = 0; id < n_ids; ++id) { @@ -270,66 +377,74 @@ static void ggml_zendnn_compute_forward_mul_mat_id( GGML_ASSERT(i02 >= 0 && i02 < n_as); + if (matrix_row_counts[i02] == 0) { + n_active_experts++; + } matrix_rows[i02].push_back({id, iid1}); matrix_row_counts[i02]++; - if (matrix_row_counts[i02] > max_rows) { - max_rows = matrix_row_counts[i02]; - } + total_rows++; } } - if (max_rows == 0) { + if (total_rows == 0) { return; // no rows to process } const size_t row_size = ggml_row_size(vec_dot_type, ne10); - // size for converting src1 rows to vec_dot_type if needed - const size_t nbw1 = row_size; - const size_t nbw2 = nbw1 * ne11; - const size_t nbw3 = nbw2 * ne12; - const size_t src1_conv_size = (src1->type != vec_dot_type && src0->type != GGML_TYPE_Q8_0) ? ne13 * nbw3 : 0; - // For Q8_0, src1 is always F32; the gather buffer must hold F32 rows (ne10*4 bytes), // not Q8_0-encoded rows (row_size ≈ ne10/32*34 bytes) — they differ by ~4x. const size_t f32_row_size = (size_t)ne10 * sizeof(float); const size_t gather_row_size = (src0->type == GGML_TYPE_Q8_0) ? f32_row_size : row_size; + if (src1->type != vec_dot_type && src0->type != GGML_TYPE_Q8_0) { + GGML_ASSERT(src1->type == GGML_TYPE_F32); + } + // size for MoE gather/scatter buffers - const size_t wdata_cur_size = max_rows * gather_row_size; - const size_t dst_cur_size = max_rows * ggml_row_size(dst->type, ne01); + const size_t wdata_cur_size = total_rows * gather_row_size; + const size_t dst_cur_size = total_rows * ggml_row_size(dst->type, ne01); // allocate single buffer for all needs - const size_t total_size = src1_conv_size + wdata_cur_size + dst_cur_size; + const size_t total_size = wdata_cur_size + dst_cur_size; if (ctx->work_size < total_size) { ctx->work_data.reset(new char[total_size]); ctx->work_size = total_size; } // partition the buffer - char * work_data = ctx->work_data.get(); - char * wdata_cur = work_data + src1_conv_size; + char * wdata_cur = ctx->work_data.get(); char * dst_cur = wdata_cur + wdata_cur_size; - // ZenDNN requires FP32 for dynamic quantization, so conversion is skipped - if (src1->type != vec_dot_type && src0->type != GGML_TYPE_Q8_0) { - GGML_ASSERT(src1->type == GGML_TYPE_F32); - - #pragma omp parallel for collapse(3) num_threads(ctx->n_threads) schedule(static) - for (int64_t i13 = 0; i13 < ne13; ++i13) { - for (int64_t i12 = 0; i12 < ne12; ++i12) { - for (int64_t i11 = 0; i11 < ne11; ++i11) { - const float * src1_f32 = (float *)((char *)src1->data + i11*nb11 + i12*nb12 + i13*nb13); - void * src1_conv = (char *)work_data + i11*nbw1 + i12*nbw2 + i13*nbw3; - from_float(src1_f32, src1_conv, ne10); - } + // per-expert data collected during gather, handed to ggml_zendnn_group_gemm() as one batch + std::vector expert_row_count(n_active_experts); + std::vector batch_src(n_active_experts); + std::vector batch_wei(n_active_experts); + std::vector batch_dst(n_active_experts); + + // precompute per-expert buffer offsets and batch indices for the parallel loop below + std::vector expert_wdata_off(n_as, 0); + std::vector expert_dst_off(n_as, 0); + std::vector expert_batch_idx(n_as, -1); + { + int64_t w_off = 0; + int64_t d_off = 0; + int batch_idx = 0; + for (int64_t cur_a = 0; cur_a < n_as; ++cur_a) { + if (matrix_row_counts[cur_a] == 0) { + continue; } + expert_wdata_off[cur_a] = w_off; + expert_dst_off[cur_a] = d_off; + expert_batch_idx[cur_a] = batch_idx; + w_off += matrix_row_counts[cur_a] * gather_row_size; + d_off += matrix_row_counts[cur_a] * ggml_row_size(dst->type, ne01); + batch_idx++; } } - const void * wdata = (src1->type == vec_dot_type || src0->type == GGML_TYPE_Q8_0) ? src1->data : work_data; - - // process each expert with gather -> gemm -> scatter pattern + // gather + inline-convert input rows into each expert's batch slot + #pragma omp parallel for num_threads(ctx->n_threads) schedule(static) for (int64_t cur_a = 0; cur_a < n_as; ++cur_a) { const int64_t cne1 = matrix_row_counts[cur_a]; @@ -337,42 +452,57 @@ static void ggml_zendnn_compute_forward_mul_mat_id( continue; } - const char * src0_cur = (const char *) src0->data + cur_a*nb02; + const int64_t w_off = expert_wdata_off[cur_a]; + const int64_t d_off = expert_dst_off[cur_a]; + const int batch_idx = expert_batch_idx[cur_a]; - // gather input rows for this expert - #pragma omp parallel for num_threads(ctx->n_threads) schedule(static) for (int64_t ir1 = 0; ir1 < cne1; ++ir1) { const mmid_row_mapping & row_mapping = matrix_rows[cur_a][ir1]; - const int64_t id = row_mapping.i1; + const int64_t id = row_mapping.i1; const int64_t i11 = id % ne11; const int64_t i12 = row_mapping.i2; - std::memcpy( - wdata_cur + ir1 * gather_row_size, - (const char *) wdata + (i11 + i12*ne11) * gather_row_size, - gather_row_size - ); + const char * src_row = (const char *) src1->data + i11*nb11 + i12*nb12; + void * dst_row = wdata_cur + w_off + ir1 * gather_row_size; + + if (src1->type != vec_dot_type && src0->type != GGML_TYPE_Q8_0) { + from_float((const float *) src_row, dst_row, ne10); + } else { + // no conversion: src1 already matches vec_dot_type, or src0 is Q8_0, whose + // ZenDNN dynamic quantization requires the row to stay in F32 + std::memcpy(dst_row, src_row, gather_row_size); + } } - // batched gemm for all tokens in this expert - if (!ggml_zendnn_gemm(ctx, - ne01, // m - cne1, // n - ne10, // k - src0_cur, - ne00, // lda - wdata_cur, - ne10, // ldb - dst_cur, - ne01, // ldc - src0->type, - src0->type == GGML_TYPE_Q8_0 ? GGML_TYPE_F32 : vec_dot_type, - dst->type)) { - GGML_ABORT("%s: ZenDNN gemm failed\n", __func__); + expert_row_count[batch_idx] = cne1; + batch_src[batch_idx] = wdata_cur + w_off; + batch_wei[batch_idx] = (const char *) src0->data + cur_a * nb02; + batch_dst[batch_idx] = dst_cur + d_off; + } + + if (!ggml_zendnn_group_gemm(ctx, + ne01, // m + ne10, // k + expert_row_count, // n (per expert) + batch_wei, ne00, // A: weights, lda + batch_src, ne10, // B: input, ldb + batch_dst, ne01, // C: output, ldc + src0->type, + src0->type == GGML_TYPE_Q8_0 ? GGML_TYPE_F32 : vec_dot_type, + dst->type)) + GGML_ABORT("%s: ZenDNN group gemm failed\n", __func__); + + // scatter output rows to destination + #pragma omp parallel for num_threads(ctx->n_threads) schedule(static) + for (int64_t cur_a = 0; cur_a < n_as; ++cur_a) { + const int64_t cne1 = matrix_row_counts[cur_a]; + + if (cne1 == 0) { + continue; } - // scatter output rows to destination - #pragma omp parallel for num_threads(ctx->n_threads) schedule(static) + const int64_t d_off = expert_dst_off[cur_a]; + for (int64_t ir1 = 0; ir1 < cne1; ++ir1) { const mmid_row_mapping & row_mapping = matrix_rows[cur_a][ir1]; const int64_t id = row_mapping.i1; @@ -381,7 +511,7 @@ static void ggml_zendnn_compute_forward_mul_mat_id( std::memcpy( (char *) dst->data + i1*nb1 + i2*nb2, - dst_cur + ir1 * ggml_row_size(dst->type, ne01), + dst_cur + d_off + ir1 * ggml_row_size(dst->type, ne01), ggml_row_size(dst->type, ne01) ); } @@ -591,22 +721,26 @@ static bool ggml_backend_zendnn_device_supports_op(ggml_backend_dev_t dev, const if(K <= 256 || N <= 128 || M <= 96) { return false; } + + // MUL_MAT_ID's gather+matmul+scatter approach favors a moderate expert count + if (op->op == GGML_OP_MUL_MAT_ID) { + const int64_t n_experts = weights->ne[2]; + const int64_t max_experts = 32; + if (n_experts > max_experts) { + return false; + } + + // fall back once the average rows per expert (N / n_experts) is too thin + // to amortize each per-expert GEMM's overhead + if (N / n_experts <= 32) { + return false; + } + } } else if (ne0 < min_batch || ne1 < min_batch || ne10 < min_batch) { return false; } - // MUL_MAT_ID performs best with a moderate number of experts due to its - // gather + batched matmul + scatter approach. Future versions will leverage - // ZenDNN's grouped_gemm for better scalability with larger expert counts: - // https://github.com/amd/ZenDNN/blob/main/docs/operator/lowoha_group_gemm_operator.md - if (op->op == GGML_OP_MUL_MAT_ID) { - const int64_t n_experts = weights->ne[2]; - const int64_t max_experts = 32; - if (n_experts > max_experts) { - return false; - } - } switch (weights->type) { case GGML_TYPE_F32: case GGML_TYPE_BF16: diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py index 650f1c8a56a6..8516222cccbb 100644 --- a/gguf-py/gguf/constants.py +++ b/gguf-py/gguf/constants.py @@ -11,6 +11,7 @@ GGUF_VERSION = 3 GGUF_DEFAULT_ALIGNMENT = 32 GGML_QUANT_VERSION = 2 # GGML_QNT_VERSION from ggml.h +GGML_MAX_DIMS = 4 # GGML_MAX_DIMS from ggml.h # # metadata keys @@ -322,6 +323,7 @@ class Clip: PROJECTOR_TYPE = "clip.projector_type" HAS_VISION_ENCODER = "clip.has_vision_encoder" HAS_AUDIO_ENCODER = "clip.has_audio_encoder" + HAS_GEN_AUDIO_ENCODER = "clip.has_gen_audio_encoder" HAS_LLAVA_PROJECTOR = "clip.has_llava_projector" class ClipVision: @@ -353,6 +355,7 @@ class ClipVision: class Attention: HEAD_COUNT = "clip.vision.attention.head_count" HEAD_COUNT_KV = "clip.vision.attention.head_count_kv" # used by mimovl (GQA) + HEAD_DIM = "clip.vision.attention.head_dim" # set when qkv width != n_embd LAYERNORM_EPS = "clip.vision.attention.layer_norm_epsilon" class Projector: @@ -395,6 +398,18 @@ class Projector: DOWNSAMPLE_RATE = "clip.audio.projector.downsample_rate" HEAD_COUNT = "clip.audio.projector.head_count" + class ClipGenAudio: + PROJECTOR_TYPE = "clip.gen.audio.projector_type" # for mixed modality models + EMBEDDING_LENGTH = "clip.gen.audio.embedding_length" + FEED_FORWARD_LENGTH = "clip.gen.audio.feed_forward_length" + BLOCK_COUNT = "clip.gen.audio.block_count" + PROJECTION_DIM = "clip.gen.audio.projection_dim" + + class Attention: + HEAD_COUNT = "clip.gen.audio.attention.head_count" + HEAD_COUNT_KV = "clip.gen.audio.attention.head_count_kv" + LAYERNORM_EPS = "clip.gen.audio.attention.layer_norm_epsilon" + class Diffusion: SHIFT_LOGITS = "diffusion.shift_logits" @@ -556,6 +571,7 @@ class MODEL_ARCH(IntEnum): TALKIE = auto() MELLUM = auto() NANBEIGE = auto() + QWEN3TTS = auto() class VISION_PROJECTOR_TYPE(IntEnum): @@ -956,6 +972,65 @@ class MODEL_TENSOR(IntEnum): A_ENC_DOWNSAMPLE_CONV = auto() # mimo-audio-tokenizer: post-transformer downsample conv A_ENC_DOWNSAMPLE_NORM = auto() # mimo-audio-tokenizer: post-transformer downsample norm A_ENC_RVQ_CODEBOOK = auto() # mimo-audio-tokenizer: residual vector quantizer codebook, per quantizer index + A_ENC_CONV_RES2 = auto() # qwen3tts + A_ENC_SE_CONV1 = auto() # qwen3tts + A_ENC_SE_CONV2 = auto() # qwen3tts + A_ENC_ASP_ATTN = auto() # qwen3tts + A_ENC_ASP_TDNN = auto() # qwen3tts + # qwen3tts code_predictor: predicts the remaining RVQ codebooks + A_GEN_CODE_PROJ_IN = auto() # small_to_mtp_projection + A_GEN_CODE_EMBD = auto() # per-codebook embedding table, merged 3D [n_codebooks, vocab, dim] + A_GEN_CODE_HEAD = auto() # per-codebook output head, merged 3D [n_codebooks, vocab, dim] + A_GEN_CODE_OUT_EMBD = auto() # codebook-0 embedding, re-fed into the talker backbone (talker.model.codec_embedding) + A_GEN_CODE_ATTN_NORM = auto() + A_GEN_CODE_ATTN_Q = auto() + A_GEN_CODE_ATTN_Q_NORM = auto() + A_GEN_CODE_ATTN_K = auto() + A_GEN_CODE_ATTN_K_NORM = auto() + A_GEN_CODE_ATTN_V = auto() + A_GEN_CODE_ATTN_OUT = auto() + A_GEN_CODE_FFN_NORM = auto() + A_GEN_CODE_FFN_GATE = auto() + A_GEN_CODE_FFN_UP = auto() + A_GEN_CODE_FFN_DOWN = auto() + A_GEN_CODE_OUTPUT_NORM = auto() + # qwen3tts code2wav: RVQ codes -> raw PCM + A_GEN_WAV_QUANT_FIRST_IN = auto() # semantic RVQ, in_proj (1x1 conv, loaded as 2D) + A_GEN_WAV_QUANT_FIRST_OUT = auto() # semantic RVQ, out_proj + A_GEN_WAV_QUANT_FIRST_CB = auto() # semantic RVQ codebook (1 layer), folded from embedding_sum/cluster_usage + A_GEN_WAV_QUANT_REST_IN = auto() # acoustic RVQ, in_proj + A_GEN_WAV_QUANT_REST_OUT = auto() # acoustic RVQ, out_proj + A_GEN_WAV_QUANT_REST_CB = auto() # acoustic RVQ codebooks, merged 3D [15, vocab, dim] + A_GEN_WAV_PRE_CONV = auto() + A_GEN_WAV_TFM_IN_PROJ = auto() + A_GEN_WAV_TFM_OUT_PROJ = auto() + A_GEN_WAV_TFM_OUTPUT_NORM = auto() + A_GEN_WAV_TFM_ATTN_NORM = auto() + A_GEN_WAV_TFM_ATTN_Q = auto() + A_GEN_WAV_TFM_ATTN_K = auto() + A_GEN_WAV_TFM_ATTN_V = auto() + A_GEN_WAV_TFM_ATTN_OUT = auto() + A_GEN_WAV_TFM_ATTN_SCALE = auto() # layer scale (gamma) on the attn output + A_GEN_WAV_TFM_FFN_NORM = auto() + A_GEN_WAV_TFM_FFN_GATE = auto() + A_GEN_WAV_TFM_FFN_UP = auto() + A_GEN_WAV_TFM_FFN_DOWN = auto() + A_GEN_WAV_TFM_FFN_SCALE = auto() # layer scale (gamma) on the FFN output + A_GEN_WAV_UP_CONV = auto() # causal ConvTranspose1d, 2x upsample + A_GEN_WAV_UP_DWCONV = auto() # ConvNeXt depthwise conv + A_GEN_WAV_UP_NORM = auto() # ConvNeXt LayerNorm + A_GEN_WAV_UP_PW1 = auto() # ConvNeXt pointwise conv 1 (expand) + A_GEN_WAV_UP_PW2 = auto() # ConvNeXt pointwise conv 2 (project) + A_GEN_WAV_UP_GAMMA = auto() # ConvNeXt layer scale + A_GEN_WAV_DAC_ENTRY = auto() # DAC conv_pre + A_GEN_WAV_DAC_UP_SNAKE = auto() # DAC per-block SnakeBeta before the upsample conv + A_GEN_WAV_DAC_UP_CONV = auto() # DAC per-block causal ConvTranspose1d + A_GEN_WAV_DAC_RES_ACT1 = auto() # DAC residual unit, SnakeBeta before conv1 + A_GEN_WAV_DAC_RES_CONV1 = auto() # DAC residual unit, dilated causal conv + A_GEN_WAV_DAC_RES_ACT2 = auto() # DAC residual unit, SnakeBeta before conv2 + A_GEN_WAV_DAC_RES_CONV2 = auto() # DAC residual unit, pointwise causal conv + A_GEN_WAV_DAC_POST_SNAKE = auto() # DAC final SnakeBeta + A_GEN_WAV_DAC_POST_CONV = auto() # DAC conv_post -> 1-channel PCM A_MMPROJ = auto() A_MMPROJ_FC = auto() A_MM_NORM_PRE = auto() @@ -1168,6 +1243,7 @@ class MODEL_TENSOR(IntEnum): MODEL_ARCH.TALKIE: "talkie", MODEL_ARCH.MELLUM: "mellum", MODEL_ARCH.NANBEIGE: "nanbeige", + MODEL_ARCH.QWEN3TTS: "qwen3tts", } VISION_PROJECTOR_TYPE_NAMES: dict[VISION_PROJECTOR_TYPE, str] = { @@ -1565,6 +1641,63 @@ class MODEL_TENSOR(IntEnum): MODEL_TENSOR.A_ENC_DOWNSAMPLE_CONV: "a.downsample.conv", MODEL_TENSOR.A_ENC_DOWNSAMPLE_NORM: "a.downsample.norm", MODEL_TENSOR.A_ENC_RVQ_CODEBOOK: "a.rvq.codebook", + MODEL_TENSOR.A_ENC_CONV_RES2: "a.blk.{bid}.res2.{xid}", + MODEL_TENSOR.A_ENC_SE_CONV1: "a.blk.{bid}.se_conv1", + MODEL_TENSOR.A_ENC_SE_CONV2: "a.blk.{bid}.se_conv2", + MODEL_TENSOR.A_ENC_ASP_ATTN: "a.asp_attn", + MODEL_TENSOR.A_ENC_ASP_TDNN: "a.asp_tdnn", + MODEL_TENSOR.A_GEN_CODE_PROJ_IN: "a.gen.code.proj_in", + MODEL_TENSOR.A_GEN_CODE_EMBD: "a.gen.code.embd", + MODEL_TENSOR.A_GEN_CODE_HEAD: "a.gen.code.head", + MODEL_TENSOR.A_GEN_CODE_OUT_EMBD: "a.gen.code.out_embd", + MODEL_TENSOR.A_GEN_CODE_ATTN_NORM: "a.gen.code.blk.{bid}.ln1", # reuses the generic clip.cpp block loader (TN_LN_1) + MODEL_TENSOR.A_GEN_CODE_ATTN_Q: "a.gen.code.blk.{bid}.attn_q", + MODEL_TENSOR.A_GEN_CODE_ATTN_Q_NORM: "a.gen.code.blk.{bid}.attn_q_norm", + MODEL_TENSOR.A_GEN_CODE_ATTN_K: "a.gen.code.blk.{bid}.attn_k", + MODEL_TENSOR.A_GEN_CODE_ATTN_K_NORM: "a.gen.code.blk.{bid}.attn_k_norm", + MODEL_TENSOR.A_GEN_CODE_ATTN_V: "a.gen.code.blk.{bid}.attn_v", + MODEL_TENSOR.A_GEN_CODE_ATTN_OUT: "a.gen.code.blk.{bid}.attn_out", + MODEL_TENSOR.A_GEN_CODE_FFN_NORM: "a.gen.code.blk.{bid}.ln2", # reuses the generic clip.cpp block loader (TN_LN_2) + MODEL_TENSOR.A_GEN_CODE_FFN_GATE: "a.gen.code.blk.{bid}.ffn_gate", + MODEL_TENSOR.A_GEN_CODE_FFN_UP: "a.gen.code.blk.{bid}.ffn_up", + MODEL_TENSOR.A_GEN_CODE_FFN_DOWN: "a.gen.code.blk.{bid}.ffn_down", + MODEL_TENSOR.A_GEN_CODE_OUTPUT_NORM: "a.gen.code.output_norm", + MODEL_TENSOR.A_GEN_WAV_QUANT_FIRST_IN: "a.gen.wav.quant.first.in_proj", + MODEL_TENSOR.A_GEN_WAV_QUANT_FIRST_OUT: "a.gen.wav.quant.first.out_proj", + MODEL_TENSOR.A_GEN_WAV_QUANT_FIRST_CB: "a.gen.wav.quant.first.codebook", + MODEL_TENSOR.A_GEN_WAV_QUANT_REST_IN: "a.gen.wav.quant.rest.in_proj", + MODEL_TENSOR.A_GEN_WAV_QUANT_REST_OUT: "a.gen.wav.quant.rest.out_proj", + MODEL_TENSOR.A_GEN_WAV_QUANT_REST_CB: "a.gen.wav.quant.rest.codebook", + MODEL_TENSOR.A_GEN_WAV_PRE_CONV: "a.gen.wav.pre_conv", + MODEL_TENSOR.A_GEN_WAV_TFM_IN_PROJ: "a.gen.wav.tfm.in_proj", + MODEL_TENSOR.A_GEN_WAV_TFM_OUT_PROJ: "a.gen.wav.tfm.out_proj", + MODEL_TENSOR.A_GEN_WAV_TFM_OUTPUT_NORM: "a.gen.wav.tfm.output_norm", + MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_NORM: "a.gen.wav.tfm.blk.{bid}.ln1", + MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_Q: "a.gen.wav.tfm.blk.{bid}.attn_q", + MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_K: "a.gen.wav.tfm.blk.{bid}.attn_k", + MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_V: "a.gen.wav.tfm.blk.{bid}.attn_v", + MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_OUT: "a.gen.wav.tfm.blk.{bid}.attn_out", + MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_SCALE: "a.gen.wav.tfm.blk.{bid}.ls1", + MODEL_TENSOR.A_GEN_WAV_TFM_FFN_NORM: "a.gen.wav.tfm.blk.{bid}.ln2", + MODEL_TENSOR.A_GEN_WAV_TFM_FFN_GATE: "a.gen.wav.tfm.blk.{bid}.ffn_gate", + MODEL_TENSOR.A_GEN_WAV_TFM_FFN_UP: "a.gen.wav.tfm.blk.{bid}.ffn_up", + MODEL_TENSOR.A_GEN_WAV_TFM_FFN_DOWN: "a.gen.wav.tfm.blk.{bid}.ffn_down", + MODEL_TENSOR.A_GEN_WAV_TFM_FFN_SCALE: "a.gen.wav.tfm.blk.{bid}.ls2", + MODEL_TENSOR.A_GEN_WAV_UP_CONV: "a.gen.wav.up.blk.{bid}.conv", + MODEL_TENSOR.A_GEN_WAV_UP_DWCONV: "a.gen.wav.up.blk.{bid}.dwconv", + MODEL_TENSOR.A_GEN_WAV_UP_NORM: "a.gen.wav.up.blk.{bid}.norm", + MODEL_TENSOR.A_GEN_WAV_UP_PW1: "a.gen.wav.up.blk.{bid}.pw1", + MODEL_TENSOR.A_GEN_WAV_UP_PW2: "a.gen.wav.up.blk.{bid}.pw2", + MODEL_TENSOR.A_GEN_WAV_UP_GAMMA: "a.gen.wav.up.blk.{bid}.gamma", + MODEL_TENSOR.A_GEN_WAV_DAC_ENTRY: "a.gen.wav.dac.entry", + MODEL_TENSOR.A_GEN_WAV_DAC_UP_SNAKE: "a.gen.wav.dac.blk.{bid}.snake", + MODEL_TENSOR.A_GEN_WAV_DAC_UP_CONV: "a.gen.wav.dac.blk.{bid}.conv", + MODEL_TENSOR.A_GEN_WAV_DAC_RES_ACT1: "a.gen.wav.dac.blk.{bid}.res.{xid}.act1", + MODEL_TENSOR.A_GEN_WAV_DAC_RES_CONV1: "a.gen.wav.dac.blk.{bid}.res.{xid}.conv1", + MODEL_TENSOR.A_GEN_WAV_DAC_RES_ACT2: "a.gen.wav.dac.blk.{bid}.res.{xid}.act2", + MODEL_TENSOR.A_GEN_WAV_DAC_RES_CONV2: "a.gen.wav.dac.blk.{bid}.res.{xid}.conv2", + MODEL_TENSOR.A_GEN_WAV_DAC_POST_SNAKE: "a.gen.wav.dac.post_snake", + MODEL_TENSOR.A_GEN_WAV_DAC_POST_CONV: "a.gen.wav.dac.post_conv", MODEL_TENSOR.A_MMPROJ: "mm.a.mlp.{bid}", MODEL_TENSOR.A_MMPROJ_FC: "mm.a.fc", MODEL_TENSOR.A_MM_NORM_PRE: "mm.a.norm_pre", @@ -1819,6 +1952,63 @@ class MODEL_TENSOR(IntEnum): MODEL_TENSOR.A_ENC_CONV_NORM, MODEL_TENSOR.A_ENC_CONV_PW1, MODEL_TENSOR.A_ENC_CONV_PW2, + MODEL_TENSOR.A_ENC_CONV_RES2, + MODEL_TENSOR.A_ENC_SE_CONV1, + MODEL_TENSOR.A_ENC_SE_CONV2, + MODEL_TENSOR.A_ENC_ASP_ATTN, + MODEL_TENSOR.A_ENC_ASP_TDNN, + MODEL_TENSOR.A_GEN_CODE_PROJ_IN, + MODEL_TENSOR.A_GEN_CODE_EMBD, + MODEL_TENSOR.A_GEN_CODE_HEAD, + MODEL_TENSOR.A_GEN_CODE_OUT_EMBD, + MODEL_TENSOR.A_GEN_CODE_ATTN_NORM, + MODEL_TENSOR.A_GEN_CODE_ATTN_Q, + MODEL_TENSOR.A_GEN_CODE_ATTN_Q_NORM, + MODEL_TENSOR.A_GEN_CODE_ATTN_K, + MODEL_TENSOR.A_GEN_CODE_ATTN_K_NORM, + MODEL_TENSOR.A_GEN_CODE_ATTN_V, + MODEL_TENSOR.A_GEN_CODE_ATTN_OUT, + MODEL_TENSOR.A_GEN_CODE_FFN_NORM, + MODEL_TENSOR.A_GEN_CODE_FFN_GATE, + MODEL_TENSOR.A_GEN_CODE_FFN_UP, + MODEL_TENSOR.A_GEN_CODE_FFN_DOWN, + MODEL_TENSOR.A_GEN_CODE_OUTPUT_NORM, + MODEL_TENSOR.A_GEN_WAV_QUANT_FIRST_IN, + MODEL_TENSOR.A_GEN_WAV_QUANT_FIRST_OUT, + MODEL_TENSOR.A_GEN_WAV_QUANT_FIRST_CB, + MODEL_TENSOR.A_GEN_WAV_QUANT_REST_IN, + MODEL_TENSOR.A_GEN_WAV_QUANT_REST_OUT, + MODEL_TENSOR.A_GEN_WAV_QUANT_REST_CB, + MODEL_TENSOR.A_GEN_WAV_PRE_CONV, + MODEL_TENSOR.A_GEN_WAV_TFM_IN_PROJ, + MODEL_TENSOR.A_GEN_WAV_TFM_OUT_PROJ, + MODEL_TENSOR.A_GEN_WAV_TFM_OUTPUT_NORM, + MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_NORM, + MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_Q, + MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_K, + MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_V, + MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_OUT, + MODEL_TENSOR.A_GEN_WAV_TFM_ATTN_SCALE, + MODEL_TENSOR.A_GEN_WAV_TFM_FFN_NORM, + MODEL_TENSOR.A_GEN_WAV_TFM_FFN_GATE, + MODEL_TENSOR.A_GEN_WAV_TFM_FFN_UP, + MODEL_TENSOR.A_GEN_WAV_TFM_FFN_DOWN, + MODEL_TENSOR.A_GEN_WAV_TFM_FFN_SCALE, + MODEL_TENSOR.A_GEN_WAV_UP_CONV, + MODEL_TENSOR.A_GEN_WAV_UP_DWCONV, + MODEL_TENSOR.A_GEN_WAV_UP_NORM, + MODEL_TENSOR.A_GEN_WAV_UP_PW1, + MODEL_TENSOR.A_GEN_WAV_UP_PW2, + MODEL_TENSOR.A_GEN_WAV_UP_GAMMA, + MODEL_TENSOR.A_GEN_WAV_DAC_ENTRY, + MODEL_TENSOR.A_GEN_WAV_DAC_UP_SNAKE, + MODEL_TENSOR.A_GEN_WAV_DAC_UP_CONV, + MODEL_TENSOR.A_GEN_WAV_DAC_RES_ACT1, + MODEL_TENSOR.A_GEN_WAV_DAC_RES_CONV1, + MODEL_TENSOR.A_GEN_WAV_DAC_RES_ACT2, + MODEL_TENSOR.A_GEN_WAV_DAC_RES_CONV2, + MODEL_TENSOR.A_GEN_WAV_DAC_POST_SNAKE, + MODEL_TENSOR.A_GEN_WAV_DAC_POST_CONV, MODEL_TENSOR.A_ENC_CONV_NORM_MEAN, MODEL_TENSOR.A_ENC_CONV_NORM_VAR, MODEL_TENSOR.A_ENC_MEL_FILTERS, @@ -2328,7 +2518,13 @@ class MODEL_TENSOR(IntEnum): MODEL_TENSOR.SSM_NORM, MODEL_TENSOR.SSM_IN, MODEL_TENSOR.SSM_BETA_ALPHA, - MODEL_TENSOR.SSM_OUT + MODEL_TENSOR.SSM_OUT, + MODEL_TENSOR.NEXTN_EH_PROJ, + MODEL_TENSOR.NEXTN_EMBED_TOKENS, + MODEL_TENSOR.NEXTN_ENORM, + MODEL_TENSOR.NEXTN_HNORM, + MODEL_TENSOR.NEXTN_SHARED_HEAD_HEAD, + MODEL_TENSOR.NEXTN_SHARED_HEAD_NORM, ], MODEL_ARCH.QWEN3VL: [ MODEL_TENSOR.TOKEN_EMBD, @@ -3214,6 +3410,13 @@ class MODEL_TENSOR(IntEnum): MODEL_TENSOR.FFN_DOWN_SHEXP, MODEL_TENSOR.FFN_UP_SHEXP, MODEL_TENSOR.FFN_EXP_PROBS_B, + # NextN/MTP tensors + MODEL_TENSOR.NEXTN_EH_PROJ, + MODEL_TENSOR.NEXTN_EMBED_TOKENS, + MODEL_TENSOR.NEXTN_ENORM, + MODEL_TENSOR.NEXTN_HNORM, + MODEL_TENSOR.NEXTN_SHARED_HEAD_HEAD, + MODEL_TENSOR.NEXTN_SHARED_HEAD_NORM, ], MODEL_ARCH.DEEPSEEK2OCR: [ MODEL_TENSOR.TOKEN_EMBD, @@ -3330,6 +3533,12 @@ class MODEL_TENSOR(IntEnum): MODEL_TENSOR.FFN_GATE_SHEXP, MODEL_TENSOR.FFN_DOWN_SHEXP, MODEL_TENSOR.FFN_UP_SHEXP, + MODEL_TENSOR.NEXTN_EH_PROJ, + MODEL_TENSOR.NEXTN_EMBED_TOKENS, + MODEL_TENSOR.NEXTN_ENORM, + MODEL_TENSOR.NEXTN_HNORM, + MODEL_TENSOR.NEXTN_SHARED_HEAD_HEAD, + MODEL_TENSOR.NEXTN_SHARED_HEAD_NORM, ], MODEL_ARCH.ERNIE4_5_MOE: [ MODEL_TENSOR.TOKEN_EMBD, @@ -4376,10 +4585,35 @@ class MODEL_TENSOR(IntEnum): MODEL_TENSOR.ATTN_OUT, MODEL_TENSOR.ATTN_Q_NORM, MODEL_TENSOR.ATTN_K_NORM, + MODEL_TENSOR.ATTN_SINKS, + MODEL_TENSOR.ATTN_Q_A, + MODEL_TENSOR.ATTN_Q_B, + MODEL_TENSOR.ATTN_Q_A_NORM, + MODEL_TENSOR.ATTN_KV, + MODEL_TENSOR.ATTN_KV_NORM, + MODEL_TENSOR.ATTN_OUT_A, + MODEL_TENSOR.ATTN_OUT_B, + MODEL_TENSOR.HC_ATTN_FN, + MODEL_TENSOR.HC_ATTN_BASE, + MODEL_TENSOR.HC_ATTN_SCALE, + MODEL_TENSOR.HC_FFN_FN, + MODEL_TENSOR.HC_FFN_BASE, + MODEL_TENSOR.HC_FFN_SCALE, + MODEL_TENSOR.HC_HEAD_FN, + MODEL_TENSOR.HC_HEAD_BASE, + MODEL_TENSOR.HC_HEAD_SCALE, MODEL_TENSOR.FFN_NORM, MODEL_TENSOR.FFN_GATE, MODEL_TENSOR.FFN_DOWN, MODEL_TENSOR.FFN_UP, + MODEL_TENSOR.FFN_GATE_INP, + MODEL_TENSOR.FFN_EXP_PROBS_B, + MODEL_TENSOR.FFN_GATE_EXP, + MODEL_TENSOR.FFN_DOWN_EXP, + MODEL_TENSOR.FFN_UP_EXP, + MODEL_TENSOR.FFN_GATE_SHEXP, + MODEL_TENSOR.FFN_DOWN_SHEXP, + MODEL_TENSOR.FFN_UP_SHEXP, MODEL_TENSOR.FC, MODEL_TENSOR.ENC_OUTPUT_NORM, # optional DSpark heads @@ -4602,6 +4836,22 @@ class MODEL_TENSOR(IntEnum): MODEL_TENSOR.FFN_DOWN, MODEL_TENSOR.FFN_UP, ], + MODEL_ARCH.QWEN3TTS: [ + MODEL_TENSOR.TOKEN_EMBD, + MODEL_TENSOR.OUTPUT_NORM, + MODEL_TENSOR.OUTPUT, + MODEL_TENSOR.ATTN_NORM, + MODEL_TENSOR.ATTN_Q, + MODEL_TENSOR.ATTN_Q_NORM, + MODEL_TENSOR.ATTN_K, + MODEL_TENSOR.ATTN_K_NORM, + MODEL_TENSOR.ATTN_V, + MODEL_TENSOR.ATTN_OUT, + MODEL_TENSOR.FFN_NORM, + MODEL_TENSOR.FFN_GATE, + MODEL_TENSOR.FFN_DOWN, + MODEL_TENSOR.FFN_UP, + ], } # tensors that will not be serialized @@ -4876,6 +5126,8 @@ class VisionProjectorType: GLM4V = "glm4v" YOUTUVL = "youtuvl" NEMOTRON_V2_VL = "nemotron_v2_vl" + QWEN3TTS_SPKENC = "qwen3tts_spkenc" # audio: ECAPA-TDNN speaker encoder + QWEN3TTS_GEN = "qwen3tts_gen" # audio generation: code_predictor HUNYUANVL = "hunyuanvl" PARAKEET = "parakeet" # audio MINIMAXM3 = "minimax_m3" diff --git a/gguf-py/gguf/gguf_reader.py b/gguf-py/gguf/gguf_reader.py index 0a1b85f50641..ea241ada285c 100644 --- a/gguf-py/gguf/gguf_reader.py +++ b/gguf-py/gguf/gguf_reader.py @@ -22,6 +22,7 @@ sys.path.insert(0, str(Path(__file__).parent.parent)) from gguf.constants import ( + GGML_MAX_DIMS, GGML_QUANT_SIZES, GGUF_DEFAULT_ALIGNMENT, GGUF_MAGIC, @@ -266,6 +267,8 @@ def _get_tensor_info_field(self, orig_offs: int) -> ReaderField: # Get Tensor Dimensions Count n_dims = self._get(offs, np.uint32) offs += int(n_dims.nbytes) + if n_dims[0] > GGML_MAX_DIMS: + raise ValueError(f'Tensor dimensions count {n_dims[0]} exceeds GGML_MAX_DIMS ({GGML_MAX_DIMS})') # Get Tensor Dimension Array dims = self._get(offs, np.uint64, n_dims[0]) @@ -326,7 +329,10 @@ def _build_tensors(self, start_offs: int, fields: list[ReaderField]) -> None: raise ValueError(f'Found duplicated tensor with name {tensor_name}') tensor_names.add(tensor_name) ggml_type = GGMLQuantizationType(raw_dtype[0]) - n_elems = int(np.prod(dims)) + # use Python ints: np.prod on uint64 wraps silently on overflow + n_elems = 1 + for dim in dims.tolist(): + n_elems *= int(dim) np_dims = tuple(reversed(dims.tolist())) block_size, type_size = GGML_QUANT_SIZES[ggml_type] n_bytes = n_elems * type_size // block_size diff --git a/gguf-py/gguf/gguf_writer.py b/gguf-py/gguf/gguf_writer.py index 3aa4f049f2bb..39da9f2c05fb 100644 --- a/gguf-py/gguf/gguf_writer.py +++ b/gguf-py/gguf/gguf_writer.py @@ -280,6 +280,10 @@ def add_key_value(self, key: str, val: Any, vtype: GGUFValueType, sub_type: GGUF self.kv_data[0][key] = GGUFValue(value=val, type=vtype, sub_type=sub_type) + def remove_key(self, key: str) -> None: + for kv_data in self.kv_data: + kv_data.pop(key, None) + def add_uint8(self, key: str, val: int) -> None: self.add_key_value(key,val, GGUFValueType.UINT8) @@ -1144,7 +1148,11 @@ def add_remove_extra_whitespaces(self, value: bool) -> None: def add_precompiled_charsmap(self, charsmap: bytes) -> None: self.add_array(Keys.Tokenizer.PRECOMPILED_CHARSMAP, charsmap) - def add_chat_template(self, value: str | Sequence[Mapping[str, str]]) -> None: + def add_chat_template(self, value: str | Sequence[Mapping[str, str]] | None) -> None: + if value is None: + self.remove_key(Keys.Tokenizer.CHAT_TEMPLATE) + return + if not isinstance(value, str): template_default = None template_names = set() @@ -1199,6 +1207,9 @@ def add_clip_has_vision_encoder(self, value: bool) -> None: def add_clip_has_audio_encoder(self, value: bool) -> None: self.add_bool(Keys.Clip.HAS_AUDIO_ENCODER, value) + def add_clip_has_gen_audio_encoder(self, value: bool) -> None: + self.add_bool(Keys.Clip.HAS_GEN_AUDIO_ENCODER, value) + def add_clip_projector_type(self, value: str) -> None: self.add_string(Keys.Clip.PROJECTOR_TYPE, value) @@ -1226,6 +1237,9 @@ def add_vision_head_count(self, value: int) -> None: def add_vision_head_count_kv(self, value: int) -> None: self.add_uint32(Keys.ClipVision.Attention.HEAD_COUNT_KV, value) + def add_vision_head_dim(self, value: int) -> None: + self.add_uint32(Keys.ClipVision.Attention.HEAD_DIM, value) + def add_vision_attention_layernorm_eps(self, value: float) -> None: self.add_float32(Keys.ClipVision.Attention.LAYERNORM_EPS, value) @@ -1398,6 +1412,32 @@ def add_audio_projector_downsample_rate(self, value: int) -> None: def add_audio_projector_head_count(self, value: int) -> None: self.add_uint32(Keys.ClipAudio.Projector.HEAD_COUNT, value) + # audio generation (mmproj) + + def add_clip_gen_audio_projector_type(self, value: str) -> None: + self.add_string(Keys.ClipGenAudio.PROJECTOR_TYPE, value) + + def add_gen_audio_projection_dim(self, value: int) -> None: + self.add_uint32(Keys.ClipGenAudio.PROJECTION_DIM, value) + + def add_gen_audio_embedding_length(self, value: int) -> None: + self.add_uint32(Keys.ClipGenAudio.EMBEDDING_LENGTH, value) + + def add_gen_audio_feed_forward_length(self, value: int) -> None: + self.add_uint32(Keys.ClipGenAudio.FEED_FORWARD_LENGTH, value) + + def add_gen_audio_block_count(self, value: int) -> None: + self.add_uint32(Keys.ClipGenAudio.BLOCK_COUNT, value) + + def add_gen_audio_head_count(self, value: int) -> None: + self.add_uint32(Keys.ClipGenAudio.Attention.HEAD_COUNT, value) + + def add_gen_audio_head_count_kv(self, value: int) -> None: + self.add_uint32(Keys.ClipGenAudio.Attention.HEAD_COUNT_KV, value) + + def add_gen_audio_attention_layernorm_eps(self, value: float) -> None: + self.add_float32(Keys.ClipGenAudio.Attention.LAYERNORM_EPS, value) + def add_xielu_alpha_p(self, values: Sequence[float]): self.add_array(Keys.xIELU.ALPHA_P, values) diff --git a/gguf-py/gguf/tensor_mapping.py b/gguf-py/gguf/tensor_mapping.py index 1e991b873cea..7892342e473d 100644 --- a/gguf-py/gguf/tensor_mapping.py +++ b/gguf-py/gguf/tensor_mapping.py @@ -2109,6 +2109,7 @@ class TensorNameMap: "conformer.subsample_conv_projection.layer{bid}.conv", # gemma4 "sound_encoder.encoder.subsampling.layers.{bid}", # parakeet "encoder.conv{bid}", # mimo-audio-tokenizer + "speaker_encoder.blocks.{bid}.conv", # qwen3tts speaker encoder (only bid=0, the stem TDNN) ), MODEL_TENSOR.A_ENC_CONV1D_NORM: ( @@ -2126,6 +2127,7 @@ class TensorNameMap: MODEL_TENSOR.A_ENC_CONV_OUT: ( "audio_tower.conv_out", # qwen3omni + "speaker_encoder.mfa.conv", # qwen3tts speaker encoder: multi-layer feature aggregation ), MODEL_TENSOR.A_PRE_NORM: (), @@ -2336,7 +2338,8 @@ class TensorNameMap: MODEL_TENSOR.A_MMPROJ_FC: ( "audio.multi_modal_projector.linear", # qwen2audio "audio_tower.proj", # qwen2omni - "model.audio_tower.output_proj" # gemma4 + "model.audio_tower.output_proj", # gemma4 + "speaker_encoder.fc", # qwen3tts speaker encoder: final speaker embedding projection ), MODEL_TENSOR.A_MM_NORM_PRE: ( @@ -2411,6 +2414,7 @@ class TensorNameMap: "conformer.layers.{bid}.lconv1d.linear_start", # gemma3n "sound_encoder.encoder.layers.{bid}.conv.pointwise_conv1", # parakeet "encoder.layers.{bid}.conv.up_conv", # granite_speech + "speaker_encoder.blocks.{bid}.tdnn1.conv", # qwen3tts speaker encoder ), MODEL_TENSOR.A_ENC_CONV_PW2: ( @@ -2418,6 +2422,23 @@ class TensorNameMap: "conformer.layers.{bid}.lconv1d.linear_end", # gemma3n "sound_encoder.encoder.layers.{bid}.conv.pointwise_conv2", # parakeet "encoder.layers.{bid}.conv.down_conv", # granite_speech + "speaker_encoder.blocks.{bid}.tdnn2.conv", # qwen3tts speaker encoder + ), + + MODEL_TENSOR.A_ENC_SE_CONV1: ( + "speaker_encoder.blocks.{bid}.se_block.conv1", # qwen3tts + ), + + MODEL_TENSOR.A_ENC_SE_CONV2: ( + "speaker_encoder.blocks.{bid}.se_block.conv2", # qwen3tts + ), + + MODEL_TENSOR.A_ENC_ASP_ATTN: ( + "speaker_encoder.asp.conv", # qwen3tts + ), + + MODEL_TENSOR.A_ENC_ASP_TDNN: ( + "speaker_encoder.asp.tdnn.conv", # qwen3tts ), MODEL_TENSOR.A_ENC_NORM_CONV: ( diff --git a/gguf-py/tests/test_gguf_reader_validation.py b/gguf-py/tests/test_gguf_reader_validation.py new file mode 100644 index 000000000000..98f30a969608 --- /dev/null +++ b/gguf-py/tests/test_gguf_reader_validation.py @@ -0,0 +1,37 @@ +import struct +import numpy as np +import pytest + +from gguf.gguf_reader import GGUFReader + + +def _write_gguf(path, n_dims_field, dims): + buf = b'GGUF' + struct.pack(' 0.0, 1.0 = disabled + float penalty_freq, // must be finite, 0.0 = disabled + float penalty_present); // must be finite, 0.0 = disabled /// @details DRY sampler, designed by p-e-w, as described in: https://github.com/oobabooga/text-generation-webui/pull/5677, porting Koboldcpp implementation authored by pi6am: https://github.com/LostRuins/koboldcpp/pull/982 LLAMA_API struct llama_sampler * llama_sampler_init_dry( const struct llama_vocab * vocab, - int32_t n_ctx_train, float dry_multiplier, float dry_base, int32_t dry_allowed_length, - int32_t dry_penalty_last_n, + int32_t dry_penalty_last_n, // last n tokens to penalize (0 = disable penalty) const char ** seq_breakers, size_t num_breakers); diff --git a/models/templates/deepseek-ai-DeepSeek-V4-Flash-0731.jinja b/models/templates/deepseek-ai-DeepSeek-V4-Flash-0731.jinja new file mode 100644 index 000000000000..ab689a57c9cf --- /dev/null +++ b/models/templates/deepseek-ai-DeepSeek-V4-Flash-0731.jinja @@ -0,0 +1,140 @@ +{%- if not add_generation_prompt is defined -%} + {%- set add_generation_prompt = false -%} +{%- endif -%} +{%- if not thinking is defined -%} + {%- if enable_thinking is defined -%} + {%- set thinking = enable_thinking -%} + {%- else -%} + {%- set thinking = false -%} + {%- endif -%} +{%- endif -%} +{%- if not drop_thinking is defined -%} + {%- set drop_thinking = true -%} +{%- endif -%} +{%- set dsml_token = '｜DSML｜' -%} +{%- set thinking_start_token = '' -%} +{%- set thinking_end_token = '' -%} +{%- set reasoning_effort_high = 'Reasoning Effort: Absolute maximum with no shortcuts permitted.\nYou MUST be very thorough in your thinking and comprehensively decompose the problem to resolve the root cause, rigorously stress-testing your logic against all potential paths, edge cases, and adversarial scenarios.\nExplicitly write out your entire deliberation process, documenting every intermediate step, considered alternative, and rejected hypothesis to ensure absolutely no assumption is left unchecked.\n\n' -%} +{%- set reasoning_effort_max = 'Reasoning Effort: Beyond maximum — exhaustive, relentless, and uncompromising.\nYou MUST reason with the utmost depth and rigor, leaving absolutely nothing to chance: exhaustively decompose the problem into its most fundamental components, trace every causal chain to its root, and resolve the underlying cause rather than any surface symptom.\nDo not stop reasoning until you have independently verified the solution from multiple angles and are certain that no assumption remains unchecked and no error remains undiscovered.\n\n' -%} +{%- set response_format_template = '## Response Format:\n\nYou MUST strictly adhere to the following schema to reply:\n' -%} +{%- set has_tools = false -%} +{%- set tools_header = '## Tools\n\nYou have access to a set of tools to help answer the user\'s question. You can invoke tools by writing a "<' + dsml_token + 'tool_calls>" block like the following:\n\n<' + dsml_token + 'tool_calls>\n<' + dsml_token + 'invoke name="$TOOL_NAME">\n<' + dsml_token + 'parameter name="$PARAMETER_NAME" string="true|false">$PARAMETER_VALUE\n...\n\n<' + dsml_token + 'invoke name="$TOOL_NAME2">\n...\n\n\n\nString parameters should be specified as is and set `string="true"`. For all other types (numbers, booleans, arrays, objects), pass the value in JSON format and set `string="false"`.\n\nIf thinking_mode is enabled (triggered by ' + thinking_start_token + '), you MUST output your complete reasoning inside ' + thinking_start_token + '...' + thinking_end_token + ' BEFORE any tool calls or final response.\n\nOtherwise, output directly after ' + thinking_end_token + ' with tool calls or final response.\n\n### Available Tool Schemas\n\n' -%} +{%- set tools_footer = '\nYou MUST strictly follow the above defined tool name and parameter schemas to invoke tool calls.\n' -%} +{%- set ns = namespace(system_prompt='', is_first_sp=true, has_tool_calls=false) -%} +{%- for message in messages -%} + {%- if message['role'] == 'system' -%} + {%- if ns.is_first_sp -%} + {%- set ns.system_prompt = ns.system_prompt + (message['content'] or '') -%} + {%- set ns.is_first_sp = false -%} + {%- else -%} + {%- set ns.system_prompt = ns.system_prompt + '\n\n' + (message['content'] or '') -%} + {%- endif -%} + {%- endif -%} +{%- endfor -%} +{%- if tools is defined and tools -%} + {%- set has_tools = true -%} + {%- set ts = namespace(schemas='') -%} + {%- for tool in tools -%} + {%- if tool['type'] == 'function' -%} + {%- set ts.schemas = ts.schemas + (tool['function'] | tojson) + '\n' -%} + {%- endif -%} + {%- endfor -%} + {%- if ns.system_prompt -%} + {%- set ns.system_prompt = ns.system_prompt + '\n\n' + tools_header + ts.schemas + tools_footer -%} + {%- else -%} + {%- set ns.system_prompt = tools_header + ts.schemas + tools_footer -%} + {%- endif -%} +{%- endif -%} +{%- if response_format is defined -%} + {%- if ns.system_prompt -%} + {%- set ns.system_prompt = ns.system_prompt + '\n\n' -%} + {%- endif -%} + {%- set ns.system_prompt = ns.system_prompt + response_format_template + (response_format | tojson) -%} +{%- endif -%} +{{- bos_token -}} +{%- if messages and thinking and reasoning_effort is defined and reasoning_effort == 'high' -%} + {{- reasoning_effort_high -}} +{%- elif messages and thinking and reasoning_effort is defined and reasoning_effort == 'max' -%} + {{- reasoning_effort_max -}} +{%- endif -%} +{{- ns.system_prompt -}} +{%- set last_user_idx = namespace(value=-1) -%} +{%- for message in messages -%} + {%- if message['role'] == 'user' or message['role'] == 'developer' or message['role'] == 'tool' -%} + {%- set last_user_idx.value = loop.index0 -%} + {%- endif -%} +{%- endfor -%} +{%- set state = namespace(in_user=false) -%} +{%- for message in messages -%} + {%- if message['role'] == 'tool' -%} + {%- set ns.has_tool_calls = true -%} + {%- endif -%} +{%- endfor -%} +{%- for message in messages -%} + {%- if message['role'] == 'user' or message['role'] == 'developer' -%} + {%- if state.in_user -%} + {{- '\n\n' -}} + {%- else -%} + {{- '<｜User｜>' -}} + {%- set state.in_user = true -%} + {%- endif -%} + {{- message['content'] or '' -}} + {%- elif message['role'] == 'tool' -%} + {%- if state.in_user -%} + {{- '\n\n' -}} + {%- else -%} + {{- '<｜User｜>' -}} + {%- set state.in_user = true -%} + {%- endif -%} + {{- '' + (message['content'] or '') + '' -}} + {%- elif message['role'] == 'assistant' -%} + {%- set state.in_user = false -%} + {{- '<｜Assistant｜>' -}} + {%- set is_after_last_user = loop.index0 > last_user_idx.value -%} + {%- set keep_reasoning = thinking and ((not drop_thinking) or has_tools or is_after_last_user or ns.has_tool_calls) -%} + {%- if keep_reasoning -%} + {{- thinking_start_token -}} + {%- if message['reasoning_content'] is defined and message['reasoning_content'] -%} + {{- message['reasoning_content'] -}} + {%- endif -%} + {{- thinking_end_token -}} + {%- else -%} + {{- thinking_end_token -}} + {%- endif -%} + {%- if message['content'] is defined and message['content'] -%} + {{- message['content'] -}} + {%- endif -%} + {%- if message['tool_calls'] -%} + {{- '\n\n<' + dsml_token + 'tool_calls>\n' -}} + {%- for tool in message['tool_calls'] -%} + {%- set func = tool['function'] -%} + {{- '<' + dsml_token + 'invoke name="' + func['name'] + '">\n' -}} + {%- set args = func['arguments'] -%} + {%- if args is string -%} + {%- set args = args | from_json -%} + {%- endif -%} + {%- for key, val in args.items() -%} + {%- if val is string -%} + {{- '<' + dsml_token + 'parameter name="' + key + '" string="true">' + val + '\n' -}} + {%- else -%} + {{- '<' + dsml_token + 'parameter name="' + key + '" string="false">' + (val | tojson) + '\n' -}} + {%- endif -%} + {%- endfor -%} + {%- if not args -%} + {{- '\n' -}} + {%- endif -%} + {{- '\n' -}} + {%- endfor -%} + {{- '' -}} + {%- endif -%} + {{- '<｜end▁of▁sentence｜>' -}} + {%- endif -%} +{%- endfor -%} +{%- if add_generation_prompt -%} + {{- '<｜Assistant｜>' -}} + {%- if thinking -%} + {{- thinking_start_token -}} + {%- else -%} + {{- thinking_end_token -}} + {%- endif -%} +{%- endif -%} diff --git a/models/templates/deepseek-ai-DeepSeek-V4.jinja b/models/templates/deepseek-ai-DeepSeek-V4.jinja index ad1ff8ce23aa..c7819149ae6e 100644 --- a/models/templates/deepseek-ai-DeepSeek-V4.jinja +++ b/models/templates/deepseek-ai-DeepSeek-V4.jinja @@ -9,11 +9,14 @@ {%- endif -%} {%- endif -%} {%- if not drop_thinking is defined -%} - {%- set drop_thinking = false -%} + {%- set drop_thinking = true -%} {%- endif -%} {%- set dsml_token = '｜DSML｜' -%} {%- set thinking_start_token = '' -%} {%- set thinking_end_token = '' -%} +{%- set reasoning_effort_max = 'Reasoning Effort: Absolute maximum with no shortcuts permitted.\nYou MUST be very thorough in your thinking and comprehensively decompose the problem to resolve the root cause, rigorously stress-testing your logic against all potential paths, edge cases, and adversarial scenarios.\nExplicitly write out your entire deliberation process, documenting every intermediate step, considered alternative, and rejected hypothesis to ensure absolutely no assumption is left unchecked.\n\n' -%} +{%- set response_format_template = '## Response Format:\n\nYou MUST strictly adhere to the following schema to reply:\n' -%} +{%- set has_tools = false -%} {%- set tools_header = '## Tools\n\nYou have access to a set of tools to help answer the user\'s question. You can invoke tools by writing a "<' + dsml_token + 'tool_calls>" block like the following:\n\n<' + dsml_token + 'tool_calls>\n<' + dsml_token + 'invoke name="$TOOL_NAME">\n<' + dsml_token + 'parameter name="$PARAMETER_NAME" string="true|false">$PARAMETER_VALUE\n...\n\n<' + dsml_token + 'invoke name="$TOOL_NAME2">\n...\n\n\n\nString parameters should be specified as is and set `string="true"`. For all other types (numbers, booleans, arrays, objects), pass the value in JSON format and set `string="false"`.\n\nIf thinking_mode is enabled (triggered by ' + thinking_start_token + '), you MUST output your complete reasoning inside ' + thinking_start_token + '...' + thinking_end_token + ' BEFORE any tool calls or final response.\n\nOtherwise, output directly after ' + thinking_end_token + ' with tool calls or final response.\n\n### Available Tool Schemas\n\n' -%} {%- set tools_footer = '\nYou MUST strictly follow the above defined tool name and parameter schemas to invoke tool calls.\n' -%} {%- set ns = namespace(system_prompt='', is_first_sp=true, has_tool_calls=false) -%} @@ -28,6 +31,7 @@ {%- endif -%} {%- endfor -%} {%- if tools is defined and tools -%} + {%- set has_tools = true -%} {%- set ts = namespace(schemas='') -%} {%- for tool in tools -%} {%- if tool['type'] == 'function' -%} @@ -40,7 +44,16 @@ {%- set ns.system_prompt = tools_header + ts.schemas + tools_footer -%} {%- endif -%} {%- endif -%} +{%- if response_format is defined -%} + {%- if ns.system_prompt -%} + {%- set ns.system_prompt = ns.system_prompt + '\n\n' -%} + {%- endif -%} + {%- set ns.system_prompt = ns.system_prompt + response_format_template + (response_format | tojson) -%} +{%- endif -%} {{- bos_token -}} +{%- if messages and thinking and reasoning_effort is defined and reasoning_effort == 'max' -%} + {{- reasoning_effort_max -}} +{%- endif -%} {{- ns.system_prompt -}} {%- set last_user_idx = namespace(value=-1) -%} {%- for message in messages -%} @@ -75,8 +88,8 @@ {%- set state.in_user = false -%} {{- '<｜Assistant｜>' -}} {%- set is_after_last_user = loop.index0 > last_user_idx.value -%} - {%- set retain_reasoning = (not drop_thinking) or (is_after_last_user or ns.has_tool_calls) -%} - {%- if retain_reasoning and thinking -%} + {%- set keep_reasoning = thinking and ((not drop_thinking) or has_tools or is_after_last_user or ns.has_tool_calls) -%} + {%- if keep_reasoning -%} {{- thinking_start_token -}} {%- if message['reasoning_content'] is defined and message['reasoning_content'] -%} {{- message['reasoning_content'] -}} @@ -104,6 +117,9 @@ {{- '<' + dsml_token + 'parameter name="' + key + '" string="false">' + (val | tojson) + '\n' -}} {%- endif -%} {%- endfor -%} + {%- if not args -%} + {{- '\n' -}} + {%- endif -%} {{- '\n' -}} {%- endfor -%} {{- '' -}} @@ -118,4 +134,4 @@ {%- else -%} {{- thinking_end_token -}} {%- endif -%} -{%- endif -%} \ No newline at end of file +{%- endif -%} diff --git a/scripts/sync-ggml.last b/scripts/sync-ggml.last index 230e59a95bbe..35e94d9fb614 100644 --- a/scripts/sync-ggml.last +++ b/scripts/sync-ggml.last @@ -1 +1 @@ -06ca97616793248fadb410ea8d69c7511b2005e4 +90951f99af1fbebef3fbdd58ff5b8715b0bb9c43 diff --git a/scripts/sync_vendor.py b/scripts/sync_vendor.py index 679e557a3215..9faa6a307c13 100755 --- a/scripts/sync_vendor.py +++ b/scripts/sync_vendor.py @@ -5,7 +5,7 @@ import sys import subprocess -HTTPLIB_VERSION = "refs/tags/v0.51.0" +HTTPLIB_VERSION = "refs/tags/v0.52.0" vendor = { "https://github.com/nlohmann/json/releases/latest/download/json.hpp": "vendor/nlohmann/json.hpp", diff --git a/scripts/ui-assets.cmake b/scripts/ui-assets.cmake index dc0417ea084b..0c1c4de555a1 100644 --- a/scripts/ui-assets.cmake +++ b/scripts/ui-assets.cmake @@ -123,15 +123,15 @@ function(npm_build out_var) endif() if(need_install) - message(STATUS "UI: running npm install") + message(STATUS "UI: running npm ci") execute_process( - COMMAND ${NPM_EXECUTABLE} install + COMMAND ${NPM_EXECUTABLE} ci WORKING_DIRECTORY "${WORK_DIR}" RESULT_VARIABLE rc ERROR_VARIABLE err ) if(NOT rc EQUAL 0) - message(STATUS "UI: npm install failed (${rc})") + message(STATUS "UI: npm ci failed (${rc})") message(STATUS " stderr: ${err}") return() endif() diff --git a/skills/code-review/SKILL.md b/skills/code-review/SKILL.md index ba76c481150e..b9372ddda870 100644 --- a/skills/code-review/SKILL.md +++ b/skills/code-review/SKILL.md @@ -47,6 +47,7 @@ Mandatory on every review; any finding here is **blocking**. Rule of thumb: GGUF - **Sizes/counts from tensor dims:** validate before allocating. Products like `ne[i]*nb[i]`/nbytes can overflow on crafted dims into an undersized alloc then heap overflow. Overflow checks must run BEFORE the arithmetic they guard - padding/alignment macros wrap to 0 near `SIZE_MAX`, so a guard after the pad passes. - **GGUF strings/arrays:** cap declared lengths and element counts before using them to size a loop or buffer; validate element type and length before casting an array to a pointer or reading fixed indices (`[i+1]`, `[0..2]`). - **File-supplied counts indexing fixed arrays:** bound any count (e.g. layer/block count into a `LLAMA_MAX_*` array) before indexing; watch checks that only fire when an optional key is present. +- **Declared vs actual array length:** check the declared length of a GGUF array against the count actually read, not just against a buffer size. - **Bounds comparisons:** flag narrowing casts (`size_t`->`int32_t`) and signed/unsigned mixing that can bypass a length check and copy past a buffer. - **Parsed/derived indices:** range-check `stoi`/`atoi` results and catch parse throws; never use a default or derived token id (EOS/BOS/...) as an index without a bounds check. - **Reused/reserved buffers:** recheck bounds after a buffer is shrunk or reused; watch `reserve()` then index-by-assumed-size, and header fields read before their length is checked. @@ -118,6 +119,7 @@ Public API changes carry a higher bar than internal ones (`CONTRIBUTING.md`). Re - In most cases, `build_vit` should be enough to build the transformer graph for vision models. Do not add a loop to build the transformer graph manually, unless you have a very good reason to do so. If you do, please explain why in the PR description. - If you need a dedicated preprocessor, there is a high chance that it can be a derived class from one of the existing preprocessors. Check carefully before adding a new preprocessor class. - If the model need a new public API in `mtmd.h`, open a discussion first. +- For audio generation models, see `tools/mtmd/README-dev.md` ## General (always) @@ -131,6 +133,8 @@ Enforce the `AGENTS.md` / `CONTRIBUTING.md` coding and naming guidelines on ever - Reuse existing infrastructure over introducing new components; no new third-party dependencies, extra headers, or files unless clearly justified. - Keep it simple: a simpler change doing 90% is often preferable to a complex one doing 100%. Flag unnecessary templates/fancy STL; basic `for` loops are fine here. - Every added line should be something the contributor can explain and defend to a reviewer without AI help - flag anything that looks copied-in without understanding. +- `Co-authored-by:` must be reserved for human co-authors; AI contributions (claude, cursor, codex, etc.) must use `Assisted-by:`; if this point is violated, it's a blocking finding. +- Any mentions of Minja must be treated as blocking; see `AGENTS.md` for why. ## Reporting diff --git a/src/CMakeLists.txt b/src/CMakeLists.txt index 320784c3a8cc..24f05cc91673 100644 --- a/src/CMakeLists.txt +++ b/src/CMakeLists.txt @@ -25,6 +25,7 @@ add_library(llama llama-kv-cache.cpp llama-kv-cache-iswa.cpp llama-kv-cache-dsa.cpp + llama-kv-cache-msa.cpp llama-kv-cache-dsv4.cpp llama-memory.cpp llama-memory-hybrid.cpp diff --git a/src/llama-arch.cpp b/src/llama-arch.cpp index e81ff647eee4..836cfade226c 100644 --- a/src/llama-arch.cpp +++ b/src/llama-arch.cpp @@ -144,6 +144,7 @@ static const std::map LLM_ARCH_NAMES = { { LLM_ARCH_TALKIE, "talkie" }, { LLM_ARCH_MELLUM, "mellum" }, { LLM_ARCH_NANBEIGE, "nanbeige" }, + { LLM_ARCH_QWEN3TTS, "qwen3tts" }, { LLM_ARCH_UNKNOWN, "(unknown)" }, }; @@ -968,6 +969,7 @@ bool llm_arch_is_hybrid(const llm_arch & arch) { case LLM_ARCH_KIMI_LINEAR: case LLM_ARCH_QWEN35: case LLM_ARCH_QWEN35MOE: + case LLM_ARCH_DEEPSEEK4: return true; default: return false; @@ -990,6 +992,7 @@ bool llm_arch_supports_rs_rollback(const llm_arch & arch) { switch (arch) { case LLM_ARCH_QWEN35: case LLM_ARCH_QWEN35MOE: + case LLM_ARCH_DEEPSEEK4: return true; default: return false; @@ -1024,6 +1027,7 @@ bool llm_arch_supports_sm_tensor(const llm_arch & arch) { case LLM_ARCH_MINIMAX_M3: case LLM_ARCH_MISTRAL4: case LLM_ARCH_KIMI_LINEAR: + case LLM_ARCH_QWEN3TTS: return false; default: return true; diff --git a/src/llama-arch.h b/src/llama-arch.h index cbc97085ea79..49c2a6ac3997 100644 --- a/src/llama-arch.h +++ b/src/llama-arch.h @@ -149,6 +149,7 @@ enum llm_arch { LLM_ARCH_MINIMAX_M3, LLM_ARCH_DFLASH, LLM_ARCH_NANBEIGE, + LLM_ARCH_QWEN3TTS, LLM_ARCH_UNKNOWN, }; diff --git a/src/llama-context.cpp b/src/llama-context.cpp index 3e0af3f317f6..19cca7df1e9d 100644 --- a/src/llama-context.cpp +++ b/src/llama-context.cpp @@ -120,8 +120,9 @@ llama_context::llama_context( cparams.no_perf = params.no_perf; cparams.warmup = false; - cparams.embeddings_layer_inp.resize(hparams.n_layer(), false); - embd_layer_inp.resize(hparams.n_layer()); + // +1: id n_layer() taps the output of the last layer ("input" of the head) + cparams.embeddings_layer_inp.resize(hparams.n_layer() + 1, false); + embd_layer_inp.resize(hparams.n_layer() + 1); cparams.ctx_type = params.ctx_type; cparams.pooling_type = params.pooling_type; @@ -1164,7 +1165,7 @@ void llama_context::set_embeddings_nextn(bool value, bool masked) { void llama_context::set_embeddings_layer_inp(uint32_t lid, bool enable) { LLAMA_LOG_DEBUG("%s: lid = %d, enable = %d\n", __func__, lid, enable); - GGML_ASSERT(lid < model.hparams.n_layer()); + GGML_ASSERT(lid <= model.hparams.n_layer()); cparams.embeddings_layer_inp[lid] = enable; @@ -1716,7 +1717,8 @@ int llama_context::decode(const llama_batch & batch_inp) { const auto & hparams = model.hparams; const int64_t n_vocab = vocab.n_tokens(); - const int64_t n_embd = hparams.n_embd_inp(); + const bool mtp_embd = cparams.ctx_type == LLAMA_CONTEXT_TYPE_MTP && batch_inp.embd; + const int64_t n_embd = mtp_embd ? hparams.n_embd_out() : hparams.n_embd_inp(); // when computing embeddings, all tokens are output const bool output_all = cparams.embeddings; @@ -2275,8 +2277,9 @@ void llama_context::extract_layer_inputs(const llm_graph_result * res, size_t to } void llama_context::output_reorder() { - const uint64_t n_vocab = model.vocab.n_tokens(); - const uint64_t n_embd = model.hparams.n_embd; + const uint64_t n_vocab = model.vocab.n_tokens(); + const uint64_t n_embd = model.hparams.n_embd; + const uint64_t n_embd_out = model.hparams.n_embd_out(); for (size_t s = 0; s < output_swaps.size(); ++s) { const uint64_t i0 = output_swaps[s].i0; @@ -2289,14 +2292,14 @@ void llama_context::output_reorder() { } if (embd.size > 0) { - for (uint64_t k = 0; k < n_embd; k++) { - std::swap(embd.data[i0*n_embd + k], embd.data[i1*n_embd + k]); + for (uint64_t k = 0; k < n_embd_out; k++) { + std::swap(embd.data[i0*n_embd_out + k], embd.data[i1*n_embd_out + k]); } } if (embd_nextn.size > 0) { - for (uint64_t k = 0; k < n_embd; k++) { - std::swap(embd_nextn.data[i0*n_embd + k], embd_nextn.data[i1*n_embd + k]); + for (uint64_t k = 0; k < n_embd_out; k++) { + std::swap(embd_nextn.data[i0*n_embd_out + k], embd_nextn.data[i1*n_embd_out + k]); } } @@ -2351,6 +2354,7 @@ uint32_t llama_context::graph_max_nodes(uint32_t n_tokens) const { model.arch == LLM_ARCH_QWEN35 || model.arch == LLM_ARCH_QWEN35MOE || model.arch == LLM_ARCH_DEEPSEEK4 || + (model.arch == LLM_ARCH_DFLASH && model.hparams.dsv4_hc_mult > 0) || model.arch == LLM_ARCH_NANBEIGE || model.arch == LLM_ARCH_MINIMAX_M3) { return std::max(n_tokens * 40, 32u * model.n_tensors()); @@ -3553,6 +3557,22 @@ llama_context * llama_init_from_model( } } + if ((model->hparams.is_mla() || model->arch == LLM_ARCH_DEEPSEEK4) && params.type_k != params.type_v) { + LLAMA_LOG_ERROR("%s: model does not support different K (%s) and V (%s) cache types\n", __func__, ggml_type_name(params.type_k), ggml_type_name(params.type_v)); + return nullptr; + } + + if (ggml_is_quantized(params.type_v) && params.flash_attn_type != LLAMA_FLASH_ATTN_TYPE_ENABLED) { + if (params.flash_attn_type == LLAMA_FLASH_ATTN_TYPE_AUTO) { + LLAMA_LOG_INFO("%s: enabling flash_attn since it is required for quantized V cache\n", __func__); + params.flash_attn_type = LLAMA_FLASH_ATTN_TYPE_ENABLED; + } + if (params.flash_attn_type == LLAMA_FLASH_ATTN_TYPE_DISABLED) { + LLAMA_LOG_ERROR("%s: quantized V cache requires flash_attn to be enabled\n", __func__); + return nullptr; + } + } + if (params.flash_attn_type != LLAMA_FLASH_ATTN_TYPE_DISABLED && ggml_is_quantized(params.type_k)) { const uint32_t blck_size = ggml_blck_size(params.type_k); for (uint32_t il = 0; il < model->hparams.n_layer(); ++il) { @@ -3575,11 +3595,6 @@ llama_context * llama_init_from_model( } } - if (ggml_is_quantized(params.type_v) && params.flash_attn_type == LLAMA_FLASH_ATTN_TYPE_DISABLED) { - LLAMA_LOG_ERROR("%s: V cache quantization requires flash_attn\n", __func__); - return nullptr; - } - if (params.pooling_type != LLAMA_POOLING_TYPE_UNSPECIFIED && params.pooling_type != model->hparams.pooling_type) { //user-specified pooling-type is different from the model default diff --git a/src/llama-ext.h b/src/llama-ext.h index 348bbae95770..35d6e58adfa8 100644 --- a/src/llama-ext.h +++ b/src/llama-ext.h @@ -124,3 +124,9 @@ LLAMA_API llama_context * llama_get_ctx_other(struct llama_context * ctx); LLAMA_API const int32_t * llama_model_target_layer_ids (const struct llama_model * model); // returns the number of extracted layers from target model LLAMA_API uint32_t llama_model_target_layer_ids_n(const struct llama_model * model); + +// retrieves the whole token embedding matrix in F32 format (n_embd * n_vocab) +// returns total number of elements or 0 on error +// if out is nullptr, returns the number of tokens without writing to out +// caller must allocate enough memory for out before calling +LLAMA_API uint32_t llama_model_get_tok_embd(const struct llama_model * model, float * out); diff --git a/src/llama-graph.cpp b/src/llama-graph.cpp index 6d1c8f4e42a8..2be3b75fb982 100644 --- a/src/llama-graph.cpp +++ b/src/llama-graph.cpp @@ -8,6 +8,7 @@ #include "llama-kv-cache.h" #include "llama-kv-cache-iswa.h" #include "llama-kv-cache-dsa.h" +#include "llama-kv-cache-msa.h" #include "llama-kv-cache-dsv4.h" #include "llama-memory-hybrid.h" #include "llama-memory-hybrid-iswa.h" @@ -518,6 +519,40 @@ bool llm_graph_input_attn_k::can_reuse(const llm_graph_params & params) { return res; } +llm_graph_input_attn_kv_msa::llm_graph_input_attn_kv_msa( + const llama_hparams & hparams, + const llama_cparams & cparams, + const llama_kv_cache_msa_context * mctx) : + llm_graph_input_attn_kv(hparams, cparams, mctx->get_base()), + mctx_msa(mctx) { +} + +void llm_graph_input_attn_kv_msa::set_input(const llama_ubatch * ubatch) { + llm_graph_input_attn_kv::set_input(ubatch); + + if (self_k_idxs_idx) { + mctx_msa->get_idx()->set_input_k_idxs(self_k_idxs_idx, ubatch); + } +} + +bool llm_graph_input_attn_kv_msa::can_reuse(const llm_graph_params & params) { + mctx_msa = static_cast(params.mctx); + + // the parent class operates on the base cache context + this->mctx = mctx_msa->get_base(); + + bool res = true; + + res &= self_k_idxs->ne[0] == params.ubatch.n_tokens; + if (self_k_idxs_idx) { + res &= self_k_idxs_idx->ne[0] == params.ubatch.n_tokens; + } + + res &= can_reuse_kq_mask(self_kq_mask, this->mctx, params.ubatch, params.cparams); + + return res; +} + void llm_graph_input_attn_k_dsa::set_input(const llama_ubatch * ubatch) { mctx->get_mla()->set_input_k_idxs(self_k_idxs_mla, ubatch); @@ -619,6 +654,63 @@ bool llm_graph_input_attn_kv_iswa::can_reuse(const llm_graph_params & params) { return res; } +void llm_graph_input_attn_k_iswa::set_input(const llama_ubatch * ubatch) { + // base tensors may not be allocated if there are no non-SWA attention layers + if (self_k_idxs && self_k_idxs->buffer) { + mctx->get_base()->set_input_k_idxs(self_k_idxs, ubatch); + } + + // the kq mask guards on its own buffer: shared cells leave idxs unbacked while the mask stays live + if (self_kq_mask && self_kq_mask->buffer) { + mctx->get_base()->set_input_kq_mask(self_kq_mask, ubatch, cparams.causal_attn); + } + + // swa tensors may not be allocated if there are no SWA attention layers + if (self_k_idxs_swa && self_k_idxs_swa->buffer) { + mctx->get_swa()->set_input_k_idxs(self_k_idxs_swa, ubatch); + } + + if (self_kq_mask_swa && self_kq_mask_swa->buffer) { + mctx->get_swa()->set_input_kq_mask(self_kq_mask_swa, ubatch, cparams.causal_attn); + } + + if (self_k_rot && self_k_rot->buffer) { + mctx->get_base()->set_input_k_rot(self_k_rot); + } + + if (self_k_rot_swa && self_k_rot_swa->buffer) { + mctx->get_swa()->set_input_k_rot(self_k_rot_swa); + } +} + +bool llm_graph_input_attn_k_iswa::can_reuse(const llm_graph_params & params) { + const auto * mctx = static_cast(params.mctx); + + this->mctx = mctx; + + bool res = true; + + // base tensors may not be allocated if there are no non-SWA attention layers + if (self_k_idxs && self_k_idxs->buffer) { + res &= self_k_idxs->ne[0] == params.ubatch.n_tokens; + } + + if (self_kq_mask && self_kq_mask->buffer) { + res &= can_reuse_kq_mask(self_kq_mask, mctx->get_base(), params.ubatch, params.cparams); + } + + // swa tensors may not be allocated if there are no SWA attention layers + if (self_k_idxs_swa && self_k_idxs_swa->buffer) { + res &= self_k_idxs_swa->ne[0] == params.ubatch.n_tokens; + } + + if (self_kq_mask_swa && self_kq_mask_swa->buffer) { + res &= can_reuse_kq_mask(self_kq_mask_swa, mctx->get_swa(), params.ubatch, params.cparams); + } + + return res; +} + static void dsv4_set_i64(ggml_tensor * dst, const std::vector & src) { if (!dst || !dst->buffer) { return; @@ -754,6 +846,10 @@ static void dsv4_set_comp_inputs( dsv4_set_i32(inp.state_pos, plan.state_pos); dsv4_set_i32(inp.state_persist_src_idxs, plan.state_persist_src_idxs); dsv4_set_i32(inp.state_persist_dst_idxs, plan.state_persist_dst_idxs); + dsv4_set_i32(inp.state_restore_src_idxs, plan.state_restore_src_idxs); + dsv4_set_i32(inp.state_restore_dst_idxs, plan.state_restore_dst_idxs); + dsv4_set_i32(inp.state_snapshot_src_idxs, plan.state_snapshot_src_idxs); + dsv4_set_i32(inp.state_snapshot_dst_idxs, plan.state_snapshot_dst_idxs); dsv4_set_i32(inp.state_read_idxs, plan.state_read_idxs); dsv4_set_i64(inp.state_write_idxs, plan.state_write_idxs); dsv4_set_i32(inp.state_write_pos, plan.state_write_pos); @@ -798,6 +894,10 @@ static bool dsv4_can_reuse_comp_input( res &= dsv4_can_reuse_tensor_1d(inp.state_pos, plan.state_pos.size()); res &= dsv4_can_reuse_tensor_1d(inp.state_persist_src_idxs, plan.state_persist_src_idxs.size()); res &= dsv4_can_reuse_tensor_1d(inp.state_persist_dst_idxs, plan.state_persist_dst_idxs.size()); + res &= dsv4_can_reuse_tensor_1d(inp.state_restore_src_idxs, plan.state_restore_src_idxs.size()); + res &= dsv4_can_reuse_tensor_1d(inp.state_restore_dst_idxs, plan.state_restore_dst_idxs.size()); + res &= dsv4_can_reuse_tensor_1d(inp.state_snapshot_src_idxs, plan.state_snapshot_src_idxs.size()); + res &= dsv4_can_reuse_tensor_1d(inp.state_snapshot_dst_idxs, plan.state_snapshot_dst_idxs.size()); res &= dsv4_can_reuse_tensor_1d(inp.state_read_idxs, plan.state_read_idxs.size()); res &= dsv4_can_reuse_tensor_1d(inp.state_write_idxs, plan.state_write_idxs.size()); res &= dsv4_can_reuse_tensor_1d(inp.state_write_pos, plan.state_write_pos.size()); @@ -832,6 +932,10 @@ static void dsv4_build_comp_inputs( inp.state_pos = dsv4_build_input_1d(ctx, GGML_TYPE_I32, plan.state_pos.size(), std::string("dsv4_") + name + "_state_pos"); inp.state_persist_src_idxs = dsv4_build_input_1d(ctx, GGML_TYPE_I32, plan.state_persist_src_idxs.size(), std::string("dsv4_") + name + "_state_persist_src_idxs"); inp.state_persist_dst_idxs = dsv4_build_input_1d(ctx, GGML_TYPE_I32, plan.state_persist_dst_idxs.size(), std::string("dsv4_") + name + "_state_persist_dst_idxs"); + inp.state_restore_src_idxs = dsv4_build_input_1d(ctx, GGML_TYPE_I32, plan.state_restore_src_idxs.size(), std::string("dsv4_") + name + "_state_restore_src_idxs"); + inp.state_restore_dst_idxs = dsv4_build_input_1d(ctx, GGML_TYPE_I32, plan.state_restore_dst_idxs.size(), std::string("dsv4_") + name + "_state_restore_dst_idxs"); + inp.state_snapshot_src_idxs = dsv4_build_input_1d(ctx, GGML_TYPE_I32, plan.state_snapshot_src_idxs.size(), std::string("dsv4_") + name + "_state_snapshot_src_idxs"); + inp.state_snapshot_dst_idxs = dsv4_build_input_1d(ctx, GGML_TYPE_I32, plan.state_snapshot_dst_idxs.size(), std::string("dsv4_") + name + "_state_snapshot_dst_idxs"); inp.state_read_idxs = dsv4_build_input_1d(ctx, GGML_TYPE_I32, plan.state_read_idxs.size(), std::string("dsv4_") + name + "_state_read_idxs"); inp.state_write_idxs = dsv4_build_input_1d(ctx, GGML_TYPE_I64, plan.state_write_idxs.size(), std::string("dsv4_") + name + "_state_write_idxs"); inp.state_write_pos = dsv4_build_input_1d(ctx, GGML_TYPE_I32, plan.state_write_pos.size(), std::string("dsv4_") + name + "_state_write_pos"); @@ -1195,7 +1299,7 @@ void llm_graph_result::reset() { t_embd_pooled = nullptr; t_h_nextn = nullptr; - t_layer_inp.resize(LLAMA_MAX_LAYERS); + t_layer_inp.resize(LLAMA_MAX_LAYERS + 1); std::fill(t_layer_inp.begin(), t_layer_inp.end(), nullptr); t_sampled.clear(); @@ -1650,7 +1754,7 @@ ggml_tensor * llm_graph_context::build_ffn( tmp = ggml_clamp(ctx0, tmp, -limit, limit); cb(tmp, "ffn_up_clamped", il); - if (arch == LLM_ARCH_DEEPSEEK4) { + if (arch == LLM_ARCH_DEEPSEEK4 || (arch == LLM_ARCH_DFLASH && hparams.dsv4_hc_mult > 0)) { cur = ggml_clamp(ctx0, cur, -INFINITY, limit); cb(cur, "ffn_gate_clamped", il); cur = ggml_swiglu_split(ctx0, cur, tmp); @@ -2045,7 +2149,7 @@ ggml_tensor * llm_graph_context::build_moe_ffn( up = ggml_clamp(ctx0, up, -limit, limit); cb(up, "ffn_moe_up_clamped", il); - if (arch == LLM_ARCH_DEEPSEEK4) { + if (arch == LLM_ARCH_DEEPSEEK4 || (arch == LLM_ARCH_DFLASH && hparams.dsv4_hc_mult > 0)) { cur = ggml_clamp(ctx0, cur, -INFINITY, limit); cb(cur, "ffn_moe_gate_clamped", il); cur = ggml_swiglu_split(ctx0, cur, up); @@ -2962,6 +3066,75 @@ ggml_tensor * llm_graph_context::build_attn( return cur; } +ggml_tensor * llm_graph_context::build_attn( + llm_graph_input_attn_k_iswa * inp, + ggml_tensor * wo, + ggml_tensor * wo_b, + ggml_tensor * wo_s, + ggml_tensor * q_cur, + ggml_tensor * k_cur, + ggml_tensor * v_cur, + ggml_tensor * kq_b, + ggml_tensor * sinks, + ggml_tensor * v_mla, + float kq_scale, + int il) const { + const bool is_swa = hparams.is_swa(il); + + GGML_UNUSED(v_cur); + + auto * k_rot = is_swa ? inp->self_k_rot_swa : inp->self_k_rot; + + if (k_rot) { + q_cur = llama_mul_mat_hadamard(ctx0, q_cur, k_rot); + if (k_cur) { + k_cur = llama_mul_mat_hadamard(ctx0, k_cur, k_rot); + } + } + + // these nodes are added to the graph together so that they are not reordered + // by doing so, the number of splits in the graph is reduced + ggml_build_forward_expand(gf, q_cur); + + if (k_cur) { + ggml_build_forward_expand(gf, k_cur); + } + + const auto * mctx_iswa = inp->mctx; + const auto * mctx_cur = is_swa ? mctx_iswa->get_swa() : mctx_iswa->get_base(); + + // optionally store to KV cache + if (k_cur) { + const auto & k_idxs = is_swa ? inp->get_k_idxs_swa() : inp->get_k_idxs(); + + ggml_build_forward_expand(gf, mctx_cur->cpy_k(ctx0, k_cur, k_idxs, il)); + } + + const auto & kq_mask = is_swa ? inp->get_kq_mask_swa() : inp->get_kq_mask(); + + // MLA-style attention: the cached K is used as V + ggml_tensor * q = q_cur; + ggml_tensor * k = mctx_cur->get_k(ctx0, il); + ggml_tensor * v = k; + + ggml_tensor * cur = build_attn_mha(q, k, v, kq_b, kq_mask, sinks, v_mla, kq_scale, il); + cb(cur, "kqv_out", il); + + if (k_rot) { + cur = llama_mul_mat_hadamard(ctx0, cur, k_rot); + } + + if (wo) { + cur = build_lora_mm(wo, cur, wo_s); + } + + if (wo_b) { + cur = ggml_add(ctx0, cur, wo_b); + } + + return cur; +} + llm_graph_input_attn_cross * llm_graph_context::build_attn_inp_cross() const { auto inp = std::make_unique(cross); @@ -3049,6 +3222,34 @@ llm_graph_input_attn_k_dsa * llm_graph_context::build_attn_inp_k_dsa() const { return (llm_graph_input_attn_k_dsa *) res->add_input(std::move(inp)); } +llm_graph_input_attn_kv_msa * llm_graph_context::build_attn_inp_kv_msa(bool msa_enabled) const { + const auto * mctx_cur = static_cast(mctx); + + auto inp = std::make_unique(hparams, cparams, mctx_cur); + + const auto * mctx_base = mctx_cur->get_base(); + const auto * mctx_idx = mctx_cur->get_idx(); + + { + GGML_ASSERT(hparams.swa_type == LLAMA_SWA_TYPE_NONE && "Use llama_kv_cache_iswa for SWA"); + + inp->self_k_idxs = mctx_base->build_input_k_idxs(ctx0, ubatch); + inp->self_v_idxs = mctx_base->build_input_v_idxs(ctx0, ubatch); + + inp->self_kq_mask = build_attn_inp_kq_mask(ctx0, mctx_base, ubatch, cparams); + inp->self_kq_mask_cnv = inp->self_kq_mask; + } + + inp->self_k_rot = mctx_base->build_input_k_rot(ctx0); + inp->self_v_rot = mctx_base->build_input_v_rot(ctx0); + + if (msa_enabled) { + inp->self_k_idxs_idx = mctx_idx->build_input_k_idxs(ctx0, ubatch); + } + + return (llm_graph_input_attn_kv_msa *) res->add_input(std::move(inp)); +} + // TODO: maybe separate the inner implementation into a separate function // like with the non-sliding window equivalent // once sliding-window hybrid caches are a thing. @@ -3084,6 +3285,34 @@ llm_graph_input_attn_kv_iswa * llm_graph_context::build_attn_inp_kv_iswa() const return (llm_graph_input_attn_kv_iswa *) res->add_input(std::move(inp)); } +llm_graph_input_attn_k_iswa * llm_graph_context::build_attn_inp_k_iswa() const { + const auto * mctx_cur = static_cast(mctx); + + auto inp = std::make_unique(hparams, cparams, mctx_cur); + + { + inp->self_k_idxs = mctx_cur->get_base()->build_input_k_idxs(ctx0, ubatch); + + inp->self_kq_mask = build_attn_inp_kq_mask(ctx0, mctx_cur->get_base(), ubatch, cparams); + inp->self_kq_mask_cnv = inp->self_kq_mask; + } + + { + GGML_ASSERT(hparams.swa_type != LLAMA_SWA_TYPE_NONE && "Use llama_kv_cache for non-SWA"); + + inp->self_k_idxs_swa = mctx_cur->get_swa()->build_input_k_idxs(ctx0, ubatch); + + inp->self_kq_mask_swa = build_attn_inp_kq_mask(ctx0, mctx_cur->get_swa(), ubatch, cparams); + inp->self_kq_mask_swa_cnv = inp->self_kq_mask_swa; + } + + inp->self_k_rot = mctx_cur->get_base()->build_input_k_rot(ctx0); + + inp->self_k_rot_swa = mctx_cur->get_swa()->build_input_k_rot(ctx0); + + return (llm_graph_input_attn_k_iswa *) res->add_input(std::move(inp)); +} + llm_graph_input_dsv4 * llm_graph_context::build_inp_dsv4() const { const auto * mctx_cur = static_cast(mctx); const auto * raw_ctx = mctx_cur->get_raw(); diff --git a/src/llama-graph.h b/src/llama-graph.h index 7ed490ce6728..32d8d395aa45 100644 --- a/src/llama-graph.h +++ b/src/llama-graph.h @@ -23,6 +23,7 @@ struct llama_memory_context_i; class llama_kv_cache_context; class llama_kv_cache_dsa_context; +class llama_kv_cache_msa_context; class llama_kv_cache_dsv4_raw_context; class llama_kv_cache_dsv4_context; class llama_kv_cache_iswa_context; @@ -425,6 +426,26 @@ class llm_graph_input_attn_k_dsa : public llm_graph_input_i { const llama_kv_cache_dsa_context * mctx; }; +// standard K/V attention input against the base cache, plus destination indices for the indexer key cache +class llm_graph_input_attn_kv_msa : public llm_graph_input_attn_kv { +public: + llm_graph_input_attn_kv_msa( + const llama_hparams & hparams, + const llama_cparams & cparams, + const llama_kv_cache_msa_context * mctx); + ~llm_graph_input_attn_kv_msa() = default; + + void set_input(const llama_ubatch * ubatch) override; + + bool can_reuse(const llm_graph_params & params) override; + + ggml_tensor * get_k_idxs_idx() const { return self_k_idxs_idx; } + + ggml_tensor * self_k_idxs_idx = nullptr; // I64 [n_batch] + + const llama_kv_cache_msa_context * mctx_msa; +}; + class llm_graph_input_attn_kv_iswa : public llm_graph_input_i { public: llm_graph_input_attn_kv_iswa( @@ -471,6 +492,45 @@ class llm_graph_input_attn_kv_iswa : public llm_graph_input_i { const llama_kv_cache_iswa_context * mctx; }; +class llm_graph_input_attn_k_iswa : public llm_graph_input_i { +public: + llm_graph_input_attn_k_iswa( + const llama_hparams & hparams, + const llama_cparams & cparams, + const llama_kv_cache_iswa_context * mctx) : + hparams(hparams), + cparams(cparams), + mctx(mctx) { + } + ~llm_graph_input_attn_k_iswa() = default; + + void set_input(const llama_ubatch * ubatch) override; + + bool can_reuse(const llm_graph_params & params) override; + + ggml_tensor * get_k_idxs() const { return self_k_idxs; } + ggml_tensor * get_k_idxs_swa() const { return self_k_idxs_swa; } + + ggml_tensor * get_kq_mask() const { return self_kq_mask_cnv; } + ggml_tensor * get_kq_mask_swa() const { return self_kq_mask_swa_cnv; } + + ggml_tensor * self_k_idxs = nullptr; // I64 [n_batch] + ggml_tensor * self_k_idxs_swa = nullptr; // I64 [n_batch] + + ggml_tensor * self_kq_mask = nullptr; // F32/F16 [n_kv, n_batch/n_stream, 1, n_stream] + ggml_tensor * self_kq_mask_cnv = nullptr; // [n_kv, n_batch/n_stream, 1, n_stream] + ggml_tensor * self_kq_mask_swa = nullptr; // F32/F16 [n_kv, n_batch/n_stream, 1, n_stream] + ggml_tensor * self_kq_mask_swa_cnv = nullptr; // [n_kv, n_batch/n_stream, 1, n_stream] + + ggml_tensor * self_k_rot = nullptr; + ggml_tensor * self_k_rot_swa = nullptr; + + const llama_hparams hparams; + const llama_cparams cparams; + + const llama_kv_cache_iswa_context * mctx; +}; + // DSV4 raw graph inputs are SWA-only, but their mask may be stream-shaped // so raw K can be concatenated with DSV4 compressed K in one attention op. class llm_graph_input_dsv4_raw { @@ -505,6 +565,10 @@ class llm_graph_input_dsv4 : public llm_graph_input_i { ggml_tensor * state_pos = nullptr; // I32 [n_state] ggml_tensor * state_persist_src_idxs = nullptr; // I32 [n_state_persist] ggml_tensor * state_persist_dst_idxs = nullptr; // I32 [n_state_persist] + ggml_tensor * state_restore_src_idxs = nullptr; // I32 [n_state_restore] + ggml_tensor * state_restore_dst_idxs = nullptr; // I32 [n_state_restore] + ggml_tensor * state_snapshot_src_idxs = nullptr; // I32 [n_state_snapshot] + ggml_tensor * state_snapshot_dst_idxs = nullptr; // I32 [n_state_snapshot] ggml_tensor * state_read_idxs = nullptr; // I32 [ratio*n_state_write] ggml_tensor * state_write_idxs = nullptr; // I64 [n_state_write] ggml_tensor * state_write_pos = nullptr; // I32 [n_state_write] @@ -1068,7 +1132,7 @@ struct llm_graph_context { ggml_tensor * build_attn_mha( ggml_tensor * q, // [n_embd_head_q, n_head_q, n_tokens] ggml_tensor * k, // [n_embd_head_k, n_head_k, n_tokens] - ggml_tensor * v, // [n_embd_head_v, n_head_v, n_tokens] (v_trans == false) + ggml_tensor * v, // [n_embd_head_v, n_head_v, n_tokens] (v_trans = false) ggml_tensor * kq_b, ggml_tensor * kq_mask, ggml_tensor * sinks, // [n_head_q] @@ -1126,6 +1190,8 @@ struct llm_graph_context { llm_graph_input_attn_k_dsa * build_attn_inp_k_dsa() const; + llm_graph_input_attn_kv_msa * build_attn_inp_kv_msa(bool msa_enabled) const; + ggml_tensor * build_attn( llm_graph_input_attn_k_dsa * inp, ggml_tensor * wo, @@ -1160,6 +1226,24 @@ struct llm_graph_context { float kq_scale, int il) const; + llm_graph_input_attn_k_iswa * build_attn_inp_k_iswa() const; + + // note: if k_cur is not provided, it will not be stored in the memory + // note: the K cache is used as V (MLA-style attention) + ggml_tensor * build_attn( + llm_graph_input_attn_k_iswa * inp, + ggml_tensor * wo, + ggml_tensor * wo_b, + ggml_tensor * wo_s, + ggml_tensor * q_cur, // [n_embd_head_q, n_head_q, n_tokens] + ggml_tensor * k_cur, // [n_embd_head_k, n_head_k, n_tokens] optional + ggml_tensor * v_cur, // [n_embd_head_v, n_head_v, n_tokens] optional + ggml_tensor * kq_b, + ggml_tensor * sinks, // [n_head_q] + ggml_tensor * v_mla, // [n_embd_head_v_mla, n_embd_head_v, n_head_v] + float kq_scale, + int il) const; + llm_graph_input_attn_cross * build_attn_inp_cross() const; ggml_tensor * build_attn( diff --git a/src/llama-hparams.cpp b/src/llama-hparams.cpp index 50af97f358c3..846d4c69a626 100644 --- a/src/llama-hparams.cpp +++ b/src/llama-hparams.cpp @@ -180,16 +180,6 @@ uint32_t llama_hparams::n_embd_v_gqa_max() const { return val; } -uint32_t llama_hparams::n_embd_k_idx(uint32_t il) const { - if (!indexer_kv || indexer_head_size == 0) { - return 0; // arch without a MSA indexer - } - if (il < n_layer_dense_lead) { - return 0; // leading dense layers carry no indexer - } - return indexer_head_size; // 128 -} - uint32_t llama_hparams::n_embd_r() const { if (wkv_head_size != 0) { // for RWKV models diff --git a/src/llama-hparams.h b/src/llama-hparams.h index fc770bf003e6..6e8336c98748 100644 --- a/src/llama-hparams.h +++ b/src/llama-hparams.h @@ -230,8 +230,6 @@ struct llama_hparams { // MSA uint32_t indexer_block_size = 0; uint32_t indexer_local_blocks = 0; - // MSA stores its indexer keys in the main KV cache (k_idx tensors); - bool indexer_kv = false; // Indexer is "full" (1) or "shared" (0) // Shared indexers reuse top-k from previous full layer @@ -356,9 +354,6 @@ struct llama_hparams { uint32_t n_embd_k_gqa_max() const; uint32_t n_embd_v_gqa_max() const; - // dimension of the single-head MSA indexer key stream - uint32_t n_embd_k_idx(uint32_t il = 0) const; - // dimension of the rolling state embeddings // corresponds to Mamba's conv_states size or RWKV's token_shift states size uint32_t n_embd_r() const; diff --git a/src/llama-kv-cache-dsa.cpp b/src/llama-kv-cache-dsa.cpp index 241c50365a13..96cb045d2e5d 100644 --- a/src/llama-kv-cache-dsa.cpp +++ b/src/llama-kv-cache-dsa.cpp @@ -23,7 +23,8 @@ llama_kv_cache_dsa::llama_kv_cache_dsa( uint32_t n_pad, uint32_t n_swa, llama_swa_type swa_type, - const layer_filter_cb & filter, + const layer_filter_cb & filter_mla, + const layer_filter_cb & filter_lid, const layer_reuse_cb & reuse) : hparams_lid(model.hparams), n_stream(unified ? 1 : n_seq_max) { @@ -32,7 +33,7 @@ llama_kv_cache_dsa::llama_kv_cache_dsa( kv_mla = std::make_unique( model, model.hparams, type_k, type_v, v_trans, offload, unified, kv_size, n_seq_max, n_pad, - n_swa, swa_type, nullptr, filter, reuse, nullptr); + n_swa, swa_type, nullptr, filter_mla, reuse, nullptr); // we use llama_kv_cache for caching indexer keys // by hand-tweaking some hparams we fool it to create @@ -49,7 +50,7 @@ llama_kv_cache_dsa::llama_kv_cache_dsa( kv_lid = std::make_unique( model, hparams_lid, type_k, type_v, v_trans, offload, unified, kv_size, n_seq_max, n_pad, - n_swa, swa_type, nullptr, filter, reuse, nullptr); + n_swa, swa_type, nullptr, filter_lid, reuse, nullptr); } void llama_kv_cache_dsa::clear(bool data) { diff --git a/src/llama-kv-cache-dsa.h b/src/llama-kv-cache-dsa.h index e2b330993b84..e74fc4d9100f 100644 --- a/src/llama-kv-cache-dsa.h +++ b/src/llama-kv-cache-dsa.h @@ -26,7 +26,8 @@ class llama_kv_cache_dsa : public llama_memory_i { uint32_t n_pad, uint32_t n_swa, llama_swa_type swa_type, - const layer_filter_cb & filter, + const layer_filter_cb & filter_mla, + const layer_filter_cb & filter_lid, const layer_reuse_cb & reuse); ~llama_kv_cache_dsa() = default; diff --git a/src/llama-kv-cache-dsv4.cpp b/src/llama-kv-cache-dsv4.cpp index 069da45f4ea3..5caa05e8b07d 100644 --- a/src/llama-kv-cache-dsv4.cpp +++ b/src/llama-kv-cache-dsv4.cpp @@ -252,7 +252,8 @@ static void dsv4_state_write_tensor_streams( uint32_t tensor_rows, uint32_t n_rows, uint32_t s0, - uint32_t ns) { + uint32_t ns, + const std::vector * stream_ids = nullptr) { const int32_t type_i = (int32_t) tensor->type; const uint64_t ne0 = tensor->ne[0]; const uint64_t rows = n_rows; @@ -273,8 +274,16 @@ static void dsv4_state_write_tensor_streams( return; } + if (stream_ids && stream_ids->size() != ns) { + throw std::runtime_error("DSV4 state tensor stream map size mismatch"); + } + for (uint32_t s = 0; s < ns; ++s) { - const size_t offset = (size_t) (s0 + s)*stream_stride; + const uint32_t stream = stream_ids ? (*stream_ids)[s] : s0 + s; + if ((int64_t) stream >= tensor->ne[2]) { + throw std::runtime_error("DSV4 state tensor stream out of range"); + } + const size_t offset = (size_t) stream*stream_stride; io.write_tensor(tensor, offset, size); } } @@ -421,7 +430,9 @@ static llama_kv_cache_dsv4_context::comp_plan dsv4_build_comp_plan( bool overlap, uint32_t state_size, uint32_t kv_size, - uint32_t n_stream) { + uint32_t n_stream, + uint32_t n_rs_seq, + const std::vector & rs_idx) { llama_kv_cache_dsv4_context::comp_plan plan; plan.n_visible.resize(ubatch.n_tokens); plan.n_stream = dsv4_comp_graph_n_stream(ubatch, n_stream); @@ -451,6 +462,7 @@ static llama_kv_cache_dsv4_context::comp_plan dsv4_build_comp_plan( std::vector overlap_cur_reads; std::map, int64_t> curr_token_idx_map; + std::map state_write_counts; for (uint32_t i = 0; i < ubatch.n_tokens; ++i) { for (int32_t s = 0; s < ubatch.n_seq_id[i]; ++s) { @@ -513,6 +525,7 @@ static llama_kv_cache_dsv4_context::comp_plan dsv4_build_comp_plan( plan.state_write_idxs.push_back(cache_off + pos/ratio); plan.state_write_pos.push_back((int32_t) source_start); + ++state_write_counts[seq_id]; if (overlap) { const llama_pos prev_start = source_start - ratio; @@ -531,33 +544,57 @@ static llama_kv_cache_dsv4_context::comp_plan dsv4_build_comp_plan( } } - if (ratio == DSV4_CSA_RATIO && plan.state_write_idxs.empty() && !plan.state_pos.empty()) { - // Non-boundary CSA steps still need a write op so their graph matches - // boundary steps. Use a padded scratch row that is masked from attention. + if (ratio == DSV4_CSA_RATIO && !plan.state_pos.empty()) { assert(kv_size > 0); - uint32_t i = 0; - while (i < ubatch.n_tokens && ubatch.pos[i] < 0) { - ++i; - } - assert(i < ubatch.n_tokens); + // Pad each stream to the reserve plan's block count. + const auto append_dummy_block = [&](llama_seq_id seq_id, uint32_t i) { + const int64_t cache_off = dsv4_stream_offset(n_stream, seq_id, kv_size); + const int32_t source_idx = state_source_idx(seq_id, ubatch.pos[i]); - const llama_pos pos = ubatch.pos[i]; - const llama_seq_id seq_id = ubatch.seq_id[i][0]; - const int64_t cache_off = dsv4_stream_offset(n_stream, seq_id, kv_size); - const int32_t source_idx = state_source_idx(seq_id, pos); + plan.state_write_idxs.push_back(cache_off + kv_size - 1); + plan.state_write_pos .push_back(0); - plan.state_write_idxs.push_back(cache_off + kv_size - 1); - plan.state_write_pos .push_back(0); + if (overlap) { + for (uint32_t j = 0; j < ratio; ++j) { + overlap_prev_reads.push_back(source_idx); + overlap_cur_reads .push_back(source_idx); + } + } else { + for (uint32_t j = 0; j < ratio; ++j) { + plan.state_read_idxs.push_back(source_idx); + } + } + }; - if (overlap) { - for (uint32_t j = 0; j < ratio; ++j) { - overlap_prev_reads.push_back(source_idx); - overlap_cur_reads .push_back(source_idx); + if (dsv4_ubatch_has_coupled(ubatch)) { + if (plan.state_write_idxs.empty()) { + uint32_t i = 0; + while (i < ubatch.n_tokens && ubatch.pos[i] < 0) { + ++i; + } + assert(i < ubatch.n_tokens); + append_dummy_block(ubatch.seq_id[i][0], i); } } else { - for (uint32_t j = 0; j < ratio; ++j) { - plan.state_read_idxs.push_back(source_idx); + const uint32_t n_blocks = (std::max(1, ubatch.n_seq_tokens) + ratio - 1)/ratio; + + for (uint32_t s = 0; s < ubatch.n_seqs_unq; ++s) { + const llama_seq_id seq_id = ubatch.seq_id_unq[s]; + const uint32_t n_writes = state_write_counts[seq_id]; + if (n_writes >= n_blocks) { + continue; + } + if (n_writes + 1 != n_blocks) { + throw std::runtime_error("DSV4 CSA sequence positions are not contiguous"); + } + + uint32_t i = 0; + while (i < ubatch.n_tokens && (ubatch.pos[i] < 0 || !dsv4_token_has_seq(ubatch, i, seq_id))) { + ++i; + } + assert(i < ubatch.n_tokens); + append_dummy_block(seq_id, i); } } } @@ -583,6 +620,63 @@ static llama_kv_cache_dsv4_context::comp_plan dsv4_build_comp_plan( plan.state_persist_dst_idxs.push_back(row.dst); } + + if (n_rs_seq > 0) { + for (uint32_t s = 0; s < ubatch.n_seqs_unq; ++s) { + const llama_seq_id seq_id = ubatch.seq_id_unq[s]; + if (seq_id < 0 || (uint32_t) seq_id >= n_stream) { + continue; + } + + const int64_t stream_off = dsv4_stream_offset(n_stream, seq_id, state_size); + const uint32_t rollback = (uint32_t) seq_id < rs_idx.size() ? rs_idx[seq_id] : 0; + // Keep the restore graph fixed-width when no rollback is pending. + const int64_t src_plane = rollback > 0 && rollback <= n_rs_seq ? (int64_t) rollback*state_rows : 0; + for (uint32_t r = 0; r < state_size; ++r) { + plan.state_restore_src_idxs.push_back((int32_t) (src_plane + stream_off + r)); + plan.state_restore_dst_idxs.push_back((int32_t) (stream_off + r)); + } + + std::vector token_idxs; + token_idxs.reserve(ubatch.n_tokens); + for (uint32_t i = 0; i < ubatch.n_tokens; ++i) { + if (dsv4_token_has_seq(ubatch, i, seq_id)) { + token_idxs.push_back(i); + } + } + if (token_idxs.empty()) { + continue; + } + + const uint32_t n_seq_tokens = (uint32_t) token_idxs.size(); + const int64_t scratch_off = (int64_t) state_rows*(1 + n_rs_seq); + for (uint32_t d = 1; d <= n_rs_seq; ++d) { + const int64_t dst_plane = (int64_t) d*state_rows; + + for (uint32_t r = 0; r < state_size; ++r) { + int32_t src; + if (d <= n_seq_tokens) { + const uint32_t prefix = n_seq_tokens - d; + src = (int32_t) (stream_off + r); + + for (uint32_t j = 0; j < prefix; ++j) { + const uint32_t i_tok = token_idxs[j]; + if (ubatch.pos[i_tok] >= 0 && (uint32_t) (ubatch.pos[i_tok]%state_size) == r) { + src = (int32_t) (scratch_off + i_tok); + } + } + } else { + const int64_t src_plane = (int64_t) (d - n_seq_tokens)*state_rows; + src = (int32_t) (src_plane + stream_off + r); + } + + plan.state_snapshot_src_idxs.push_back(src); + plan.state_snapshot_dst_idxs.push_back((int32_t) (dst_plane + stream_off + r)); + } + } + } + } + static const bool debug = []() { const char * env = getenv("LLAMA_DSV4_COMPRESS_DEBUG"); return env && atoi(env) > 0; @@ -604,12 +698,14 @@ static std::vector dsv4_build_comp_plans bool overlap, uint32_t state_size, uint32_t kv_size, - uint32_t n_stream) { + uint32_t n_stream, + uint32_t n_rs_seq, + const std::vector & rs_idx) { std::vector plans; plans.reserve(ubatches.size()); for (const llama_ubatch & ubatch : ubatches) { - plans.push_back(dsv4_build_comp_plan(ubatch, ratio, overlap, state_size, kv_size, n_stream)); + plans.push_back(dsv4_build_comp_plan(ubatch, ratio, overlap, state_size, kv_size, n_stream, n_rs_seq, rs_idx)); } return plans; @@ -696,7 +792,8 @@ static llama_kv_cache_dsv4_context::comp_plan dsv4_build_reserve_comp_plan( bool overlap, uint32_t state_size, uint32_t kv_size, - uint32_t n_stream) { + uint32_t n_stream, + uint32_t n_rs_seq) { llama_kv_cache_dsv4_context::comp_plan plan; plan.n_visible.resize(ubatch.n_tokens); plan.n_stream = dsv4_comp_graph_n_stream(ubatch, n_stream); @@ -714,10 +811,16 @@ static llama_kv_cache_dsv4_context::comp_plan dsv4_build_reserve_comp_plan( const uint64_t state_rows = (uint64_t) state_size*n_stream; const size_t n_persist = (size_t) std::min(ubatch.n_tokens, state_rows); + const size_t n_restore = n_rs_seq > 0 ? (size_t) state_size*std::max(1, ubatch.n_seqs_unq) : 0; + const size_t n_snapshot = (size_t) n_rs_seq*state_size*std::max(1, ubatch.n_seqs_unq); plan.state_pos .resize(ubatch.n_tokens); plan.state_persist_src_idxs.resize(n_persist); plan.state_persist_dst_idxs.resize(n_persist); + plan.state_restore_src_idxs.resize(n_restore); + plan.state_restore_dst_idxs.resize(n_restore); + plan.state_snapshot_src_idxs.resize(n_snapshot); + plan.state_snapshot_dst_idxs.resize(n_snapshot); plan.state_read_idxs .resize((overlap ? 2u : 1u)*ratio*n_blocks); plan.state_write_idxs.resize(n_blocks); plan.state_write_pos .resize(n_blocks); @@ -743,12 +846,14 @@ llama_dsv4_comp_state::llama_dsv4_comp_state( uint32_t ratio, uint32_t state_size, uint32_t n_embd_state, + uint32_t n_rs_seq, const char * name, const llama_memory_i::layer_filter_cb & filter) : ratio(ratio), state_size(state_size), n_embd_state(n_embd_state), - n_stream(unified ? 1 : n_seq_max) { + n_stream(unified ? 1 : n_seq_max), + n_rs_seq(n_rs_seq) { const llama_hparams & hparams = model.hparams; struct ggml_backend_buft_comparator { @@ -804,8 +909,9 @@ llama_dsv4_comp_state::llama_dsv4_comp_state( throw std::runtime_error("failed to create ggml context for DSV4 compressor state"); } - ggml_tensor * kv = ggml_new_tensor_3d(ctx, GGML_TYPE_F32, n_embd_state, state_size, n_stream); - ggml_tensor * score = ggml_new_tensor_3d(ctx, GGML_TYPE_F32, n_embd_state, state_size, n_stream); + const uint32_t n_planes = n_stream*(1 + n_rs_seq); + ggml_tensor * kv = ggml_new_tensor_3d(ctx, GGML_TYPE_F32, n_embd_state, state_size, n_planes); + ggml_tensor * score = ggml_new_tensor_3d(ctx, GGML_TYPE_F32, n_embd_state, state_size, n_planes); ggml_format_name(kv, "dsv4_%s_state_kv_l%d", name, il); ggml_format_name(score, "dsv4_%s_state_score_l%d", name, il); @@ -837,8 +943,8 @@ llama_dsv4_comp_state::llama_dsv4_comp_state( ctxs_bufs.emplace_back(std::move(ctx), buf); } - LLAMA_LOG_INFO("%s: %s ratio = %u, state = %u x %u, streams = %u, layers = %zu, size = %7.2f MiB\n", - __func__, name, ratio, state_size, n_embd_state, n_stream, layers.size(), total_size()/1024.0/1024.0); + LLAMA_LOG_INFO("%s: %s ratio = %u, state = %u x %u, streams = %u, rs_seq = %u, layers = %zu, size = %7.2f MiB\n", + __func__, name, ratio, state_size, n_embd_state, n_stream, n_rs_seq, layers.size(), total_size()/1024.0/1024.0); } void llama_dsv4_comp_state::clear(llama_seq_id seq_id, bool data) { @@ -848,9 +954,13 @@ void llama_dsv4_comp_state::clear(llama_seq_id seq_id, bool data) { if (seq_id >= 0) { GGML_ASSERT((uint32_t) seq_id < n_stream); + for (const auto & layer : layers) { - dsv4_clear_tensor_stream(layer.kv, (uint32_t) seq_id); - dsv4_clear_tensor_stream(layer.score, (uint32_t) seq_id); + for (uint32_t d = 0; d <= n_rs_seq; ++d) { + const uint32_t stream = d*n_stream + (uint32_t) seq_id; + dsv4_clear_tensor_stream(layer.kv, stream); + dsv4_clear_tensor_stream(layer.score, stream); + } } return; } @@ -868,6 +978,8 @@ void llama_dsv4_comp_state::seq_cp(llama_seq_id seq_id_src, llama_seq_id seq_id_ return; } + clear(seq_id_dst, true); + sc_info.ssrc.push_back((uint32_t) seq_id_src); sc_info.sdst.push_back((uint32_t) seq_id_dst); } @@ -896,6 +1008,14 @@ uint32_t llama_dsv4_comp_state::get_n_stream() const { return n_stream; } +uint32_t llama_dsv4_comp_state::get_n_rs_seq() const { + return n_rs_seq; +} + +uint32_t llama_dsv4_comp_state::get_n_rows() const { + return state_size*n_stream; +} + std::map llama_dsv4_comp_state::memory_breakdown() const { std::map ret; for (const auto & [_, buf] : ctxs_bufs) { @@ -905,13 +1025,26 @@ std::map llama_dsv4_comp_state::memory_break return ret; } -void llama_dsv4_comp_state::state_write(llama_io_write_i & io, llama_seq_id seq_id, llama_state_seq_flags flags) const { +void llama_dsv4_comp_state::state_write( + llama_io_write_i & io, + llama_seq_id seq_id, + llama_state_seq_flags flags, + const std::vector & rs_idx) const { GGML_UNUSED(flags); uint32_t s0; uint32_t ns; dsv4_state_src_stream_range(n_stream, seq_id, s0, ns); + std::vector stream_ids(ns); + for (uint32_t s = 0; s < ns; ++s) { + const uint32_t seq = seq_id >= 0 ? (uint32_t) seq_id : s0 + s; + if (seq >= rs_idx.size() || rs_idx[seq] > n_rs_seq) { + throw std::runtime_error("DSV4 recurrent state rollback index out of range"); + } + stream_ids[s] = rs_idx[seq]*n_stream + s0 + s; + } + const uint32_t version = DSV4_COMP_STATE_VER; const uint32_t n_layer = layers.size(); @@ -925,8 +1058,8 @@ void llama_dsv4_comp_state::state_write(llama_io_write_i & io, llama_seq_id seq_ for (const auto & layer : layers) { io.write(&layer.il, sizeof(layer.il)); - dsv4_state_write_tensor_streams(io, layer.kv, state_size, state_size, s0, ns); - dsv4_state_write_tensor_streams(io, layer.score, state_size, state_size, s0, ns); + dsv4_state_write_tensor_streams(io, layer.kv, state_size, state_size, s0, ns, &stream_ids); + dsv4_state_write_tensor_streams(io, layer.score, state_size, state_size, s0, ns, &stream_ids); } } @@ -972,28 +1105,40 @@ void llama_dsv4_comp_state::state_read(llama_io_read_i & io, llama_seq_id seq_id } } -ggml_tensor * llama_dsv4_comp_state::get_kv(ggml_context * ctx, int32_t il) const { +ggml_tensor * llama_dsv4_comp_state::get_kv_all(ggml_context * ctx, int32_t il) const { const int32_t ids = map_layer_ids.at(il); - ggml_tensor * state = layers[ids].kv; - return ggml_reshape_2d(ctx, state, state->ne[0], state->ne[1]*state->ne[2]); + return ggml_view_2d(ctx, state, state->ne[0], get_n_rows()*(1 + n_rs_seq), state->nb[1], 0); } -ggml_tensor * llama_dsv4_comp_state::get_score(ggml_context * ctx, int32_t il) const { +ggml_tensor * llama_dsv4_comp_state::get_score_all(ggml_context * ctx, int32_t il) const { const int32_t ids = map_layer_ids.at(il); - ggml_tensor * state = layers[ids].score; - return ggml_reshape_2d(ctx, state, state->ne[0], state->ne[1]*state->ne[2]); + return ggml_view_2d(ctx, state, state->ne[0], get_n_rows()*(1 + n_rs_seq), state->nb[1], 0); +} + +ggml_tensor * llama_dsv4_comp_state::get_kv(ggml_context * ctx, int32_t il) const { + ggml_tensor * state = get_kv_all(ctx, il); + const size_t row_size = ggml_row_size(state->type, state->ne[0]); + + return ggml_view_2d(ctx, state, state->ne[0], get_n_rows(), state->nb[1], 0*row_size); +} + +ggml_tensor * llama_dsv4_comp_state::get_score(ggml_context * ctx, int32_t il) const { + ggml_tensor * state = get_score_all(ctx, il); + const size_t row_size = ggml_row_size(state->type, state->ne[0]); + + return ggml_view_2d(ctx, state, state->ne[0], get_n_rows(), state->nb[1], 0*row_size); } ggml_tensor * llama_dsv4_comp_state::cpy_kv(ggml_context * ctx, ggml_tensor * cur, ggml_tensor * idxs, int32_t il) const { - return ggml_set_rows(ctx, get_kv(ctx, il), cur, idxs); + return ggml_set_rows(ctx, get_kv_all(ctx, il), cur, idxs); } ggml_tensor * llama_dsv4_comp_state::cpy_score(ggml_context * ctx, ggml_tensor * cur, ggml_tensor * idxs, int32_t il) const { - return ggml_set_rows(ctx, get_score(ctx, il), cur, idxs); + return ggml_set_rows(ctx, get_score_all(ctx, il), cur, idxs); } size_t llama_dsv4_comp_state::total_size() const { @@ -1022,13 +1167,16 @@ llama_kv_cache_dsv4::llama_kv_cache_dsv4( uint32_t n_seq_max, uint32_t n_ubatch, uint32_t n_pad, + uint32_t n_rs_seq, const layer_filter_cb & filter, const layer_reuse_cb & reuse) : hparams_raw(model.hparams), hparams_csa(model.hparams), hparams_hca(model.hparams), hparams_lid(model.hparams), - n_seq_max(n_seq_max) { + n_seq_max(n_seq_max), + n_rs_seq(n_rs_seq), + rs_idx(n_seq_max, 0) { const layer_filter_cb filter_raw = [&](int32_t il) { if (filter && !filter(il)) { @@ -1043,6 +1191,11 @@ llama_kv_cache_dsv4::llama_kv_cache_dsv4( // Keep DSV4 KV/state streams per sequence even when public KV mode is unified. const bool unified_raw = false; + hparams_raw.n_layer_nextn = 0; + hparams_csa.n_layer_nextn = 0; + hparams_hca.n_layer_nextn = 0; + hparams_lid.n_layer_nextn = 0; + LLAMA_LOG_INFO("%s: creating DSV4 raw KV cache\n", __func__); dsv4_make_k_only(hparams_raw); @@ -1109,19 +1262,19 @@ llama_kv_cache_dsv4::llama_kv_cache_dsv4( csa_state = std::make_unique( model, offload, unified_compressed, n_seq_max, DSV4_CSA_RATIO, 2*DSV4_CSA_RATIO, - 2*model.hparams.n_embd_head_k(), "csa", filter_csa); + 2*model.hparams.n_embd_head_k(), n_rs_seq, "csa", filter_csa); LLAMA_LOG_INFO("%s: creating DSV4 HCA compressor state\n", __func__); hca_state = std::make_unique( model, offload, unified_compressed, n_seq_max, DSV4_HCA_RATIO, DSV4_HCA_RATIO, - model.hparams.n_embd_head_k(), "hca", filter_hca); + model.hparams.n_embd_head_k(), n_rs_seq, "hca", filter_hca); LLAMA_LOG_INFO("%s: creating DSV4 lightning-indexer compressor state\n", __func__); lid_state = std::make_unique( model, offload, unified_compressed, n_seq_max, DSV4_CSA_RATIO, 2*DSV4_CSA_RATIO, - 2*model.hparams.indexer_head_size, "lid", filter_csa); + 2*model.hparams.indexer_head_size, n_rs_seq, "lid", filter_csa); // DSV4 attention reads compressed-K / compressor-state rows that the current // graph does not necessarily overwrite; uninitialized buffer contents would @@ -1255,17 +1408,35 @@ bool llama_kv_cache_dsv4::seq_rm(llama_seq_id seq_id, llama_pos p0, llama_pos p1 } if (p0 > 0) { - if (seq_id < 0 || (uint32_t) seq_id >= n_seq_max || - p0 <= kv_raw->seq_pos_max(seq_id)) { + if (seq_id < 0 || (uint32_t) seq_id >= n_seq_max) { + return false; + } + + const llama_pos pos_max = kv_raw->seq_pos_max(seq_id); + if (p0 > pos_max) { + bool res = true; + + res = res & kv_raw->seq_rm(seq_id, p0, -1); + res = res & kv_csa->seq_rm(seq_id, p0/DSV4_CSA_RATIO, -1); + res = res & kv_hca->seq_rm(seq_id, p0/DSV4_HCA_RATIO, -1); + res = res & kv_lid->seq_rm(seq_id, p0/DSV4_CSA_RATIO, -1); + + return res; + } + + if (n_rs_seq == 0) { return false; } - bool res = true; + const llama_pos rollback = pos_max - (p0 - 1); + if (rollback < 1 || rollback > (llama_pos) n_rs_seq) { + return false; + } - res = res & kv_raw->seq_rm(seq_id, p0, -1); - res = res & kv_csa->seq_rm(seq_id, p0/DSV4_CSA_RATIO, -1); - res = res & kv_hca->seq_rm(seq_id, p0/DSV4_HCA_RATIO, -1); - res = res & kv_lid->seq_rm(seq_id, p0/DSV4_CSA_RATIO, -1); + const bool res = kv_raw->seq_rm(seq_id, p0, p1); + if (res) { + rs_idx[seq_id] = (uint32_t) rollback; + } return res; } @@ -1290,6 +1461,10 @@ void llama_kv_cache_dsv4::seq_cp(llama_seq_id seq_id_src, llama_seq_id seq_id_ds csa_state->seq_cp(seq_id_src, seq_id_dst); hca_state->seq_cp(seq_id_src, seq_id_dst); lid_state->seq_cp(seq_id_src, seq_id_dst); + + if (seq_id_src != seq_id_dst) { + rs_idx[seq_id_dst] = 0; + } } void llama_kv_cache_dsv4::seq_keep(llama_seq_id seq_id) { @@ -1386,9 +1561,9 @@ void llama_kv_cache_dsv4::state_write(llama_io_write_i & io, llama_seq_id seq_id dsv4_state_write_k_cache(io, kv_lid.get(), seq_id, flags, n_rows_lid); } - csa_state->state_write(io, seq_id, flags); - hca_state->state_write(io, seq_id, flags); - lid_state->state_write(io, seq_id, flags); + csa_state->state_write(io, seq_id, flags, rs_idx); + hca_state->state_write(io, seq_id, flags, rs_idx); + lid_state->state_write(io, seq_id, flags, rs_idx); } void llama_kv_cache_dsv4::state_read(llama_io_read_i & io, llama_seq_id seq_id, llama_state_seq_flags flags) { @@ -1432,6 +1607,12 @@ void llama_kv_cache_dsv4::state_read(llama_io_read_i & io, llama_seq_id seq_id, hca_state->state_read(io, seq_id, flags); lid_state->state_read(io, seq_id, flags); + if (seq_id >= 0) { + GGML_ASSERT((uint32_t) seq_id < n_seq_max); + rs_idx[seq_id] = 0; + } else { + std::fill(rs_idx.begin(), rs_idx.end(), 0); + } } llama_kv_cache_iswa * llama_kv_cache_dsv4::get_raw() const { @@ -1462,6 +1643,31 @@ llama_dsv4_comp_state * llama_kv_cache_dsv4::get_lid_state() const { return lid_state.get(); } +uint32_t llama_kv_cache_dsv4::get_n_rs_seq() const { + return n_rs_seq; +} + +const std::vector & llama_kv_cache_dsv4::get_rs_idx() const { + return rs_idx; +} + +void llama_kv_cache_dsv4::reset_rs_idx_for_ubatches(const std::vector & ubatches) { + if (n_rs_seq == 0) { + return; + } + + for (const llama_ubatch & ubatch : ubatches) { + for (uint32_t i = 0; i < ubatch.n_tokens; ++i) { + for (int32_t s = 0; s < ubatch.n_seq_id[i]; ++s) { + const llama_seq_id seq_id = ubatch.seq_id[i][s]; + if (seq_id >= 0 && (uint32_t) seq_id < n_seq_max) { + rs_idx[seq_id] = 0; + } + } + } + } +} + void llama_kv_cache_dsv4::clear_compressed(llama_seq_id seq_id, bool data) { if (seq_id < 0) { kv_csa->clear(data); @@ -1488,6 +1694,12 @@ void llama_kv_cache_dsv4::clear_compressed(llama_seq_id seq_id, bool data) { csa_state->clear(seq_id, data); hca_state->clear(seq_id, data); lid_state->clear(seq_id, data); + + if (seq_id >= 0) { + rs_idx[seq_id] = 0; + } else { + std::fill(rs_idx.begin(), rs_idx.end(), 0); + } } // @@ -1779,10 +1991,14 @@ llama_kv_cache_dsv4_context::llama_kv_cache_dsv4_context( std::vector ubatches_raw) : ubatches(std::move(ubatches)), plans_csa(dsv4_build_comp_plans(this->ubatches, DSV4_CSA_RATIO, true, - kv->get_csa_state()->get_state_size(), kv->get_csa()->get_size(), kv->get_csa_state()->get_n_stream())), + kv->get_csa_state()->get_state_size(), kv->get_csa()->get_size(), kv->get_csa_state()->get_n_stream(), + kv->get_n_rs_seq(), kv->get_rs_idx())), plans_hca(dsv4_build_comp_plans(this->ubatches, DSV4_HCA_RATIO, false, - kv->get_hca_state()->get_state_size(), kv->get_hca()->get_size(), kv->get_hca_state()->get_n_stream())), - plans_lid(plans_csa), + kv->get_hca_state()->get_state_size(), kv->get_hca()->get_size(), kv->get_hca_state()->get_n_stream(), + kv->get_n_rs_seq(), kv->get_rs_idx())), + plans_lid(dsv4_build_comp_plans(this->ubatches, DSV4_CSA_RATIO, true, + kv->get_lid_state()->get_state_size(), kv->get_lid()->get_size(), kv->get_lid_state()->get_n_stream(), + kv->get_n_rs_seq(), kv->get_rs_idx())), ctx_raw(std::make_unique( kv->get_raw(), std::move(sinfos_raw_base_write), @@ -1809,6 +2025,7 @@ llama_kv_cache_dsv4_context::llama_kv_cache_dsv4_context( hca_state(kv->get_hca_state()), lid_state(kv->get_lid_state()), status(ctx_raw->get_status()) { + kv->reset_rs_idx_for_ubatches(this->ubatches); } llama_kv_cache_dsv4_context::~llama_kv_cache_dsv4_context() = default; @@ -1944,7 +2161,7 @@ const llama_kv_cache_dsv4_context::comp_plan & llama_kv_cache_dsv4_context::get_ reserve_plan_csa = dsv4_build_reserve_comp_plan( ubatch, DSV4_CSA_RATIO, true, - csa_state->get_state_size(), get_csa()->get_n_kv(), csa_state->get_n_stream()); + csa_state->get_state_size(), get_csa()->get_n_kv(), csa_state->get_n_stream(), csa_state->get_n_rs_seq()); return reserve_plan_csa; } @@ -1958,7 +2175,7 @@ const llama_kv_cache_dsv4_context::comp_plan & llama_kv_cache_dsv4_context::get_ reserve_plan_hca = dsv4_build_reserve_comp_plan( ubatch, DSV4_HCA_RATIO, false, - hca_state->get_state_size(), get_hca()->get_n_kv(), hca_state->get_n_stream()); + hca_state->get_state_size(), get_hca()->get_n_kv(), hca_state->get_n_stream(), hca_state->get_n_rs_seq()); return reserve_plan_hca; } @@ -1972,7 +2189,7 @@ const llama_kv_cache_dsv4_context::comp_plan & llama_kv_cache_dsv4_context::get_ reserve_plan_lid = dsv4_build_reserve_comp_plan( ubatch, DSV4_CSA_RATIO, true, - lid_state->get_state_size(), get_lid()->get_n_kv(), lid_state->get_n_stream()); + lid_state->get_state_size(), get_lid()->get_n_kv(), lid_state->get_n_stream(), lid_state->get_n_rs_seq()); return reserve_plan_lid; } diff --git a/src/llama-kv-cache-dsv4.h b/src/llama-kv-cache-dsv4.h index 76b1daf57871..ce39867c0342 100644 --- a/src/llama-kv-cache-dsv4.h +++ b/src/llama-kv-cache-dsv4.h @@ -22,6 +22,7 @@ class llama_dsv4_comp_state { uint32_t ratio, uint32_t state_size, uint32_t n_embd_state, + uint32_t n_rs_seq, const char * name, const llama_memory_i::layer_filter_cb & filter); @@ -29,17 +30,21 @@ class llama_dsv4_comp_state { void seq_cp(llama_seq_id seq_id_src, llama_seq_id seq_id_dst); void apply_copies(const stream_copy_info & sc_info) const; - uint32_t get_ratio() const; + uint32_t get_ratio() const; uint32_t get_state_size() const; - uint32_t get_n_stream() const; + uint32_t get_n_stream() const; + uint32_t get_n_rs_seq() const; + uint32_t get_n_rows() const; std::map memory_breakdown() const; - void state_write(llama_io_write_i & io, llama_seq_id seq_id, llama_state_seq_flags flags) const; + void state_write(llama_io_write_i & io, llama_seq_id seq_id, llama_state_seq_flags flags, const std::vector & rs_idx) const; void state_read (llama_io_read_i & io, llama_seq_id seq_id, llama_state_seq_flags flags); - ggml_tensor * get_kv (ggml_context * ctx, int32_t il) const; - ggml_tensor * get_score(ggml_context * ctx, int32_t il) const; + ggml_tensor * get_kv (ggml_context * ctx, int32_t il) const; + ggml_tensor * get_score (ggml_context * ctx, int32_t il) const; + ggml_tensor * get_kv_all (ggml_context * ctx, int32_t il) const; + ggml_tensor * get_score_all(ggml_context * ctx, int32_t il) const; ggml_tensor * cpy_kv (ggml_context * ctx, ggml_tensor * cur, ggml_tensor * idxs, int32_t il) const; ggml_tensor * cpy_score(ggml_context * ctx, ggml_tensor * cur, ggml_tensor * idxs, int32_t il) const; @@ -59,6 +64,7 @@ class llama_dsv4_comp_state { const uint32_t state_size; const uint32_t n_embd_state; const uint32_t n_stream; + const uint32_t n_rs_seq; std::vector> ctxs_bufs; @@ -93,6 +99,7 @@ class llama_kv_cache_dsv4 : public llama_memory_i { uint32_t n_seq_max, uint32_t n_ubatch, uint32_t n_pad, + uint32_t n_rs_seq, const layer_filter_cb & filter, const layer_reuse_cb & reuse); @@ -141,6 +148,10 @@ class llama_kv_cache_dsv4 : public llama_memory_i { llama_dsv4_comp_state * get_hca_state() const; llama_dsv4_comp_state * get_lid_state() const; + uint32_t get_n_rs_seq() const; + const std::vector & get_rs_idx() const; + void reset_rs_idx_for_ubatches(const std::vector & ubatches); + private: llama_hparams hparams_raw; llama_hparams hparams_csa; @@ -148,6 +159,9 @@ class llama_kv_cache_dsv4 : public llama_memory_i { llama_hparams hparams_lid; const uint32_t n_seq_max; + const uint32_t n_rs_seq; + + std::vector rs_idx; std::unique_ptr kv_raw; std::unique_ptr kv_csa; @@ -268,6 +282,17 @@ class llama_kv_cache_dsv4_context : public llama_memory_context_i { std::vector state_persist_src_idxs; std::vector state_persist_dst_idxs; + // Device-side rollback restore copies snapshot planes back to the + // current compressor-state plane before the graph reads it. + std::vector state_restore_src_idxs; + std::vector state_restore_dst_idxs; + + // Device-side rollback snapshots copy rows from the graph-local + // [persistent_state | current_ubatch_scratch] tensor into rollback + // planes after the graph has computed current-token compressor state. + std::vector state_snapshot_src_idxs; + std::vector state_snapshot_dst_idxs; + // Flattened source row ids used for state-backed commits. Source rows // index the graph-local [persistent_state | current_ubatch_scratch] // tensor. For overlapped compression the first half is previous rows diff --git a/src/llama-kv-cache-msa.cpp b/src/llama-kv-cache-msa.cpp new file mode 100644 index 000000000000..55ef286cafa7 --- /dev/null +++ b/src/llama-kv-cache-msa.cpp @@ -0,0 +1,395 @@ +#include "llama-kv-cache-msa.h" + +#include "llama-impl.h" +#include "llama-batch.h" +#include "llama-model.h" + +#include +#include +#include + +// llama_kv_cache_msa + +llama_kv_cache_msa::llama_kv_cache_msa( + const llama_model & model, + ggml_type type_k, + ggml_type type_v, + bool v_trans, + bool offload, + bool unified, + uint32_t kv_size, + uint32_t n_seq_max, + uint32_t n_pad, + uint32_t n_swa, + llama_swa_type swa_type, + const layer_filter_cb & filter, + const layer_filter_cb & filter_idx, + const layer_reuse_cb & reuse) : + hparams_idx(model.hparams), + n_stream(unified ? 1 : n_seq_max), n_seq_max(n_seq_max), n_pad(n_pad), + n_swa(n_swa), swa_type(swa_type) { + + LLAMA_LOG_INFO("%s: creating main KV cache, size = %u cells\n", __func__, kv_size); + + kv_base = std::make_unique( + model, model.hparams, type_k, type_v, + v_trans, offload, unified, kv_size, n_seq_max, n_pad, + n_swa, swa_type, nullptr, filter, reuse, nullptr); + + // the MSA indexer uses a single key head per layer + std::fill(hparams_idx.n_head_kv_arr.begin(), hparams_idx.n_head_kv_arr.end(), 1); + hparams_idx.n_embd_head_k_full = model.hparams.indexer_head_size; + // the rope parameters are kept identical to the main cache + + LLAMA_LOG_INFO("%s: creating indexer KV cache, size = %u cells\n", __func__, kv_size); + + kv_idx = std::make_unique( + model, hparams_idx, type_k, type_v, + v_trans, offload, unified, kv_size, n_seq_max, n_pad, + n_swa, swa_type, nullptr, filter_idx, reuse, nullptr); +} + +void llama_kv_cache_msa::clear(bool data) { + kv_base->clear(data); + kv_idx ->clear(data); +} + +bool llama_kv_cache_msa::seq_rm(llama_seq_id seq_id, llama_pos p0, llama_pos p1) { + bool res = true; + + res = res & kv_base->seq_rm(seq_id, p0, p1); + res = res & kv_idx ->seq_rm(seq_id, p0, p1); + + return res; +} + +void llama_kv_cache_msa::seq_cp(llama_seq_id seq_id_src, llama_seq_id seq_id_dst, llama_pos p0, llama_pos p1) { + kv_base->seq_cp(seq_id_src, seq_id_dst, p0, p1); + kv_idx ->seq_cp(seq_id_src, seq_id_dst, p0, p1); +} + +void llama_kv_cache_msa::seq_keep(llama_seq_id seq_id) { + kv_base->seq_keep(seq_id); + kv_idx ->seq_keep(seq_id); +} + +void llama_kv_cache_msa::seq_add(llama_seq_id seq_id, llama_pos p0, llama_pos p1, llama_pos shift) { + kv_base->seq_add(seq_id, p0, p1, shift); + kv_idx ->seq_add(seq_id, p0, p1, shift); +} + +void llama_kv_cache_msa::seq_div(llama_seq_id seq_id, llama_pos p0, llama_pos p1, int d) { + kv_base->seq_div(seq_id, p0, p1, d); + kv_idx ->seq_div(seq_id, p0, p1, d); +} + +llama_pos llama_kv_cache_msa::seq_pos_min(llama_seq_id seq_id) const { + return kv_base->seq_pos_min(seq_id); +} + +llama_pos llama_kv_cache_msa::seq_pos_max(llama_seq_id seq_id) const { + return kv_base->seq_pos_max(seq_id); +} + +std::map llama_kv_cache_msa::memory_breakdown() const { + std::map mb = kv_base->memory_breakdown(); + for (const auto & buft_size : kv_idx->memory_breakdown()) { + mb[buft_size.first] += buft_size.second; + } + return mb; +} + +llama_memory_context_ptr llama_kv_cache_msa::init_batch( + llama_batch_allocr & balloc, + uint32_t n_ubatch, + bool embd_all) { + GGML_UNUSED(embd_all); + + do { + balloc.split_reset(); + + std::vector ubatches; + while (true) { + auto ubatch = n_stream == 1 ? balloc.split_simple(n_ubatch) : balloc.split_equal(n_ubatch, true, 0); + + if (ubatch.n_tokens == 0) { + break; + } + + ubatches.push_back(std::move(ubatch)); + } + + if (balloc.get_n_used() < balloc.get_n_tokens()) { + // failed to find a suitable split + break; + } + + auto sinfos_base = kv_base->prepare(ubatches); + if (sinfos_base.empty()) { + break; + } + + auto sinfos_idx = kv_idx->prepare(ubatches); + if (sinfos_idx.empty()) { + break; + } + + assert(sinfos_base.size() == sinfos_idx.size()); + + return std::make_unique( + this, std::move(sinfos_base), std::move(sinfos_idx), std::move(ubatches)); + } while (false); + + return std::make_unique(LLAMA_MEMORY_STATUS_FAILED_PREPARE); +} + +llama_memory_context_ptr llama_kv_cache_msa::init_full() { + return std::make_unique(this); +} + +llama_memory_context_ptr llama_kv_cache_msa::init_update(llama_context * lctx, bool optimize) { + return std::make_unique(this, lctx, optimize); +} + +bool llama_kv_cache_msa::get_can_shift() const { + return kv_base->get_can_shift() && + kv_idx ->get_can_shift() && + kv_base->get_size() == kv_idx->get_size(); +} + +void llama_kv_cache_msa::state_write(llama_io_write_i & io, llama_seq_id seq_id, llama_state_seq_flags flags) const { + kv_base->state_write(io, seq_id, flags); + kv_idx ->state_write(io, seq_id, flags); +} + +void llama_kv_cache_msa::state_read(llama_io_read_i & io, llama_seq_id seq_id, llama_state_seq_flags flags) { + kv_base->state_read(io, seq_id, flags); + kv_idx ->state_read(io, seq_id, flags); +} + +llama_kv_cache * llama_kv_cache_msa::get_base() const { + return kv_base.get(); +} + +llama_kv_cache * llama_kv_cache_msa::get_idx() const { + return kv_idx.get(); +} + +// llama_kv_cache_msa_context + +llama_kv_cache_msa_context::llama_kv_cache_msa_context(llama_memory_status status) : + kv(nullptr), status(status) {} + +llama_kv_cache_msa_context::llama_kv_cache_msa_context( + llama_kv_cache_msa * kv) : + kv(kv), + ctx_base(kv->get_base()->init_full()), + ctx_idx (kv->get_idx ()->init_full()), + status(llama_memory_status_combine(ctx_base->get_status(), ctx_idx->get_status())) { +} + +llama_kv_cache_msa_context::llama_kv_cache_msa_context( + llama_kv_cache_msa * kv, + llama_context * lctx, + bool optimize) : + kv(kv), + ctx_base(kv->get_base()->init_update(lctx, optimize)), + ctx_idx (kv->get_idx ()->init_update(lctx, optimize)), + status(llama_memory_status_combine(ctx_base->get_status(), ctx_idx->get_status())) { +} + +llama_kv_cache_msa_context::llama_kv_cache_msa_context( + llama_kv_cache_msa * kv, + slot_info_vec_t sinfos_base, + slot_info_vec_t sinfos_idx, + std::vector ubatches) : + kv(kv), + ubatches(std::move(ubatches)), + // here we copy the ubatches. not sure if this is ideal + ctx_base(new llama_kv_cache_context(kv->get_base(), std::move(sinfos_base), this->ubatches)), + ctx_idx (new llama_kv_cache_context(kv->get_idx (), std::move(sinfos_idx), this->ubatches)), + status(llama_memory_status_combine(ctx_base->get_status(), ctx_idx->get_status())) { +} + +llama_kv_cache_msa_context::~llama_kv_cache_msa_context() = default; + +bool llama_kv_cache_msa_context::next() { + assert(status == LLAMA_MEMORY_STATUS_SUCCESS); + + ctx_base->next(); + ctx_idx ->next(); + + if (++i_next >= ubatches.size()) { + return false; + } + + return true; +} + +bool llama_kv_cache_msa_context::apply() { + assert(!llama_memory_status_is_fail(status)); + + bool res = true; + + res = res & ctx_base->apply(); + res = res & ctx_idx ->apply(); + + return res; +} + +llama_memory_status llama_kv_cache_msa_context::get_status() const { + return status; +} + +const llama_ubatch & llama_kv_cache_msa_context::get_ubatch() const { + assert(status == LLAMA_MEMORY_STATUS_SUCCESS); + + return ubatches[i_next]; +} + +const llama_kv_cache_context * llama_kv_cache_msa_context::get_base() const { + assert(status == LLAMA_MEMORY_STATUS_SUCCESS); + + return static_cast(ctx_base.get()); +} + +const llama_kv_cache_context * llama_kv_cache_msa_context::get_idx() const { + assert(status == LLAMA_MEMORY_STATUS_SUCCESS); + + return static_cast(ctx_idx.get()); +} + +uint32_t llama_kv_cache_msa_context::get_n_pos() const { + // pad the value so that the graph remains constant across batches and can be reused + const uint32_t n_pad_cur = std::max(kv->get_n_pad(), 256u); + + llama_pos pos_max = -1; + + for (llama_seq_id seq_id = 0; seq_id < (llama_seq_id) kv->get_n_seq_max(); ++seq_id) { + pos_max = std::max(pos_max, kv->seq_pos_max(seq_id)); + } + + return std::max(n_pad_cur, GGML_PAD((uint32_t) (pos_max + 1), n_pad_cur)); +} + +void llama_kv_cache_msa_context::set_input_cell_pos(ggml_tensor * dst, const llama_ubatch * ubatch, int32_t div) const { + GGML_ASSERT(ggml_backend_buffer_is_host(dst->buffer)); + GGML_ASSERT(dst->type == GGML_TYPE_I32); + GGML_ASSERT(div > 0); + + const int64_t n_tokens = ubatch->n_tokens; + const int64_t n_kv = dst->ne[0]; + const int64_t n_stream_ub = dst->ne[1]; + + GGML_ASSERT(n_tokens % n_stream_ub == 0); + const int64_t n_tps = n_tokens/n_stream_ub; + + int32_t * data = (int32_t *) dst->data; + + for (int64_t s = 0; s < n_stream_ub; ++s) { + const llama_seq_id seq_id = ubatch->seq_id[s*n_tps][0]; + + const auto & cells = kv->get_base()->get_cells(seq_id); + + for (int64_t j = 0; j < n_kv; ++j) { + // the value for empty or other-sequence cells is irrelevant as consumers mask them + data[s*n_kv + j] = + cells.is_empty(j) || !cells.seq_has(j, seq_id) + ? 0 + : (int32_t) (cells.pos_get(j)/div); + } + } +} + +void llama_kv_cache_msa_context::set_input_pos_slot(ggml_tensor * dst, const llama_ubatch * ubatch) const { + GGML_ASSERT(ggml_backend_buffer_is_host(dst->buffer)); + GGML_ASSERT(dst->type == GGML_TYPE_I32 || dst->type == GGML_TYPE_F32); + + const int64_t n_tokens = ubatch->n_tokens; + const int64_t n_pos = dst->ne[0]; + const int64_t n_stream_ub = dst->ne[1]; + + GGML_ASSERT(n_tokens % n_stream_ub == 0); + const int64_t n_tps = n_tokens/n_stream_ub; + + for (int64_t s = 0; s < n_stream_ub; ++s) { + const llama_seq_id seq_id = ubatch->seq_id[s*n_tps][0]; + + const auto & cells = kv->get_base()->get_cells(seq_id); + + std::vector map(n_pos, 0); + + for (uint32_t j = 0; j < cells.size(); ++j) { + if (cells.is_empty(j) || !cells.seq_has(j, seq_id)) { + continue; + } + + const llama_pos p0 = cells.pos_get(j); + + if (p0 < 0 || p0 >= n_pos) { + continue; + } + + map[p0] = (int32_t) j; + } + + if (dst->type == GGML_TYPE_I32) { + int32_t * data = (int32_t *) dst->data + s*n_pos; + std::copy(map.begin(), map.end(), data); + } else { + float * data = (float *) dst->data + s*n_pos; + for (int64_t p = 0; p < n_pos; ++p) { + data[p] = (float) map[p]; + } + } + } +} + +void llama_kv_cache_msa_context::set_input_pos_mask(ggml_tensor * dst, const llama_ubatch * ubatch) const { + GGML_ASSERT(ggml_backend_buffer_is_host(dst->buffer)); + GGML_ASSERT(dst->type == GGML_TYPE_F32); + + const int64_t n_tokens = ubatch->n_tokens; + const int64_t n_pos = dst->ne[0]; + + GGML_ASSERT(dst->ne[1] == n_tokens); + + const uint32_t n_swa = kv->get_n_swa(); + const llama_swa_type swa_type = kv->get_swa_type(); + + float * data = (float *) dst->data; + + std::fill(data, data + n_pos*n_tokens, -INFINITY); + + for (int64_t i = 0; i < n_tokens; ++i) { + const llama_seq_id seq_id = ubatch->seq_id[i][0]; + + const auto & cells = kv->get_base()->get_cells(seq_id); + + const llama_pos p1 = ubatch->pos[i]; + + for (uint32_t j = 0; j < cells.size(); ++j) { + if (cells.is_empty(j) || !cells.seq_has(j, seq_id)) { + continue; + } + + const llama_pos p0 = cells.pos_get(j); + + if (p0 < 0 || p0 >= n_pos) { + continue; + } + + // causal mask + if (p0 > p1) { + continue; + } + + // apply SWA if any + if (llama_hparams::is_masked_swa(n_swa, swa_type, p0, p1)) { + continue; + } + + data[i*n_pos + p0] = 0.0f; + } + } +} diff --git a/src/llama-kv-cache-msa.h b/src/llama-kv-cache-msa.h new file mode 100644 index 000000000000..f09b6d32b044 --- /dev/null +++ b/src/llama-kv-cache-msa.h @@ -0,0 +1,153 @@ +#pragma once + +#include "llama-kv-cache.h" + +#include + +// llama_kv_cache_msa + +// uses two instances of llama_kv_cache, one for K/V tensors, and one for the MSA indexer tensors +// both receive identical sequence operations and identical ubatches, so their cell layouts stay in synced. +// the context also exposes per-ubatch pos - cell translation maps populated from llama_kv_cells via +// llama_kv_cache::get_cells(), which the model graph uses to run MSA block selection in position space + +class llama_kv_cache_msa : public llama_memory_i { +public: + llama_kv_cache_msa( + const llama_model & model, + ggml_type type_k, + ggml_type type_v, + bool v_trans, + bool offload, + bool unified, + uint32_t kv_size, + uint32_t n_seq_max, + uint32_t n_pad, + uint32_t n_swa, + llama_swa_type swa_type, + const layer_filter_cb & filter, + const layer_filter_cb & filter_idx, + const layer_reuse_cb & reuse); + + ~llama_kv_cache_msa() = default; + + // llama_memory_i + + llama_memory_context_ptr init_batch( + llama_batch_allocr & balloc, + uint32_t n_ubatch, + bool embd_all) override; + + llama_memory_context_ptr init_full() override; + + llama_memory_context_ptr init_update(llama_context * lctx, bool optimize) override; + + bool get_can_shift() const override; + + void clear(bool data) override; + + bool seq_rm (llama_seq_id seq_id, llama_pos p0, llama_pos p1) override; + void seq_cp (llama_seq_id seq_id_src, llama_seq_id seq_id_dst, llama_pos p0, llama_pos p1) override; + void seq_keep(llama_seq_id seq_id) override; + void seq_add (llama_seq_id seq_id, llama_pos p0, llama_pos p1, llama_pos shift) override; + void seq_div (llama_seq_id seq_id, llama_pos p0, llama_pos p1, int d) override; + + llama_pos seq_pos_min(llama_seq_id seq_id) const override; + llama_pos seq_pos_max(llama_seq_id seq_id) const override; + + std::map memory_breakdown() const override; + + // state write/load + + void state_write(llama_io_write_i & io, llama_seq_id seq_id = -1, llama_state_seq_flags flags = 0) const override; + void state_read (llama_io_read_i & io, llama_seq_id seq_id = -1, llama_state_seq_flags flags = 0) override; + + // llama_kv_cache_msa specific API + + llama_kv_cache * get_base() const; + llama_kv_cache * get_idx () const; + + uint32_t get_n_pad() const { return n_pad; } + uint32_t get_n_seq_max() const { return n_seq_max; } + uint32_t get_n_swa() const { return n_swa; } + llama_swa_type get_swa_type() const { return swa_type; } + +private: + // keep the indexer KV cache hparams instance here as llama_kv_cache stores only a reference + llama_hparams hparams_idx; + + const uint32_t n_stream = 1; + const uint32_t n_seq_max = 1; + const uint32_t n_pad = 1; + + const uint32_t n_swa = 0; + const llama_swa_type swa_type = LLAMA_SWA_TYPE_NONE; + + std::unique_ptr kv_base; + std::unique_ptr kv_idx; +}; + +class llama_kv_cache_msa_context : public llama_memory_context_i { +public: + using slot_info_vec_t = llama_kv_cache::slot_info_vec_t; + + // used for errors + llama_kv_cache_msa_context(llama_memory_status status); + + // used to create a full-cache context + llama_kv_cache_msa_context( + llama_kv_cache_msa * kv); + + // used to create an update context + llama_kv_cache_msa_context( + llama_kv_cache_msa * kv, + llama_context * lctx, + bool optimize); + + // used to create a batch processing context from a batch + llama_kv_cache_msa_context( + llama_kv_cache_msa * kv, + slot_info_vec_t sinfos_base, + slot_info_vec_t sinfos_idx, + std::vector ubatches); + + virtual ~llama_kv_cache_msa_context(); + + // llama_memory_context_i + + bool next() override; + bool apply() override; + + llama_memory_status get_status() const override; + const llama_ubatch & get_ubatch() const override; + + // llama_kv_cache_msa_context specific API + + const llama_kv_cache_context * get_base() const; + const llama_kv_cache_context * get_idx () const; + + // max position currently present in the cache plus one, padded MSA blocks are defined over token positions + // so the block-selection tensors are sized by this value rather than by the number of cells + uint32_t get_n_pos() const; + + // position <-> cell translation maps, populated from the base cache cells + // the model graph relates cache contents to token positions only through these per ubatch inputs + // value for empty or other-sequence cells is 0 so consumers must mask them + void set_input_cell_pos(ggml_tensor * dst, const llama_ubatch * ubatch, int32_t div) const; + // positions without a cell map to cell 0, consumers must mask them assumes one sequence per stream + void set_input_pos_slot(ggml_tensor * dst, const llama_ubatch * ubatch) const; + void set_input_pos_mask(ggml_tensor * dst, const llama_ubatch * ubatch) const; + +private: + llama_kv_cache_msa * kv; + + // the index of the next ubatch to process + size_t i_next = 0; + + std::vector ubatches; + + const llama_memory_context_ptr ctx_base; + const llama_memory_context_ptr ctx_idx; + + const llama_memory_status status; +}; diff --git a/src/llama-kv-cache.cpp b/src/llama-kv-cache.cpp index 44cb1668dacf..8678a326d9ee 100644 --- a/src/llama-kv-cache.cpp +++ b/src/llama-kv-cache.cpp @@ -112,7 +112,7 @@ llama_kv_cache::llama_kv_cache( auto it = ctx_map.find(buft); if (it == ctx_map.end()) { ggml_init_params params = { - /*.mem_size =*/ size_t(3u*(1 + n_stream)*n_layer*ggml_tensor_overhead()), //Reserve tensor metadata for up to 3 tensors per layer (K, V, and optional K_idx), plus one view per tensor per stream. + /*.mem_size =*/ size_t(2u*(1 + n_stream)*n_layer*ggml_tensor_overhead()), /*.mem_buffer =*/ NULL, /*.no_alloc =*/ true, }; @@ -242,25 +242,9 @@ llama_kv_cache::llama_kv_cache( v_stream.push_back(has_v ? ggml_view_2d(ctx, v, n_embd_v_gqa, kv_size, v->nb[1], s*v->nb[2]) : nullptr); } - const uint32_t n_embd_k_idx = hparams.n_embd_k_idx(il); - ggml_tensor * k_idx = n_embd_k_idx > 0 - ? ggml_new_tensor_3d(ctx, GGML_TYPE_F32, n_embd_k_idx, kv_size, n_stream) - : nullptr; - if (k_idx) { - ggml_format_name(k_idx, "cache_k_idx_l%d", il); - msa_strict_slots = (n_stream == n_seq_max); - } - - std::vector k_idx_stream; - for (uint32_t s = 0; s < n_stream; ++s) { - k_idx_stream.push_back(k_idx - ? ggml_view_2d(ctx, k_idx, n_embd_k_idx, kv_size, k_idx->nb[1], s*k_idx->nb[2]) - : nullptr); - } - map_layer_ids[il] = layers.size(); - layers.push_back({ il, k, v, k_idx, k_stream, v_stream, k_idx_stream }); + layers.push_back({ il, k, v, k_stream, v_stream, }); } if (reuse) { @@ -309,24 +293,13 @@ llama_kv_cache::llama_kv_cache( } { - const size_t memory_size_k = size_k_bytes(); - const size_t memory_size_v = size_v_bytes(); - const size_t memory_size_k_idx = size_k_idx_bytes(); - const size_t memory_size_total = memory_size_k + memory_size_v + memory_size_k_idx; - - constexpr float mib = 1024.0f * 1024.0f; - - const std::string k_log = format(", K (%s): %7.2f MiB", ggml_type_name(type_k), (float) memory_size_k / mib); - const std::string v_log = format(", V (%s): %7.2f MiB", ggml_type_name(type_v), (float) memory_size_v / mib); - - std::string k_idx_log; - if (memory_size_k_idx > 0) { - k_idx_log = format(", K_idx (%s): %7.2f MiB", ggml_type_name(GGML_TYPE_F32), (float) memory_size_k_idx / mib); - } + const size_t memory_size_k = size_k_bytes(); + const size_t memory_size_v = size_v_bytes(); - LLAMA_LOG_INFO("%s: size = %7.2f MiB (%6u cells, %3d layers, %2u/%u seqs)%s%s%s\n", __func__, - (float) memory_size_total / mib, kv_size, (int) layers.size(), n_seq_max, n_stream, - k_log.c_str(), v_log.c_str(), k_idx_log.c_str()); + LLAMA_LOG_INFO("%s: size = %7.2f MiB (%6u cells, %3d layers, %2u/%u seqs), K (%s): %7.2f MiB, V (%s): %7.2f MiB\n", __func__, + (float)(memory_size_k + memory_size_v) / (1024.0f * 1024.0f), kv_size, (int) layers.size(), n_seq_max, n_stream, + ggml_type_name(type_k), (float)memory_size_k / (1024.0f * 1024.0f), + ggml_type_name(type_v), (float)memory_size_v / (1024.0f * 1024.0f)); } // TODO: refactor [TAG_KV_CACHE_SHARE_CELLS] @@ -419,39 +392,6 @@ bool llama_kv_cache::seq_rm(llama_seq_id seq_id, llama_pos p0, llama_pos p1) { p1 = std::numeric_limits::max(); } - // empty range - nothing to remove - if (p0 >= p1) { - return true; - } - - // MSA anchors block selection to absolute cache slots (slot == position). Tail trim and full removal preserve this invariant, but removing a prefix - // or middle range would free slots while later cells survive, desynchronizing the indexer cache. Reject such removals before modifying the cache. - if (msa_strict_slots) { - for (llama_seq_id sid = 0; sid < (llama_seq_id) seq_to_stream.size(); ++sid) { - if (seq_id >= 0 && sid != seq_id) { - continue; - } - - const auto & cells = v_cells[seq_to_stream[sid]]; - - const llama_pos pmin = cells.seq_pos_min(sid); - const llama_pos pmax = cells.seq_pos_max(sid); - - if (pmin < 0) { - continue; // empty sequence - } - - const bool overlaps = p0 <= pmax && p1 > pmin; // the range removes something - const bool leaves_tail = p1 <= pmax; // cells beyond the range survive - - if (overlaps && leaves_tail) { - LLAMA_LOG_WARN("%s: MSA: partial (non-suffix) removal [%d, %d) for seq %d is not supported " - "(block selection is anchored to cache slots) - rejected\n", __func__, p0, p1, sid); - return false; - } - } - } - if (seq_id >= 0) { auto & cells = v_cells[seq_to_stream[seq_id]]; auto & head = v_heads[seq_to_stream[seq_id]]; @@ -906,10 +846,6 @@ bool llama_kv_cache::update(llama_context * lctx, bool do_shift, const stream_co if (layer.v_stream[ssrc]) { ggml_backend_tensor_copy(layer.v_stream[ssrc], layer.v_stream[sdst]); } - if (layer.k_idx_stream[ssrc]) { - GGML_ASSERT(layer.k_idx_stream[sdst]); - ggml_backend_tensor_copy(layer.k_idx_stream[ssrc], layer.k_idx_stream[sdst]); - } } } } @@ -1058,44 +994,6 @@ llama_kv_cache::slot_info llama_kv_cache::find_slot(const llama_ubatch & ubatch, const auto & cells = v_cells[seq_to_stream[seq_id]]; - if (n_tokens > cells.size()) { - LLAMA_LOG_ERROR("%s: n_tokens = %d > size = %u\n", __func__, n_tokens, cells.size()); - return { }; - } - - // MSA block selection assumes slot == logical position (append-only streams). - if (msa_strict_slots) { - for (uint32_t ii = 0; ii < n_tokens; ++ii) { - const llama_pos pos = ubatch.pos[s*n_tokens + ii]; - - if (pos < 0 || (uint64_t) pos >= cells.size()) { - LLAMA_LOG_WARN("%s: MSA: position %d is outside the cache range [0, %u)\n", - __func__, pos, cells.size()); - return { }; - } - - const uint32_t idx = (uint32_t) pos; - - if (!cells.is_empty(idx)) { - LLAMA_LOG_WARN("%s: MSA: required slot %u is already occupied (stream %u)\n", - __func__, idx, seq_to_stream[seq_id]); - return { }; - } - - // strictly increasing positions, rules out duplicates and, for contiguous requests, is tightened to exact adjacency - if (!res.idxs[s].empty() && (cont ? idx != res.idxs[s].back() + 1 - : idx <= res.idxs[s].back())) { - LLAMA_LOG_WARN("%s: MSA: token positions are not %s within the ubatch\n", - __func__, cont ? "contiguous" : "strictly increasing"); - return { }; - } - - res.idxs[s].push_back(idx); - } - - continue; - } - uint32_t head_cur = v_heads[seq_to_stream[seq_id]]; // if we have enough unused cells before the current head -> @@ -1104,6 +1002,11 @@ llama_kv_cache::slot_info llama_kv_cache::find_slot(const llama_ubatch & ubatch, head_cur = 0; } + if (n_tokens > cells.size()) { + LLAMA_LOG_ERROR("%s: n_tokens = %d > size = %u\n", __func__, n_tokens, cells.size()); + return { }; + } + uint32_t n_tested = 0; // for continuous slots, we test that all tokens in the ubatch fit, starting from the current head @@ -1210,15 +1113,6 @@ void llama_kv_cache::apply_ubatch(const slot_info & sinfo, const llama_ubatch & const auto idx = sinfo.idxs[s][ii]; - if (msa_strict_slots && (llama_pos) idx != ubatch.pos[i]) { - LLAMA_LOG_ERROR("%s: MSA slot/position invariant violated: " - "writing pos %d into cell %u (stream %u). The indexer cache " - "would desync and block selection would silently corrupt. " - "This is a bug, please report it with reproduction steps.\n", - __func__, ubatch.pos[i], idx, sinfo.strm[s]); - GGML_ABORT("MSA: slot != pos"); - } - if (!cells.is_empty(idx)) { assert(cells.seq_count(idx) == 1); @@ -1262,8 +1156,7 @@ void llama_kv_cache::apply_ubatch(const slot_info & sinfo, const llama_ubatch & LLAMA_LOG_DEBUG("%s: purging positions [%d, %d] of sequence %d from KV cache\n", __func__, cells.seq_pos_min(s), seq_pos_max_rm[s], s); - // under MSA strict slots this path should be unreachable, since strict MSA placement never selects occupied cells - GGML_ASSERT(seq_rm(s, cells.seq_pos_min(s), seq_pos_max_rm[s] + 1)); + seq_rm(s, cells.seq_pos_min(s), seq_pos_max_rm[s] + 1); } } @@ -1283,12 +1176,6 @@ bool llama_kv_cache::get_can_shift() const { if (hparams.n_pos_per_embd() > 1) { return false; } - // shifting would leave k_idx stale - for (const auto & layer : layers) { - if (layer.k_idx) { - return false; - } - } return true; } @@ -1337,6 +1224,12 @@ ggml_tensor * llama_kv_cache::get_k_storage(int32_t il) const { return layers[ikv].k; } +const llama_kv_cells & llama_kv_cache::get_cells(llama_seq_id seq_id) const { + GGML_ASSERT(seq_id >= 0 && (size_t) seq_id < seq_to_stream.size()); + + return v_cells[seq_to_stream[seq_id]]; +} + uint32_t llama_kv_cache::get_n_kv(const slot_info & sinfo) const { uint32_t result = 0; @@ -1405,23 +1298,6 @@ ggml_tensor * llama_kv_cache::get_v(ggml_context * ctx, int32_t il, uint32_t n_k ggml_row_size(v->type, kv_size*n_embd_v_gqa)*sinfo.s0); } -ggml_tensor * llama_kv_cache::get_k_idx(ggml_context * ctx, int32_t il, uint32_t n_kv, const slot_info & sinfo) const { - const int32_t ikv = map_layer_ids.at(il); - auto * k_idx = layers[ikv].k_idx; - GGML_ASSERT(k_idx); - - const uint64_t kv_size = get_size(); - const int64_t n_idx = k_idx->ne[0]; // 128 - const uint32_t ns = sinfo.s1 - sinfo.s0 + 1; - - return ggml_view_4d(ctx, k_idx, - n_idx, 1, n_kv, ns, - ggml_row_size(k_idx->type, n_idx), // nb1 (single head) - ggml_row_size(k_idx->type, n_idx), // nb2 (per cell) - ggml_row_size(k_idx->type, n_idx*kv_size), // nb3 (per stream) - ggml_row_size(k_idx->type, n_idx*kv_size)*sinfo.s0); -} - ggml_tensor * llama_kv_cache::cpy_k(ggml_context * ctx, ggml_tensor * k_cur, ggml_tensor * k_idxs, int32_t il, const slot_info & sinfo) const { GGML_UNUSED(sinfo); @@ -1523,28 +1399,6 @@ ggml_tensor * llama_kv_cache::build_input_k_idxs(ggml_context * ctx, const llama return k_idxs; } -ggml_tensor * llama_kv_cache::cpy_k_idx(ggml_context * ctx, ggml_tensor * k_idx_cur, ggml_tensor * k_idxs, int32_t il, const slot_info & sinfo) const { - GGML_UNUSED(sinfo); - const int32_t ikv = map_layer_ids.at(il); - ggml_tensor * k_idx = layers[ikv].k_idx; - GGML_ASSERT(k_idx && "cpy_k_idx on a layer with no indexer cache"); - - const int64_t n_embd_head = k_idx_cur->ne[0]; // 128 - const int64_t n_head = k_idx_cur->ne[1]; // 1 - const int64_t n_tokens = k_idx_cur->ne[2]; - const int64_t n_embd_gqa = n_embd_head*n_head; // 128 - - GGML_ASSERT(ggml_row_size(k_idx_cur->type, n_embd_head) == k_idx_cur->nb[1]); - k_idx_cur = ggml_view_2d(ctx, k_idx_cur, n_embd_gqa, n_tokens, k_idx_cur->nb[2], 0); - - const int64_t n_stream = k_idx->ne[2]; - if (n_stream > 1) { - const int64_t kv_size = get_size(); - k_idx = ggml_reshape_2d(ctx, k_idx, n_embd_gqa, kv_size*n_stream); - } - return ggml_set_rows(ctx, k_idx, k_idx_cur, k_idxs); // same k_idxs as the K store -} - ggml_tensor * llama_kv_cache::build_input_v_idxs(ggml_context * ctx, const llama_ubatch & ubatch) const { const uint32_t n_tokens = ubatch.n_tokens; @@ -1979,18 +1833,6 @@ size_t llama_kv_cache::size_v_bytes() const { return size_v_bytes; } -size_t llama_kv_cache::size_k_idx_bytes() const { - size_t size_k_idx_bytes = 0; - - for (const auto & layer : layers) { - if (layer.k_idx) { - size_k_idx_bytes += ggml_nbytes(layer.k_idx); - } - } - - return size_k_idx_bytes; -} - ggml_tensor * llama_kv_cache::build_rope_shift( const llama_cparams & cparams, ggml_context * ctx, @@ -2303,36 +2145,6 @@ void llama_kv_cache::state_write_data(llama_io_write_i & io, const cell_ranges_t } } - if (size_k_idx_bytes() > 0) { - const uint32_t has_k_idx_u32 = 1; - io.write(&has_k_idx_u32, sizeof(has_k_idx_u32)); - - for (const auto & layer : layers) { - const uint32_t layer_has_k_idx = layer.k_idx ? 1 : 0; - io.write(&layer_has_k_idx, sizeof(layer_has_k_idx)); - - if (!layer_has_k_idx) { - continue; - } - - GGML_ASSERT(layer.k_idx_stream[cr.strm]); - - const int32_t k_idx_type_i = (int32_t) layer.k_idx->type; - io.write(&k_idx_type_i, sizeof(k_idx_type_i)); - - const uint64_t k_idx_size_row = ggml_row_size(layer.k_idx->type, layer.k_idx->ne[0]); - io.write(&k_idx_size_row, sizeof(k_idx_size_row)); - - for (const auto & range : cr.data) { - const size_t range_size = range.second - range.first; - const size_t buf_size = range_size * k_idx_size_row; - const size_t offset = range.first * k_idx_size_row; - - io.write_tensor(layer.k_idx_stream[cr.strm], offset, buf_size); - } - } - } - if (!v_trans) { for (const auto & layer : layers) { const uint32_t il = layer.il; @@ -2581,68 +2393,6 @@ bool llama_kv_cache::state_read_data(llama_io_read_i & io, uint32_t strm, uint32 } } - if (size_k_idx_bytes() > 0) { - uint32_t has_k_idx_u32 = 0; - io.read(&has_k_idx_u32, sizeof(has_k_idx_u32)); - - if (has_k_idx_u32 != 1) { - LLAMA_LOG_ERROR("%s: missing k_idx data in KV cache state\n", __func__); - return false; - } - - for (const auto & layer : layers) { - uint32_t layer_has_k_idx = 0; - io.read(&layer_has_k_idx, sizeof(layer_has_k_idx)); - - const uint32_t expected_layer_has_k_idx = layer.k_idx ? 1 : 0; - - if (layer_has_k_idx != expected_layer_has_k_idx) { - LLAMA_LOG_ERROR( - "%s: mismatched k_idx state for layer: got %u, expected %u\n", - __func__, layer_has_k_idx, expected_layer_has_k_idx); - return false; - } - - if (!layer_has_k_idx) { - continue; - } - - GGML_ASSERT(layer.k_idx_stream[strm]); - - int32_t k_idx_type_i = -1; - io.read(&k_idx_type_i, sizeof(k_idx_type_i)); - - if (k_idx_type_i != (int32_t) layer.k_idx->type) { - LLAMA_LOG_ERROR( - "%s: mismatched k_idx type: got %d, expected %d\n", - __func__, k_idx_type_i, (int32_t) layer.k_idx->type); - return false; - } - - uint64_t k_idx_size_row = 0; - io.read(&k_idx_size_row, sizeof(k_idx_size_row)); - - const uint64_t expected_k_idx_size_row = ggml_row_size(layer.k_idx->type, layer.k_idx->ne[0]); - - if (k_idx_size_row != expected_k_idx_size_row) { - LLAMA_LOG_ERROR( - "%s: mismatched k_idx row size: got %zu, expected %zu\n", - __func__, (size_t) k_idx_size_row, (size_t) expected_k_idx_size_row); - return false; - } - - if (cell_count) { - if (sinfo.is_contiguous()) { - io.read_tensor(layer.k_idx_stream[strm], sinfo.head() * k_idx_size_row, cell_count * k_idx_size_row); - } else { - for (uint32_t i = 0; i < cell_count; ++i) { - io.read_tensor(layer.k_idx_stream[strm], sinfo.idxs[0][i] * k_idx_size_row, k_idx_size_row); - } - } - } - } - } - if (!this->v_trans) { for (const auto & layer : layers) { const uint32_t il = layer.il; @@ -2844,10 +2594,6 @@ ggml_tensor * llama_kv_cache_context::get_v(ggml_context * ctx, int32_t il) cons return kv->get_v(ctx, il, n_kv, sinfos[i_cur]); } -ggml_tensor * llama_kv_cache_context::get_k_idx(ggml_context * ctx, int32_t il) const { - return kv->get_k_idx(ctx, il, n_kv, sinfos[i_cur]); -} - ggml_tensor * llama_kv_cache_context::cpy_k(ggml_context * ctx, ggml_tensor * k_cur, ggml_tensor * k_idxs, int32_t il) const { return kv->cpy_k(ctx, k_cur, k_idxs, il, sinfos[i_cur]); } @@ -2856,10 +2602,6 @@ ggml_tensor * llama_kv_cache_context::cpy_v(ggml_context * ctx, ggml_tensor * v_ return kv->cpy_v(ctx, v_cur, v_idxs, il, sinfos[i_cur]); } -ggml_tensor * llama_kv_cache_context::cpy_k_idx(ggml_context * ctx, ggml_tensor * k_idx_cur, ggml_tensor * k_idxs, int32_t il) const { - return kv->cpy_k_idx(ctx, k_idx_cur, k_idxs, il, sinfos[i_cur]); -} - ggml_tensor * llama_kv_cache_context::build_input_k_idxs(ggml_context * ctx, const llama_ubatch & ubatch) const { return kv->build_input_k_idxs(ctx, ubatch); } diff --git a/src/llama-kv-cache.h b/src/llama-kv-cache.h index d5a92f4405b5..6cb6dbd2f984 100644 --- a/src/llama-kv-cache.h +++ b/src/llama-kv-cache.h @@ -164,6 +164,8 @@ class llama_kv_cache : public llama_memory_i { std::vector get_layer_ids() const; ggml_tensor * get_k_storage(int32_t il) const; + const llama_kv_cells & get_cells(llama_seq_id seq_id) const; + // // graph_build API // @@ -173,12 +175,10 @@ class llama_kv_cache : public llama_memory_i { // get views of the current state of the cache ggml_tensor * get_k(ggml_context * ctx, int32_t il, uint32_t n_kv, const slot_info & sinfo) const; ggml_tensor * get_v(ggml_context * ctx, int32_t il, uint32_t n_kv, const slot_info & sinfo) const; - ggml_tensor * get_k_idx(ggml_context * ctx, int32_t il, uint32_t n_kv, const slot_info & sinfo) const; // store k_cur and v_cur in the cache based on the provided head location ggml_tensor * cpy_k(ggml_context * ctx, ggml_tensor * k_cur, ggml_tensor * k_idxs, int32_t il, const slot_info & sinfo) const; ggml_tensor * cpy_v(ggml_context * ctx, ggml_tensor * v_cur, ggml_tensor * v_idxs, int32_t il, const slot_info & sinfo) const; - ggml_tensor * cpy_k_idx(ggml_context * ctx, ggml_tensor * k_idx_cur, ggml_tensor * k_idxs, int32_t il, const slot_info & sinfo) const; // // preparation API @@ -230,11 +230,9 @@ class llama_kv_cache : public llama_memory_i { ggml_tensor * k; ggml_tensor * v; - ggml_tensor * k_idx; // MSA single-head indexer keys, F32 std::vector k_stream; std::vector v_stream; - std::vector k_idx_stream; }; bool v_trans = true; // the value tensor is transposed @@ -263,9 +261,6 @@ class llama_kv_cache : public llama_memory_i { // env: LLAMA_KV_CACHE_DEBUG int debug = 0; - // set when a k_idx (indexer) cache exists and the stream layout supports MSA (single seq, or one stream per seq) - bool msa_strict_slots = false; - // this is the SWA type of the cache - not to be confused with the model SWA type const llama_swa_type swa_type = LLAMA_SWA_TYPE_NONE; @@ -298,7 +293,6 @@ class llama_kv_cache : public llama_memory_i { size_t size_k_bytes() const; size_t size_v_bytes() const; - size_t size_k_idx_bytes() const; ggml_tensor * build_rope_shift( const llama_cparams & cparams, @@ -378,7 +372,6 @@ class llama_kv_cache_context : public llama_memory_context_i { // get views of the current state of the cache ggml_tensor * get_k(ggml_context * ctx, int32_t il) const; ggml_tensor * get_v(ggml_context * ctx, int32_t il) const; - ggml_tensor * get_k_idx(ggml_context * ctx, int32_t il) const; // store k_cur and v_cur in the cache based on the provided head location // note: the heads in k_cur and v_cur should be laid out contiguously in memory @@ -388,7 +381,6 @@ class llama_kv_cache_context : public llama_memory_context_i { // - v_idxs [n_tokens] or [n_tokens*n_embd_v_gqa] depending if V cache is transposed ggml_tensor * cpy_k(ggml_context * ctx, ggml_tensor * k_cur, ggml_tensor * k_idxs, int32_t il) const; ggml_tensor * cpy_v(ggml_context * ctx, ggml_tensor * v_cur, ggml_tensor * v_idxs, int32_t il) const; - ggml_tensor * cpy_k_idx(ggml_context * ctx, ggml_tensor * k_idx_cur, ggml_tensor * k_idxs, int32_t il) const; // create destination indices for each head of the current batch for where it would be written in the KV cache // the indices address the global KV cache (not per stream) - this is not relevant for the user of this API, but diff --git a/src/llama-model-loader.cpp b/src/llama-model-loader.cpp index 510586e96c20..b31e92e2da7e 100644 --- a/src/llama-model-loader.cpp +++ b/src/llama-model-loader.cpp @@ -526,6 +526,7 @@ llama_model_loader::llama_model_loader( llama_load_mode load_mode, bool check_tensors, bool no_alloc, + bool load_mtp, const llama_model_kv_override * param_overrides_p, const llama_model_tensor_buft_override * param_tensor_buft_overrides_p) : metadata(meta), set_tensor_data(set_tensor_data), set_tensor_data_ud(set_tensor_data_ud) { @@ -812,6 +813,7 @@ llama_model_loader::llama_model_loader( this->check_tensors = check_tensors; this->no_alloc = no_alloc; + this->load_mtp = load_mtp; } std::string llama_model_loader::get_arch_name() const { @@ -855,7 +857,11 @@ struct ggml_tensor * llama_model_loader::require_tensor_meta(const std::string & return tensor; } -const struct ggml_tensor * llama_model_loader::check_tensor_dims(const std::string & name, const std::vector & ne, bool required) const { +const struct ggml_tensor * llama_model_loader::check_tensor_dims( + const std::string & name, + const std::vector & ne, + bool required, + bool allow_reshape) const { const struct ggml_tensor * cur = get_tensor_meta(name.c_str()); if (cur == NULL) { @@ -865,21 +871,33 @@ const struct ggml_tensor * llama_model_loader::check_tensor_dims(const std::stri throw std::runtime_error(format("%s: tensor '%s' not found", __func__, name.c_str())); } - { - bool is_ok = true; + bool is_ok = true; + + if (allow_reshape) { + // check total number of elements only + const int64_t ncur = ggml_nelements(cur); + int64_t nexp = 1; + for (size_t i = 0; i < ne.size(); ++i) { + nexp *= ne[i]; + } + if (ncur != nexp) { + is_ok = false; + } + } else { for (size_t i = 0; i < GGML_MAX_DIMS; ++i) { if ((i < ne.size() && ne[i] != cur->ne[i]) || (i >= ne.size() && cur->ne[i] != 1)) { is_ok = false; break; } } - if (!is_ok) { - throw std::runtime_error( - format("%s: tensor '%s' has wrong shape; expected %s, got %s", - __func__, name.c_str(), - llama_format_tensor_shape(ne).c_str(), - llama_format_tensor_shape(cur).c_str())); - } + } + + if (!is_ok) { + throw std::runtime_error( + format("%s: tensor '%s' has wrong shape; expected %s, got %s", + __func__, name.c_str(), + llama_format_tensor_shape(ne).c_str(), + llama_format_tensor_shape(cur).c_str())); } return cur; @@ -1244,11 +1262,25 @@ struct ggml_tensor * llama_model_loader::create_tensor( return ret; } - ggml_tensor * t_meta = get_tensor_meta(tn.str().c_str()); - ggml_backend_buffer_type_t buft = buft_for_tensor(t_meta); + LLAMA_LOG_DEBUG("%s: loading tensor %s\n", __func__, tn.str().c_str()); + const struct ggml_tensor * cur = check_tensor_dims(tn.str(), ne, !(flags & TENSOR_NOT_REQUIRED), flags & TENSOR_ALLOW_RESHAPE); + if (cur == NULL) { + return NULL; + } + + ggml_tensor t_meta = *cur; + if (flags & TENSOR_ALLOW_RESHAPE) { + for (size_t dim = 0; dim < GGML_MAX_DIMS; dim++) { + t_meta.ne[dim] = dim < ne.size() ? ne.begin()[dim] : 1; + t_meta.nb[dim] = dim == 0 ? ggml_type_size(t_meta.type) : t_meta.ne[dim-1]*t_meta.nb[dim-1]; + } + } + + ggml_backend_buffer_type_t buft = buft_for_tensor(&t_meta); if (buft == nullptr) { - return nullptr; // return type is ggml_tensor * + return nullptr; } + ggml_context * ctx = ctx_for_buft(buft); // if duplicated, check if the original tensor was allocated in the same buffer type context and avoid creating a new one @@ -1259,20 +1291,13 @@ struct ggml_tensor * llama_model_loader::create_tensor( } } - LLAMA_LOG_DEBUG("%s: loading tensor %s\n", __func__, tn.str().c_str()); - const struct ggml_tensor * cur = check_tensor_dims(tn.str(), ne, !(flags & TENSOR_NOT_REQUIRED)); - - if (cur == NULL) { - return NULL; - } - const bool duplicated = flags & TENSOR_DUPLICATED; - struct ggml_tensor * tensor = ggml_dup_tensor(ctx, cur); - ggml_set_name(tensor, ggml_get_name(cur)); + struct ggml_tensor * tensor = ggml_dup_tensor(ctx, &t_meta); + ggml_set_name(tensor, ggml_get_name(&t_meta)); if (duplicated) { - size_data += ggml_nbytes(cur); + size_data += ggml_nbytes(&t_meta); } else { n_created++; } @@ -1280,34 +1305,6 @@ struct ggml_tensor * llama_model_loader::create_tensor( return tensor; } -struct ggml_tensor * llama_model_loader::create_tensor_as_view(struct ggml_context * ctx, struct ggml_tensor * base, const std::string & name, const std::initializer_list & ne, size_t offset, bool required) { - const struct ggml_tensor * cur = check_tensor_dims(name, ne, required); - - if (cur == NULL) { - return NULL; - } - - if (cur->type != base->type) { - throw std::runtime_error(format("%s: tensor '%s' has wrong type; expected %s, got %s", __func__, name.c_str(), ggml_type_name(base->type), ggml_type_name(cur->type))); - } - - std::array dims; - for (size_t i = 0; i < GGML_MAX_DIMS; ++i) { - dims[i] = i < ne.size() ? ne.begin()[i] : 1; - } - - struct ggml_tensor * tensor = ggml_view_4d(ctx, base, - dims[0], dims[1], dims[2], dims[3], - cur->nb[1], cur->nb[2], cur->nb[3], - offset); - - ggml_set_name(tensor, name.c_str()); - - n_created++; - - return tensor; -} - void llama_model_loader::done_getting_tensors(bool partial) const { if (n_created > n_tensors) { throw std::runtime_error(format("%s: too many tensors created; expected %d, got %d", __func__, n_tensors, n_created)); diff --git a/src/llama-model-loader.h b/src/llama-model-loader.h index 75a3652d06bd..d6b31c231118 100644 --- a/src/llama-model-loader.h +++ b/src/llama-model-loader.h @@ -67,6 +67,7 @@ struct llama_model_loader { static const int TENSOR_DUPLICATED = 1 << 1; static const int TENSOR_SKIP = 1 << 2; static const int TENSOR_SKIP_IF_VIRTUAL = 1 << 3; + static const int TENSOR_ALLOW_RESHAPE = 1 << 4; int n_kv = 0; int n_tensors = 0; @@ -79,6 +80,7 @@ struct llama_model_loader { bool use_direct_io = false; bool check_tensors; bool no_alloc; + bool load_mtp; llama_files files; llama_ftype ftype; @@ -129,6 +131,7 @@ struct llama_model_loader { llama_load_mode load_mode, bool check_tensors, bool no_alloc, + bool load_mtp, const llama_model_kv_override * param_overrides_p, const llama_model_tensor_buft_override * param_tensor_buft_overrides_p); @@ -175,14 +178,16 @@ struct llama_model_loader { struct ggml_tensor * require_tensor_meta(const std::string & name) const; - const struct ggml_tensor * check_tensor_dims(const std::string & name, const std::vector & ne, bool required) const; + const struct ggml_tensor * check_tensor_dims( + const std::string & name, + const std::vector & ne, + bool required, + bool allow_reshape) const; struct ggml_tensor * create_tensor( const llama_hparams & hparams, const buft_list_t * buft_list_cpu, const buft_list_t * buft_list_input, const buft_list_t * buft_list_output, const buft_list_t * buft_list_layer, const LLM_TN_IMPL & tn, const std::initializer_list & ne, int flags); - struct ggml_tensor * create_tensor_as_view(struct ggml_context * ctx, struct ggml_tensor * base, const std::string & name, const std::initializer_list & ne, size_t offset, bool required = true); - void done_getting_tensors(bool partial = false) const; void init_mappings(bool prefetch = true, llama_mlocks * mlock_mmaps = nullptr); diff --git a/src/llama-model.cpp b/src/llama-model.cpp index 5e501f983bc0..dda311c47bbf 100644 --- a/src/llama-model.cpp +++ b/src/llama-model.cpp @@ -11,6 +11,7 @@ #include "llama-kv-cache.h" #include "llama-kv-cache-iswa.h" #include "llama-kv-cache-dsa.h" +#include "llama-kv-cache-msa.h" #include "llama-kv-cache-dsv4.h" #include "llama-memory-hybrid.h" #include "llama-memory-hybrid-iswa.h" @@ -111,6 +112,8 @@ static llama_model * llama_model_mapping(llm_arch arch, const llama_model_params return new llama_model_qwen3vl(params); case LLM_ARCH_QWEN3VLMOE: return new llama_model_qwen3vlmoe(params); + case LLM_ARCH_QWEN3TTS: + return new llama_model_qwen3tts(params); case LLM_ARCH_PHI2: return new llama_model_phi2(params); case LLM_ARCH_PHI3: @@ -2071,9 +2074,13 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params, { res = nullptr; } break; - case LLM_ARCH_DEEPSEEK32: + case LLM_ARCH_MINIMAX_M3: { - res = new llama_kv_cache_dsa( + // sparse (MSA) layers carry an indexer key cache, but leading dense layers do not + llama_kv_cache::layer_filter_cb filter_idx = + [&](int32_t il) { return (uint32_t) il >= hparams.n_layer_dense_lead; }; + + res = new llama_kv_cache_msa( *this, params.type_k, params.type_v, @@ -2086,9 +2093,11 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params, hparams.n_swa, hparams.swa_type, nullptr, + filter_idx, nullptr); } break; case LLM_ARCH_GLM_DSA: + case LLM_ARCH_DEEPSEEK32: { if (params.ctx_type == LLAMA_CONTEXT_TYPE_MTP && hparams.n_layer_nextn > 0) { // The NextN/MTP draft head runs dense MLA (no DSA indexer), so the @@ -2117,10 +2126,11 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params, } else { // Main context: DSA cache for the trunk layers only - the nextn // layer(s) are never attended by the trunk graph. - llama_kv_cache::layer_filter_cb filter = nullptr; + llama_kv_cache::layer_filter_cb filter_mla = nullptr; if (hparams.n_layer_nextn > 0) { - filter = [&](uint32_t il) { return il < hparams.n_layer(); }; + filter_mla = [&](uint32_t il) { return il < hparams.n_layer(); }; } + llama_kv_cache::layer_filter_cb filter_lid = [&](uint32_t il) { return il < hparams.n_layer() && (arch != LLM_ARCH_GLM_DSA || hparams.is_indexer_full(il)); }; res = new llama_kv_cache_dsa( *this, @@ -2134,19 +2144,89 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params, 1, hparams.n_swa, hparams.swa_type, - filter, + filter_mla, + filter_lid, + nullptr); + } + } break; + case LLM_ARCH_DEEPSEEK4: + { + GGML_ASSERT(hparams.swa_type != LLAMA_SWA_TYPE_NONE); + + if (params.ctx_type == LLAMA_CONTEXT_TYPE_MTP) { + const llama_memory_i::layer_filter_cb filter_mtp = [&](int32_t il) { + return il >= (int32_t) hparams.n_layer(); + }; + + res = new llama_kv_cache_iswa( + *this, + params.type_k, + params.type_v, + !cparams.flash_attn, + cparams.offload_kqv, + params.swa_full, + cparams.kv_unified, + cparams.n_ctx_seq, + cparams.n_seq_max, + cparams.n_ubatch, + 1, + nullptr, + filter_mtp, + nullptr, + nullptr); + } else { + res = new llama_kv_cache_dsv4( + *this, + params.type_k, + params.type_v, + !cparams.flash_attn, + cparams.offload_kqv, + params.swa_full, + cparams.kv_unified, + cparams.n_ctx_seq, + cparams.n_seq_max, + cparams.n_ubatch, + 1, + cparams.n_rs_seq, + nullptr, nullptr); } } break; + case LLM_ARCH_DFLASH: + { + // DSV4 DSpark stages store a single MLA-style K per position (window = the draft ring) + if (hparams.dsv4_hc_mult > 0) { + GGML_ASSERT(hparams.swa_type != LLAMA_SWA_TYPE_NONE); + + res = new llama_kv_cache_iswa( + *this, + params.type_k, + params.type_v, + !cparams.flash_attn, + cparams.offload_kqv, + params.swa_full, + cparams.kv_unified, + cparams.n_ctx_seq, + cparams.n_seq_max, + cparams.n_ubatch, + 1, + nullptr, + nullptr, + nullptr, + nullptr); + break; + } + } + [[fallthrough]]; // Models that need standard caching should rely on recurrent/hybrid // checks default: { - // The MTP head is dense-attention only on hybrid Qwen3.5/3.6, so use a plain + // The MTP head is dense-attention only on hybrid Qwen3-Next/3.5/3.6, so use a plain // attention KV cache for the MTP context instead of the hybrid wrapper. - const bool mtp_on_hybrid_qwen35 = + const bool mtp_on_hybrid_qwen = params.ctx_type == LLAMA_CONTEXT_TYPE_MTP && - (arch == LLM_ARCH_QWEN35 || arch == LLM_ARCH_QWEN35MOE); + (arch == LLM_ARCH_QWEN3NEXT || arch == LLM_ARCH_QWEN35 || arch == LLM_ARCH_QWEN35MOE); if (llm_arch_is_recurrent(arch)) { res = new llama_memory_recurrent( @@ -2158,7 +2238,7 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params, cparams.n_seq_max, cparams.n_rs_seq, nullptr); - } else if (llm_arch_is_hybrid(arch) && !mtp_on_hybrid_qwen35) { + } else if (llm_arch_is_hybrid(arch) && !mtp_on_hybrid_qwen) { // The main difference between hybrid architectures is the // layer filters, so pick the right one here llama_memory_hybrid::layer_filter_cb filter_attn = nullptr; @@ -2173,7 +2253,7 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params, filter_recr = [&](uint32_t il) { return hparams.is_recr(il) && hparams.n_ff(il) == 0; }; - } else if (arch == LLM_ARCH_QWEN35 || arch == LLM_ARCH_QWEN35MOE) { + } else if (arch == LLM_ARCH_QWEN3NEXT || arch == LLM_ARCH_QWEN35 || arch == LLM_ARCH_QWEN35MOE) { filter_attn = [&](uint32_t il) { return il < hparams.n_layer() && !hparams.is_recr(il); }; @@ -2239,12 +2319,12 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params, }; } - if (mtp_on_hybrid_qwen35) { + if (mtp_on_hybrid_qwen) { filter = [&](uint32_t il) { return il >= hparams.n_layer(); }; } if ((arch == LLM_ARCH_STEP35 || arch == LLM_ARCH_HY_V3 || arch == LLM_ARCH_GLM_DSA || - arch == LLM_ARCH_MIMO2) && + arch == LLM_ARCH_MIMO2 || arch == LLM_ARCH_DEEPSEEK32) && hparams.n_layer_nextn > 0) { if (params.ctx_type == LLAMA_CONTEXT_TYPE_MTP) { filter = [&](uint32_t il) { return il >= hparams.n_layer(); }; @@ -2253,24 +2333,7 @@ llama_memory_i * llama_model::create_memory(const llama_memory_params & params, } } - if (arch == LLM_ARCH_DEEPSEEK4) { - GGML_ASSERT(hparams.swa_type != LLAMA_SWA_TYPE_NONE); - - res = new llama_kv_cache_dsv4( - *this, - params.type_k, - params.type_v, - !cparams.flash_attn, - cparams.offload_kqv, - params.swa_full, - cparams.kv_unified, - cparams.n_ctx_seq, - cparams.n_seq_max, - cparams.n_ubatch, - 1, - filter, - reuse); - } else if (hparams.swa_type != LLAMA_SWA_TYPE_NONE) { + if (hparams.swa_type != LLAMA_SWA_TYPE_NONE) { GGML_ASSERT(hparams.is_swa_any()); if (arch == LLM_ARCH_GEMMA4_ASSISTANT) { @@ -2390,6 +2453,7 @@ llama_model_params llama_model_default_params() { /*.use_extra_bufts =*/ true, /*.no_host =*/ false, /*.no_alloc =*/ false, + /*.load_mtp =*/ false, }; return result; @@ -2618,9 +2682,12 @@ llama_rope_type llama_model_rope_type(const llama_model * model) { case LLM_ARCH_STEP35: case LLM_ARCH_TALKIE: case LLM_ARCH_MELLUM: - case LLM_ARCH_DFLASH: return LLAMA_ROPE_TYPE_NEOX; + case LLM_ARCH_DFLASH: + // DSV4 DSpark drafters use DeepSeek-V4's normal RoPE; legacy DFlash backbones are NeoX + return model->hparams.dsv4_hc_mult > 0 ? LLAMA_ROPE_TYPE_NORM : LLAMA_ROPE_TYPE_NEOX; + case LLM_ARCH_QWEN2VL: case LLM_ARCH_PADDLEOCR: return LLAMA_ROPE_TYPE_MROPE; @@ -2628,6 +2695,7 @@ llama_rope_type llama_model_rope_type(const llama_model * model) { case LLM_ARCH_QWEN3VLMOE: case LLM_ARCH_QWEN35: case LLM_ARCH_QWEN35MOE: + case LLM_ARCH_QWEN3TTS: return LLAMA_ROPE_TYPE_IMROPE; case LLM_ARCH_GLM4: @@ -2802,7 +2870,8 @@ llama_model_base::llama_model_base(const struct llama_model_params & params) : l TENSOR_DUPLICATED (llama_model_loader::TENSOR_DUPLICATED), TENSOR_NOT_REQUIRED (llama_model_loader::TENSOR_NOT_REQUIRED), TENSOR_SKIP (llama_model_loader::TENSOR_SKIP), - TENSOR_SKIP_IF_VIRTUAL(llama_model_loader::TENSOR_SKIP_IF_VIRTUAL) {} + TENSOR_SKIP_IF_VIRTUAL(llama_model_loader::TENSOR_SKIP_IF_VIRTUAL), + TENSOR_ALLOW_RESHAPE (llama_model_loader::TENSOR_ALLOW_RESHAPE) {} ggml_tensor * llama_model_base::create_tensor(const LLM_TN_IMPL & tn, const std::initializer_list & ne, int flags) { GGML_ASSERT(ml != nullptr); @@ -2842,3 +2911,38 @@ const int32_t * llama_model_target_layer_ids(const struct llama_model * model) { uint32_t llama_model_target_layer_ids_n(const struct llama_model * model) { return (uint32_t) model->target_layer_ids.size(); } + +uint32_t llama_model_get_tok_embd(const struct llama_model * model, float * out) { + if (model->vocab.n_tokens() == 0 || model->tok_embd == nullptr) { + return 0; + } + + const ggml_tensor * tensor = model->tok_embd; + const size_t nelements = ggml_nelements(tensor); + GGML_ASSERT(nelements <= UINT32_MAX); // for the return type + + if (out == nullptr) { + return (uint32_t) nelements; + } + + if (tensor->type == GGML_TYPE_F32) { + ggml_backend_tensor_get(tensor, out, 0, nelements * sizeof(float)); + return (uint32_t) nelements; + } + + std::vector buf(ggml_nbytes(tensor)); + ggml_backend_tensor_get(tensor, buf.data(), 0, buf.size()); + + const ggml_type_traits * traits = ggml_get_type_traits(tensor->type); + if (tensor->type == GGML_TYPE_F16) { + ggml_fp16_to_fp32_row((const ggml_fp16_t *) buf.data(), out, nelements); + } else if (tensor->type == GGML_TYPE_BF16) { + ggml_bf16_to_fp32_row((const ggml_bf16_t *) buf.data(), out, nelements); + } else if (ggml_is_quantized(tensor->type) && traits->to_float != nullptr) { + traits->to_float(buf.data(), out, nelements); + } else { + GGML_ABORT("unsupported tensor type for dequantization: %s", ggml_type_name(tensor->type)); + } + + return (uint32_t) nelements; +} diff --git a/src/llama-model.h b/src/llama-model.h index 056a6efa59e8..6b9e94a0a692 100644 --- a/src/llama-model.h +++ b/src/llama-model.h @@ -719,6 +719,7 @@ struct llama_model_base : public llama_model { const int TENSOR_NOT_REQUIRED; const int TENSOR_SKIP; const int TENSOR_SKIP_IF_VIRTUAL; + const int TENSOR_ALLOW_RESHAPE; explicit llama_model_base(const llama_model_params & params); virtual ~llama_model_base() = default; diff --git a/src/llama-quant.cpp b/src/llama-quant.cpp index 92ebc11b99f3..fd6e787bd7d2 100644 --- a/src/llama-quant.cpp +++ b/src/llama-quant.cpp @@ -893,7 +893,7 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std:: const llama_model_kv_override * kv_overrides = params->kv_overrides; std::vector splits = {}; llama_model_loader ml(/*metadata*/ nullptr, /*set_tensor_data*/ nullptr, /*set_tensor_data_ud*/ nullptr, - fname_inp, splits, /*file*/ nullptr, /*load_mode*/ load_mode, /*check_tensors*/ true, /*no_alloc*/ false, kv_overrides, nullptr); + fname_inp, splits, /*file*/ nullptr, /*load_mode*/ load_mode, /*check_tensors*/ true, /*no_alloc*/ false, /*load_mtp*/ true, kv_overrides, nullptr); ml.init_mappings(false); // no prefetching auto mparams = llama_model_default_params(); diff --git a/src/llama-sampler.cpp b/src/llama-sampler.cpp index a9cb6bee5fd7..e550fbe4ae00 100644 --- a/src/llama-sampler.cpp +++ b/src/llama-sampler.cpp @@ -2638,7 +2638,8 @@ struct llama_sampler * llama_sampler_init_grammar_lazy_patterns( // penalties -struct llama_sampler_penalties { +struct llama_sampler_penalties : public llama_sampler_backend { + const int32_t n_vocab; const int32_t penalty_last_n; const float penalty_repeat; const float penalty_freq; @@ -2648,10 +2649,50 @@ struct llama_sampler_penalties { // a frequency map to count token occurrences std::unordered_map token_count; + + // backend graph inputs + ggml_tensor * inp_token_ids = nullptr; + ggml_tensor * inp_counts = nullptr; + + // backend helpers + int32_t n_max = 0; + bool has_candidates = false; + + std::vector host_token_ids; + std::vector host_counts; + + static bool is_disabled( + int32_t penalty_last_n, + float penalty_repeat, + float penalty_freq, + float penalty_present) { + return penalty_last_n == 0 || + (penalty_repeat == 1.0f && penalty_freq == 0.0f && penalty_present == 0.0f); + } + + bool is_disabled() const { + return is_disabled(penalty_last_n, penalty_repeat, penalty_freq, penalty_present); + } + + llama_sampler_penalties( + int32_t n_vocab, + int32_t penalty_last_n, + float penalty_repeat, + float penalty_freq, + float penalty_present) + : llama_sampler_backend("penalties") + , n_vocab (n_vocab) + , penalty_last_n (penalty_last_n) + , penalty_repeat (penalty_repeat) + , penalty_freq (penalty_freq) + , penalty_present (penalty_present) + , prev (penalty_last_n) { + } }; -static const char * llama_sampler_penalties_name(const struct llama_sampler * /*smpl*/) { - return "penalties"; +static const char * llama_sampler_penalties_name(const struct llama_sampler * smpl) { + auto * ctx = (llama_sampler_penalties *) smpl->ctx; + return ctx->get_name(); } static void llama_sampler_penalties_accept(struct llama_sampler * smpl, llama_token token) { @@ -2688,8 +2729,7 @@ static void llama_sampler_penalties_accept(struct llama_sampler * smpl, llama_to static void llama_sampler_penalties_apply(struct llama_sampler * smpl, llama_token_data_array * cur_p) { auto * ctx = (llama_sampler_penalties *) smpl->ctx; - if ((ctx->penalty_last_n == 0) || - (ctx->penalty_repeat == 1.0f && ctx->penalty_freq == 0.0f && ctx->penalty_present == 0.0f)) { + if (ctx->is_disabled()) { return; } @@ -2727,6 +2767,7 @@ static void llama_sampler_penalties_reset(struct llama_sampler * smpl) { static struct llama_sampler * llama_sampler_penalties_clone(const struct llama_sampler * smpl) { const auto * ctx = (const llama_sampler_penalties *) smpl->ctx; auto * result = llama_sampler_init_penalties( + ctx->n_vocab, ctx->penalty_last_n, ctx->penalty_repeat, ctx->penalty_freq, @@ -2736,7 +2777,8 @@ static struct llama_sampler * llama_sampler_penalties_clone(const struct llama_s { auto * result_ctx = (llama_sampler_penalties *) result->ctx; - result_ctx->prev = ctx->prev; + result_ctx->prev = ctx->prev; + result_ctx->token_count = ctx->token_count; } return result; @@ -2746,6 +2788,170 @@ static void llama_sampler_penalties_free(struct llama_sampler * smpl) { delete (llama_sampler_penalties *) smpl->ctx; } +static bool llama_sampler_penalties_backend_init( + struct llama_sampler * smpl, + ggml_backend_buffer_type_t buft) { + auto * sctx = (llama_sampler_penalties *) smpl->ctx; + + const bool res = llama_sampler_backend_support(smpl, buft); + + sctx->init(res); + + return res; +} + +static void llama_sampler_penalties_backend_apply( + struct llama_sampler * smpl, + struct ggml_context * ctx, + struct ggml_cgraph * gf, + struct llama_sampler_data * data) { + GGML_UNUSED(gf); + + auto * sctx = (llama_sampler_penalties *) smpl->ctx; + + if (sctx->is_disabled()) { + return; + } + + GGML_ASSERT(sctx->n_vocab > 0); + + sctx->has_candidates = data->candidates != nullptr; + sctx->n_max = std::min(sctx->penalty_last_n, sctx->n_vocab); + + sctx->inp_token_ids = ggml_new_tensor_1d(ctx, GGML_TYPE_I32, sctx->n_max); + ggml_set_name(sctx->inp_token_ids, "penalties_token_ids"); + ggml_set_input(sctx->inp_token_ids); + + sctx->inp_counts = ggml_new_tensor_1d(ctx, GGML_TYPE_I32, sctx->n_max); + ggml_set_name(sctx->inp_counts, "penalties_counts"); + ggml_set_input(sctx->inp_counts); + + if ((int32_t) sctx->host_token_ids.size() != sctx->n_max) { + sctx->host_token_ids.assign(sctx->n_max, 0); + sctx->host_counts.assign(sctx->n_max, 0); + } + + // flatten + ggml_tensor * logits = ggml_reshape_1d(ctx, data->logits, ggml_nelements(data->logits)); + ggml_tensor * gathered = logits; + ggml_tensor * counts_f32 = ggml_cast(ctx, sctx->inp_counts, GGML_TYPE_F32); + + if (sctx->has_candidates) { + ggml_tensor * candidates = ggml_reshape_1d( + ctx, data->candidates, ggml_nelements(data->candidates)); + const int64_t n_candidates = candidates->ne[0]; + GGML_ASSERT(n_candidates == ggml_nelements(logits)); + + ggml_tensor * counts_rows = ggml_fill( + ctx, ggml_new_tensor_2d(ctx, GGML_TYPE_F32, 1, sctx->n_vocab), 0.0f); + ggml_tensor * scatter_rows = ggml_reshape_2d(ctx, counts_f32, 1, sctx->n_max); + counts_rows = ggml_set_rows(ctx, counts_rows, scatter_rows, sctx->inp_token_ids); + counts_f32 = ggml_get_rows(ctx, counts_rows, candidates); + counts_f32 = ggml_reshape_1d(ctx, counts_f32, n_candidates); + } else { + ggml_tensor * logits_rows = ggml_reshape_2d(ctx, logits, 1, ggml_nelements(logits)); + gathered = ggml_get_rows(ctx, logits_rows, sctx->inp_token_ids); + gathered = ggml_reshape_1d(ctx, gathered, sctx->n_max); + } + + ggml_tensor * active_mask = ggml_step(ctx, counts_f32); + ggml_tensor * inactive_mask = ggml_sub(ctx, ggml_fill(ctx, active_mask, 1.0f), active_mask); + + ggml_tensor * penalized = gathered; + + if (sctx->penalty_repeat != 1.0f) { + ggml_tensor * pos_mask = ggml_step(ctx, penalized); + ggml_tensor * neg_mask = ggml_sub(ctx, ggml_fill(ctx, pos_mask, 1.0f), pos_mask); + + ggml_tensor * pos_scale = ggml_scale(ctx, pos_mask, 1.0f/sctx->penalty_repeat); + ggml_tensor * neg_scale = ggml_scale(ctx, neg_mask, sctx->penalty_repeat); + ggml_tensor * repeat_scale = ggml_add(ctx, pos_scale, neg_scale); + + // scale inactive entries with 1 to avoid -INF * 0 = NaN for values masked by top-p + repeat_scale = ggml_mul(ctx, repeat_scale, active_mask); + repeat_scale = ggml_add(ctx, repeat_scale, inactive_mask); + penalized = ggml_mul(ctx, gathered, repeat_scale); + } + + if (sctx->penalty_freq != 0.0f) { + ggml_tensor * penalty_freq = ggml_scale(ctx, counts_f32, sctx->penalty_freq); + penalized = ggml_sub(ctx, penalized, penalty_freq); + } + + if (sctx->penalty_present != 0.0f) { + ggml_tensor * penalty_present = ggml_scale(ctx, active_mask, sctx->penalty_present); + penalized = ggml_sub(ctx, penalized, penalty_present); + } + + if (sctx->has_candidates) { + data->logits = penalized; + } else { + ggml_tensor * logits_rows = ggml_reshape_2d(ctx, logits, 1, ggml_nelements(logits)); + ggml_tensor * scatter_rows = ggml_reshape_2d(ctx, penalized, 1, sctx->n_max); + logits_rows = ggml_set_rows(ctx, logits_rows, scatter_rows, sctx->inp_token_ids); + data->logits = ggml_reshape_1d(ctx, logits_rows, ggml_nelements(logits)); + } +} + +static void llama_sampler_penalties_backend_set_input(struct llama_sampler * smpl) { + auto * sctx = (llama_sampler_penalties *) smpl->ctx; + + if (!sctx->inp_token_ids || !sctx->inp_counts || sctx->n_max <= 0 || sctx->n_vocab <= 0) { + return; + } + + if (sctx->is_disabled()) { + return; + } + + // fill active entries from the map + int32_t n_active = 0; + + for (const auto & it : sctx->token_count) { + GGML_ASSERT(n_active < sctx->n_max); + sctx->host_token_ids[n_active] = it.first; + sctx->host_counts [n_active] = it.second; + ++n_active; + } + + // Sorting is required because backend_apply uses ggml_set_rows (a scatter-back operation) + std::vector> entries; + entries.reserve(n_active); + for (int32_t i = 0; i < n_active; ++i) { + entries.emplace_back(sctx->host_token_ids[i], sctx->host_counts[i]); + } + std::sort(entries.begin(), entries.end(), [](const auto & a, const auto & b) { + return a.first < b.first; + }); + for (int32_t i = 0; i < n_active; ++i) { + sctx->host_token_ids[i] = entries[i].first; + sctx->host_counts [i] = entries[i].second; + } + + // Padding: Finds a filler token id that is not present in token_count. + // Use it to do padding for the arrays, it avoids resizing every time. + // The arrays must always have exactly n_max entries (the GPU tensor is a fixed size). + int32_t filler = 0; + if (n_active < sctx->n_max) { + while (sctx->token_count.find(filler) != sctx->token_count.end()) { + ++filler; + } + GGML_ASSERT(filler < sctx->n_vocab); + } + + // Fill the rest of the arrays with the filler token id and count 0. + // Inactive slots are padded with a unique dummy token ID (count = 0). + // The uniqueness matters because ggml_set_rows with duplicate indices can produce non-deterministic or incorrect results. + // Using a filler token with count 0 that isn't in the active set is safe, because the active_mask step in backend_apply filters them out via ggml_step(counts_f32) + for (int32_t i = n_active; i < sctx->n_max; ++i) { + sctx->host_token_ids[i] = filler; + sctx->host_counts [i] = 0; + } + + ggml_backend_tensor_set(sctx->inp_token_ids, sctx->host_token_ids.data(), 0, sctx->n_max * sizeof(int32_t)); + ggml_backend_tensor_set(sctx->inp_counts, sctx->host_counts.data(), 0, sctx->n_max * sizeof(int32_t)); +} + static struct llama_sampler_i llama_sampler_penalties_i = { /* .name = */ llama_sampler_penalties_name, /* .accept = */ llama_sampler_penalties_accept, @@ -2753,35 +2959,33 @@ static struct llama_sampler_i llama_sampler_penalties_i = { /* .reset = */ llama_sampler_penalties_reset, /* .clone = */ llama_sampler_penalties_clone, /* .free = */ llama_sampler_penalties_free, - /* .backend_init = */ nullptr, + /* .backend_init = */ llama_sampler_penalties_backend_init, /* .backend_accept = */ nullptr, - /* .backend_apply = */ nullptr, - /* .backend_set_input = */ nullptr, + /* .backend_apply = */ llama_sampler_penalties_backend_apply, + /* .backend_set_input = */ llama_sampler_penalties_backend_set_input, }; struct llama_sampler * llama_sampler_init_penalties( + int32_t n_vocab, int32_t penalty_last_n, float penalty_repeat, float penalty_freq, float penalty_present) { penalty_last_n = std::max(penalty_last_n, 0); - const bool is_empty = (penalty_last_n == 0 || (penalty_repeat == 1.0f && penalty_freq == 0.0f && penalty_present == 0.0f)); - - if (is_empty) { + if (llama_sampler_penalties::is_disabled( + penalty_last_n, penalty_repeat, penalty_freq, penalty_present)) { return llama_sampler_init_empty("?penalties"); } return llama_sampler_init( /* .iface = */ &llama_sampler_penalties_i, - /* .ctx = */ new llama_sampler_penalties { - /* .penalty_last_n = */ penalty_last_n, - /* .penalty_repeat = */ penalty_repeat, - /* .penalty_freq = */ penalty_freq, - /* .penalty_present = */ penalty_present, - /* .prev = */ ring_buffer(penalty_last_n), - /* .token_count = */ {}, - } + /* .ctx = */ new llama_sampler_penalties( + n_vocab, + penalty_last_n, + penalty_repeat, + penalty_freq, + penalty_present) ); } @@ -2874,8 +3078,6 @@ struct llama_sampler * llama_sampler_init_top_n_sigma(float n) { // DRY struct llama_sampler_dry { - int32_t total_context_size; - const float dry_multiplier; const float dry_base; const int32_t dry_allowed_length; @@ -2951,8 +3153,7 @@ static void llama_sampler_dry_apply(struct llama_sampler * smpl, llama_token_dat return; } - int32_t effective_dry_penalty_last_n = (ctx->dry_penalty_last_n == -1) ? ctx->total_context_size : std::max(ctx->dry_penalty_last_n, 0); - int last_n_repeat = std::min(std::min((int)ctx->last_tokens.size(), effective_dry_penalty_last_n), ctx->total_context_size); + int last_n_repeat = std::min((int) ctx->last_tokens.size(), ctx->dry_penalty_last_n); if (last_n_repeat <= ctx->dry_allowed_length) { return; @@ -3165,7 +3366,7 @@ static struct llama_sampler * llama_sampler_dry_clone(const struct llama_sampler llama_vocab dummy_vocab; // dummy vocab is passed because it is only needed for raw sequence breaker processing, which we have already done and will simply be copying - auto * result = llama_sampler_init_dry(&dummy_vocab, ctx->total_context_size, ctx->dry_multiplier, ctx->dry_base, ctx->dry_allowed_length, ctx->dry_penalty_last_n, NULL, 0); + auto * result = llama_sampler_init_dry(&dummy_vocab, ctx->dry_multiplier, ctx->dry_base, ctx->dry_allowed_length, ctx->dry_penalty_last_n, NULL, 0); // Copy the state, including the processed breakers { @@ -3196,8 +3397,8 @@ static struct llama_sampler_i llama_sampler_dry_i = { /* .backend_set_input = */ nullptr, }; -struct llama_sampler * llama_sampler_init_dry(const struct llama_vocab * vocab, int32_t n_ctx_train, float dry_multiplier, float dry_base, int32_t dry_allowed_length, int32_t dry_penalty_last_n, const char** seq_breakers, size_t num_breakers) { - int32_t effective_dry_penalty_last_n = (dry_penalty_last_n == -1) ? n_ctx_train : std::max(dry_penalty_last_n, 0); +struct llama_sampler * llama_sampler_init_dry(const struct llama_vocab * vocab, float dry_multiplier, float dry_base, int32_t dry_allowed_length, int32_t dry_penalty_last_n, const char** seq_breakers, size_t num_breakers) { + dry_penalty_last_n = std::max(dry_penalty_last_n, 0); std::unordered_multimap> processed_breakers; const int MAX_CHAR_LEN = 40; const int MAX_SEQ_LEN = 20; @@ -3234,23 +3435,22 @@ struct llama_sampler * llama_sampler_init_dry(const struct llama_vocab * vocab, return llama_sampler_init( /* .iface = */ &llama_sampler_dry_i, /* .ctx = */ new llama_sampler_dry { - /* .total_context_size = */ n_ctx_train, /* .dry_multiplier = */ dry_multiplier, /* .dry_base = */ dry_base, /* .dry_allowed_length = */ dry_allowed_length, /* .dry_penalty_last_n = */ dry_penalty_last_n, /* .dry_processed_breakers = */ std::move(processed_breakers), - /* .dry_repeat_count = */ dry_enabled ? std::vector(effective_dry_penalty_last_n, 0) : std::vector{}, + /* .dry_repeat_count = */ dry_enabled ? std::vector(dry_penalty_last_n, 0) : std::vector{}, /* .dry_max_token_repeat = */ {}, - /* .last_tokens = */ dry_enabled ? ring_buffer(effective_dry_penalty_last_n) : ring_buffer(0), + /* .last_tokens = */ dry_enabled ? ring_buffer(dry_penalty_last_n) : ring_buffer(0), } ); } // wrapper for test-sampling.cpp -struct llama_sampler * llama_sampler_init_dry_testing(int32_t context_size, float dry_multiplier, float dry_base, int32_t dry_allowed_length, int32_t dry_penalty_last_n, const std::vector>& seq_breakers) { +struct llama_sampler * llama_sampler_init_dry_testing(float dry_multiplier, float dry_base, int32_t dry_allowed_length, int32_t dry_penalty_last_n, const std::vector>& seq_breakers) { llama_vocab dummy_vocab; - auto * result = llama_sampler_init_dry(&dummy_vocab, context_size, dry_multiplier, dry_base, dry_allowed_length, dry_penalty_last_n, NULL, 0); + auto * result = llama_sampler_init_dry(&dummy_vocab, dry_multiplier, dry_base, dry_allowed_length, dry_penalty_last_n, NULL, 0); auto * ctx = (llama_sampler_dry *) result->ctx; // Process the token-based sequence breakers diff --git a/src/llama-sampler.h b/src/llama-sampler.h index b9bfc20d2517..9292075146a1 100644 --- a/src/llama-sampler.h +++ b/src/llama-sampler.h @@ -34,7 +34,6 @@ struct llama_sampler_chain { }; struct llama_sampler * llama_sampler_init_dry_testing( - int32_t context_size, float dry_multiplier, float dry_base, int32_t dry_allowed_length, diff --git a/src/llama-vocab.cpp b/src/llama-vocab.cpp index 443cd4640858..4a01dfd4cab6 100644 --- a/src/llama-vocab.cpp +++ b/src/llama-vocab.cpp @@ -1373,8 +1373,10 @@ struct llm_tokenizer_plamo2 : llm_tokenizer { if (vocab.is_byte(token_id)) { if (entry.text.length() == 6 && entry.text.substr(0, 3) == "<0x" && entry.text.back() == '>') { std::string hex_str = entry.text.substr(3, 2); - int byte_val = std::stoi(hex_str, nullptr, 16); - bytes_[byte_val] = static_cast(token_id); + if (std::isxdigit(static_cast(hex_str[0])) && std::isxdigit(static_cast(hex_str[1]))) { + int byte_val = std::stoi(hex_str, nullptr, 16); + bytes_[byte_val] = static_cast(token_id); + } } continue; } @@ -2532,6 +2534,12 @@ void llama_vocab::impl::load(llama_model_loader & ml, const LLM_KV & kv) { const std::string & key = kv(std::get<0>(it)); int32_t & id = std::get<1>(it); + if (id >= 0 && static_cast(id) >= id_to_token.size()) { + LLAMA_LOG_WARN("%s: default special token '%s' = %d out of vocab range, disabling\n", + __func__, key.c_str(), id); + id = LLAMA_TOKEN_NULL; + } + uint32_t new_id; if (!ml.get_key(std::get<0>(it), new_id, false)) { continue; @@ -3619,12 +3627,15 @@ int32_t llama_vocab::impl::token_to_piece(llama_token token, char * buf, int32_t if (vocab.is_byte(token)) { // Handle byte tokens like <0xXX> if (token_text.length() == 6 && token_text.substr(0, 3) == "<0x" && token_text.back() == '>') { - int hex_val = std::stoi(token_text.substr(3, 2), nullptr, 16); - if (length < 1) { - return -1; + std::string hex_str = token_text.substr(3, 2); + if (std::isxdigit(static_cast(hex_str[0])) && std::isxdigit(static_cast(hex_str[1]))) { + int hex_val = std::stoi(hex_str, nullptr, 16); + if (length < 1) { + return -1; + } + buf[0] = static_cast(hex_val); + return 1; } - buf[0] = static_cast(hex_val); - return 1; } } diff --git a/src/llama.cpp b/src/llama.cpp index d22e4c81a9e3..d6e0bbfefa72 100644 --- a/src/llama.cpp +++ b/src/llama.cpp @@ -305,7 +305,7 @@ static std::pair llama_model_load(struct gguf_context * meta const std::string & fname, std::vector & splits, FILE * file, llama_model_params & params) { try { llama_model_loader ml(metadata, set_tensor_data, set_tensor_data_ud, fname, splits, file, params.load_mode, - params.check_tensors, params.no_alloc, params.kv_overrides, params.tensor_buft_overrides); + params.check_tensors, params.no_alloc, params.load_mtp, params.kv_overrides, params.tensor_buft_overrides); ml.print_info(); std::unique_ptr model_ptr(llama_model_create(ml, params)); diff --git a/src/models/cohere2moe.cpp b/src/models/cohere2moe.cpp index 499c73a1c49c..3acb7e77af80 100644 --- a/src/models/cohere2moe.cpp +++ b/src/models/cohere2moe.cpp @@ -55,7 +55,11 @@ void llama_model_cohere2moe::load_arch_tensors(llama_model_loader & ml) { const std::string mtp_probe = "blk." + std::to_string(n_layer) + ".nextn.eh_proj.weight"; const bool trunk_only = (hparams.n_layer_nextn > 0) && (ml.get_weight(mtp_probe.c_str()) == nullptr); const int trunk_flags = mtp_only ? TENSOR_NOT_REQUIRED : 0; - const int mtp_flags = trunk_only ? TENSOR_NOT_REQUIRED : 0; + int mtp_flags = trunk_only ? TENSOR_NOT_REQUIRED : 0; + + if (!ml.load_mtp) { + mtp_flags |= TENSOR_SKIP; + } tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), { n_embd, n_vocab }, 0); diff --git a/src/models/deepseek2.cpp b/src/models/deepseek2.cpp index a9e8bc514036..ba90c0d0776b 100644 --- a/src/models/deepseek2.cpp +++ b/src/models/deepseek2.cpp @@ -37,6 +37,11 @@ void llama_model_deepseek2::load_arch_hparams(llama_model_loader & ml) { hparams.rope_yarn_log_mul /= 0.1f; } + // NextN/MTP + ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.n_layer_nextn, false); + GGML_ASSERT(hparams.n_layer_nextn == 0 || + hparams.n_layer() + hparams.n_layer_nextn == hparams.n_layer_all); + // (optional) temperature tuning - used by mistral-large ml.get_key(LLM_KV_ATTENTION_TEMPERATURE_SCALE, hparams.f_attn_temp_scale, false); ml.get_key(LLM_KV_ATTENTION_TEMPERATURE_LENGTH, hparams.n_attn_temp_floor_scale, false); // FIXME why not use temperature_length? @@ -52,10 +57,20 @@ void llama_model_deepseek2::load_arch_hparams(llama_model_loader & ml) { } } -void llama_model_deepseek2::load_arch_tensors(llama_model_loader &) { +void llama_model_deepseek2::load_arch_tensors(llama_model_loader & ml) { LLAMA_LOAD_LOCALS; const int64_t n_expert_shared = hparams.n_expert_shared; + const bool mtp_only = (hparams.n_layer_nextn > 0) && (ml.get_weight("blk.0.attn_norm.weight") == nullptr); + const std::string mtp_probe = "blk." + std::to_string(n_layer) + ".nextn.eh_proj.weight"; + const bool trunk_only = (hparams.n_layer_nextn > 0) && (ml.get_weight(mtp_probe.c_str()) == nullptr); + const int trunk_flags = mtp_only ? TENSOR_NOT_REQUIRED : 0; + int mtp_flags = trunk_only ? TENSOR_NOT_REQUIRED : 0; + + if (!ml.load_mtp) { + mtp_flags |= TENSOR_SKIP; + } + const bool is_mla = hparams.is_mla(); // note: these are the actual head sizes you get when treating as MHA or after "decompression" using wv_b for MLA @@ -81,44 +96,45 @@ void llama_model_deepseek2::load_arch_tensors(llama_model_loader &) { output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED); } - for (int i = 0; i < n_layer; ++i) { + for (int i = 0; i < n_layer_all; ++i) { auto & layer = layers[i]; + const int flags = i < n_layer ? trunk_flags : mtp_flags; - layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, 0); + layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, flags); if (q_lora_rank > 0) { - layer.attn_q_a_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_A_NORM, "weight", i), {q_lora_rank}, 0); + layer.attn_q_a_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_A_NORM, "weight", i), {q_lora_rank}, flags); } - layer.attn_kv_a_norm = create_tensor(tn(LLM_TENSOR_ATTN_KV_A_NORM, "weight", i), {kv_lora_rank}, 0); + layer.attn_kv_a_norm = create_tensor(tn(LLM_TENSOR_ATTN_KV_A_NORM, "weight", i), {kv_lora_rank}, flags); if (q_lora_rank > 0) { - layer.wq_a = create_tensor(tn(LLM_TENSOR_ATTN_Q_A, "weight", i), {n_embd, q_lora_rank}, 0); - layer.wq_b = create_tensor(tn(LLM_TENSOR_ATTN_Q_B, "weight", i), {q_lora_rank, n_head * n_embd_head_k_mla}, 0); + layer.wq_a = create_tensor(tn(LLM_TENSOR_ATTN_Q_A, "weight", i), {n_embd, q_lora_rank}, flags); + layer.wq_b = create_tensor(tn(LLM_TENSOR_ATTN_Q_B, "weight", i), {q_lora_rank, n_head * n_embd_head_k_mla}, flags); } else { - layer.wq = create_tensor(tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_head * n_embd_head_k_mla}, 0); + layer.wq = create_tensor(tn(LLM_TENSOR_ATTN_Q, "weight", i), {n_embd, n_head * n_embd_head_k_mla}, flags); } - layer.wkv_a_mqa = create_tensor(tn(LLM_TENSOR_ATTN_KV_A_MQA, "weight", i), {n_embd, kv_lora_rank + n_embd_head_qk_rope}, 0); + layer.wkv_a_mqa = create_tensor(tn(LLM_TENSOR_ATTN_KV_A_MQA, "weight", i), {n_embd, kv_lora_rank + n_embd_head_qk_rope}, flags); // note: only old legacy GGUF files will have the unsplit wkv_b tensor in if (is_mla) { - layer.wk_b = create_tensor(tn(LLM_TENSOR_ATTN_K_B, "weight", i), {n_embd_head_qk_nope, kv_lora_rank, n_head}, 0); - layer.wv_b = create_tensor(tn(LLM_TENSOR_ATTN_V_B, "weight", i), {kv_lora_rank, n_embd_head_v_mla, n_head}, 0); + layer.wk_b = create_tensor(tn(LLM_TENSOR_ATTN_K_B, "weight", i), {n_embd_head_qk_nope, kv_lora_rank, n_head}, flags); + layer.wv_b = create_tensor(tn(LLM_TENSOR_ATTN_V_B, "weight", i), {kv_lora_rank, n_embd_head_v_mla, n_head}, flags); } else { - layer.wkv_b = create_tensor(tn(LLM_TENSOR_ATTN_KV_B, "weight", i), {kv_lora_rank, n_head * (n_embd_head_qk_nope + n_embd_head_v_mla)}, 0); + layer.wkv_b = create_tensor(tn(LLM_TENSOR_ATTN_KV_B, "weight", i), {kv_lora_rank, n_head * (n_embd_head_qk_nope + n_embd_head_v_mla)}, flags); } - layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_head * n_embd_head_v_mla, n_embd}, 0); + layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_head * n_embd_head_v_mla, n_embd}, flags); - layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, 0); + layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, flags); if (i < (int) hparams.n_layer_dense_lead) { - layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}, 0); - layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}, 0); - layer.ffn_up = create_tensor(tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}, 0); + layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}, flags); + layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd}, flags); + layer.ffn_up = create_tensor(tn(LLM_TENSOR_FFN_UP, "weight", i), {n_embd, n_ff}, flags); } else { - layer.ffn_gate_inp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert}, 0); - layer.ffn_exp_probs_b = create_tensor(tn(LLM_TENSOR_FFN_EXP_PROBS_B, "bias", i), {n_expert}, TENSOR_NOT_REQUIRED); + layer.ffn_gate_inp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert}, flags); + layer.ffn_exp_probs_b = create_tensor(tn(LLM_TENSOR_FFN_EXP_PROBS_B, "bias", i), {n_expert}, TENSOR_NOT_REQUIRED | flags); if (n_expert == 0) { throw std::runtime_error("n_expert must be > 0"); @@ -128,21 +144,281 @@ void llama_model_deepseek2::load_arch_tensors(llama_model_loader &) { } // MoE branch - layer.ffn_down_exps = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), {n_ff_exp, n_embd, n_expert}, 0); - create_tensor_gate_up_exps(layer, i, n_embd, n_ff_exp, n_expert, 0); + layer.ffn_down_exps = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), {n_ff_exp, n_embd, n_expert}, flags); + create_tensor_gate_up_exps(layer, i, n_embd, n_ff_exp, n_expert, flags); // Shared expert branch - layer.ffn_gate_shexp = create_tensor(tn(LLM_TENSOR_FFN_GATE_SHEXP, "weight", i), {n_embd, n_ff_exp * n_expert_shared}, 0); - layer.ffn_down_shexp = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP, "weight", i), { n_ff_exp * n_expert_shared, n_embd}, 0); - layer.ffn_up_shexp = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP, "weight", i), {n_embd, n_ff_exp * n_expert_shared}, 0); + layer.ffn_gate_shexp = create_tensor(tn(LLM_TENSOR_FFN_GATE_SHEXP, "weight", i), {n_embd, n_ff_exp * n_expert_shared}, flags); + layer.ffn_down_shexp = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP, "weight", i), { n_ff_exp * n_expert_shared, n_embd}, flags); + layer.ffn_up_shexp = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP, "weight", i), {n_embd, n_ff_exp * n_expert_shared}, flags); + } + + // NextN/MTP tensors + if (i >= n_layer) { + layer.nextn.eh_proj = create_tensor(tn(LLM_TENSOR_NEXTN_EH_PROJ, "weight", i), { 2 * n_embd, n_embd }, mtp_flags); + layer.nextn.enorm = create_tensor(tn(LLM_TENSOR_NEXTN_ENORM, "weight", i), { n_embd }, mtp_flags); + layer.nextn.hnorm = create_tensor(tn(LLM_TENSOR_NEXTN_HNORM, "weight", i), { n_embd }, mtp_flags); + layer.nextn.embed_tokens = create_tensor(tn(LLM_TENSOR_NEXTN_EMBED_TOKENS, "weight", i), { n_embd, n_vocab }, TENSOR_NOT_REQUIRED | flags); + layer.nextn.shared_head_head = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_HEAD, "weight", i), { n_embd, n_vocab }, TENSOR_NOT_REQUIRED | flags); + layer.nextn.shared_head_norm = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_NORM, "weight", i), { n_embd }, TENSOR_NOT_REQUIRED | flags); } } } std::unique_ptr llama_model_deepseek2::build_arch_graph(const llm_graph_params & params) const { + if (params.gtype == LLM_GRAPH_TYPE_DECODER_MTP) { + return std::make_unique(*this, params); + } return std::make_unique(*this, params); } +llama_model_deepseek2::graph_mtp::graph_mtp(const llama_model & model, const llm_graph_params & params) : + llm_graph_context(params) { + GGML_ASSERT(hparams.n_layer_nextn > 0 && "GLM4 MTP requires n_layer_nextn > 0"); + GGML_ASSERT(hparams.n_layer_nextn == 1 && "GLM4 MTP currently only supports a single MTP block"); + GGML_ASSERT(hparams.is_mla() && "GLM4 MTP requires MLA"); + GGML_ASSERT(hparams.f_attn_temp_scale == 0.0f && "GLM4 MTP does not support attention temperature scaling"); + + // The appended MTP block is stored immediately after the main decoder layers. + const int il = hparams.n_layer(); + const auto & layer = model.layers[il]; + + GGML_ASSERT(layer.nextn.eh_proj && "MTP block missing nextn.eh_proj"); + GGML_ASSERT(layer.nextn.enorm && "MTP block missing nextn.enorm"); + GGML_ASSERT(layer.nextn.hnorm && "MTP block missing nextn.hnorm"); + + GGML_ASSERT((uint32_t) il >= hparams.n_layer_dense_lead && "GLM4 MTP block expected to use MoE FFN"); + + const int64_t n_embd_head_k_mla = hparams.n_embd_head_k_mla(); + const int64_t n_embd_head_qk_rope = hparams.n_rot(); + const int64_t n_embd_head_qk_nope = n_embd_head_k_mla - n_embd_head_qk_rope; + const int64_t kv_lora_rank = hparams.n_lora_kv; + + GGML_ASSERT(n_embd_head_qk_nope >= 1); + GGML_ASSERT(hparams.n_lora_q > 0); + GGML_ASSERT(layer.wq_a); + GGML_ASSERT(layer.attn_q_a_norm); + GGML_ASSERT(layer.wq_b); + GGML_ASSERT(layer.wkv_a_mqa); + GGML_ASSERT(layer.attn_kv_a_norm); + GGML_ASSERT(layer.wk_b); + + const bool has_split_exps = + layer.ffn_up_exps != nullptr && + layer.ffn_gate_exps != nullptr; + + const bool has_fused_exps = layer.ffn_gate_up_exps != nullptr; + + GGML_ASSERT(has_split_exps || has_fused_exps); + GGML_ASSERT(layer.ffn_norm); + GGML_ASSERT(layer.ffn_gate_inp); + GGML_ASSERT(layer.ffn_down_exps); + GGML_ASSERT(layer.ffn_gate_shexp); + GGML_ASSERT(layer.ffn_down_shexp); + GGML_ASSERT(layer.ffn_up_shexp); + + auto inp = std::make_unique(hparams.n_embd); + + inp->tokens = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_tokens); + ggml_set_input(inp->tokens); + + inp->embd = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, hparams.n_embd_inp(), n_tokens); + ggml_set_input(inp->embd); + + ggml_tensor * tok_embd; + if (ubatch.token) { + ggml_tensor * tok_embd_w = layer.nextn.embed_tokens + ? layer.nextn.embed_tokens + : model.tok_embd; + + tok_embd = ggml_get_rows(ctx0, tok_embd_w, inp->tokens); + } else { + tok_embd = inp->embd; + } + cb(tok_embd, "mtp_tok_embd", il); + + inp->h = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, hparams.n_embd, n_tokens); + ggml_set_input(inp->h); + ggml_set_name(inp->h, "mtp_h_input"); + + ggml_tensor * h_embd = inp->h; + + res->add_input(std::move(inp)); + + ggml_tensor * inp_pos = build_inp_pos(); + ggml_tensor * inp_out_ids = build_inp_out_ids(); + + auto * inp_attn_k = build_attn_inp_k(); + + ggml_tensor * h_norm = build_norm(h_embd, layer.nextn.hnorm, nullptr, LLM_NORM_RMS, il); + cb(h_norm, "mtp_hnorm", il); + + ggml_tensor * e_norm = build_norm(tok_embd, layer.nextn.enorm, nullptr, LLM_NORM_RMS, il); + cb(e_norm, "mtp_enorm", il); + + ggml_tensor * concat = ggml_concat(ctx0, e_norm, h_norm, 0); + cb(concat, "mtp_concat", il); + + ggml_tensor * cur = build_lora_mm(layer.nextn.eh_proj, concat, layer.nextn.eh_proj_s); + cb(cur, "mtp_eh_proj", il); + + ggml_tensor * inpSA = cur; + + cur = build_norm(cur, layer.attn_norm, nullptr, LLM_NORM_RMS, il); + cb(cur, "mtp_attn_norm", il); + + ggml_tensor * q = ggml_mul_mat(ctx0, layer.wq_a, cur); + cb(q, "mtp_q_a", il); + + q = build_norm(q, layer.attn_q_a_norm, nullptr, LLM_NORM_RMS, il); + cb(q, "mtp_q_a_norm", il); + + q = ggml_mul_mat(ctx0, layer.wq_b, q); + cb(q, "mtp_q_b", il); + + ggml_tensor * q_nope = + ggml_view_3d(ctx0, q, n_embd_head_qk_nope, n_head, n_tokens, + ggml_row_size(q->type, n_embd_head_k_mla), + ggml_row_size(q->type, n_embd_head_k_mla) * n_head, 0); + cb(q_nope, "mtp_q_nope", il); + + ggml_tensor * q_pe = + ggml_view_3d(ctx0, q, n_embd_head_qk_rope, n_head, n_tokens, + ggml_row_size(q->type, n_embd_head_k_mla), + ggml_row_size(q->type, n_embd_head_k_mla) * n_head, + ggml_row_size(q->type, n_embd_head_qk_nope)); + cb(q_pe, "mtp_q_pe", il); + + ggml_tensor * kv_cmpr_pe = ggml_mul_mat(ctx0, layer.wkv_a_mqa, cur); + cb(kv_cmpr_pe, "mtp_kv_cmpr_pe", il); + + ggml_tensor * kv_cmpr = + ggml_view_2d(ctx0, kv_cmpr_pe, kv_lora_rank, n_tokens, + ggml_row_size(kv_cmpr_pe->type, kv_lora_rank + n_embd_head_qk_rope), 0); + cb(kv_cmpr, "mtp_kv_cmpr", il); + + ggml_tensor * k_pe = + ggml_view_3d(ctx0, kv_cmpr_pe, n_embd_head_qk_rope, 1, n_tokens, + ggml_row_size(kv_cmpr_pe->type, kv_lora_rank + n_embd_head_qk_rope), + ggml_row_size(kv_cmpr_pe->type, kv_lora_rank + n_embd_head_qk_rope), + ggml_row_size(kv_cmpr_pe->type, kv_lora_rank)); + cb(k_pe, "mtp_k_pe", il); + + kv_cmpr = build_norm(kv_cmpr, layer.attn_kv_a_norm, nullptr, LLM_NORM_RMS, il); + cb(kv_cmpr, "mtp_kv_cmpr_norm", il); + + GGML_ASSERT(ext_factor >= 0.0f); + + const float attn_factor_org = + attn_factor * (1.0f + 0.1f * logf(1.0f / freq_scale)); + + const float mscale = + attn_factor_org * (1.0f + 0.1f * hparams.rope_yarn_log_mul * logf(1.0f / freq_scale)); + + const float kq_scale = + 1.0f * mscale * mscale / sqrtf(float(n_embd_head_k_mla)); + + q_pe = ggml_rope_ext(ctx0, q_pe, inp_pos, nullptr, + n_rot, rope_type, n_ctx_orig, freq_base, freq_scale, + ext_factor, attn_factor, beta_fast, beta_slow); + cb(q_pe, "mtp_q_pe_rope", il); + + k_pe = ggml_rope_ext(ctx0, k_pe, inp_pos, nullptr, + n_rot, rope_type, n_ctx_orig, freq_base, freq_scale, + ext_factor, attn_factor, beta_fast, beta_slow); + cb(k_pe, "mtp_k_pe_rope", il); + + q_nope = ggml_permute(ctx0, q_nope, 0, 2, 1, 3); + cb(q_nope, "mtp_q_nope_perm", il); + + ggml_tensor * q_nope_absorbed = ggml_mul_mat(ctx0, layer.wk_b, q_nope); + cb(q_nope_absorbed, "mtp_q_nope_absorbed", il); + + q_nope_absorbed = ggml_permute(ctx0, q_nope_absorbed, 0, 2, 1, 3); + cb(q_nope_absorbed, "mtp_q_nope_absorbed_perm", il); + + ggml_tensor * Qcur = ggml_concat(ctx0, q_nope_absorbed, q_pe, 0); + cb(Qcur, "mtp_Qcur", il); + + kv_cmpr = ggml_reshape_3d(ctx0, kv_cmpr, hparams.n_lora_kv, 1, n_tokens); + cb(kv_cmpr, "mtp_kv_cmpr_reshape", il); + + ggml_tensor * Kcur = ggml_concat(ctx0, kv_cmpr, k_pe, 0); + cb(Kcur, "mtp_Kcur", il); + + ggml_tensor * Vcur = kv_cmpr; + cb(Vcur, "mtp_Vcur", il); + + cur = build_attn(inp_attn_k, + layer.wo, nullptr, layer.wo_s, + Qcur, Kcur, Vcur, nullptr, nullptr, layer.wv_b, kq_scale, il); + cb(cur, "mtp_attn_out", il); + + ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA); + cb(ffn_inp, "mtp_ffn_inp", il); + + cur = build_norm(ffn_inp, layer.ffn_norm, nullptr, LLM_NORM_RMS, il); + cb(cur, "mtp_ffn_norm", il); + + ggml_tensor * moe_out = build_moe_ffn(cur, + layer.ffn_gate_inp, + layer.ffn_up_exps, + layer.ffn_gate_exps, + layer.ffn_down_exps, + layer.ffn_exp_probs_b, + n_expert, n_expert_used, + LLM_FFN_SILU, hparams.expert_weights_norm, + hparams.expert_weights_scale, + (llama_expert_gating_func_type) hparams.expert_gating_func, + il, + nullptr, + layer.ffn_gate_up_exps); + cb(moe_out, "mtp_ffn_moe_out", il); + + ggml_tensor * ffn_shexp = build_ffn(cur, + layer.ffn_up_shexp, nullptr, nullptr, + layer.ffn_gate_shexp, nullptr, nullptr, + layer.ffn_down_shexp, nullptr, nullptr, + nullptr, LLM_FFN_SILU, LLM_FFN_PAR, il); + cb(ffn_shexp, "mtp_ffn_shexp", il); + + cur = ggml_add(ctx0, moe_out, ffn_shexp); + cb(cur, "mtp_ffn_out", il); + + cur = ggml_add(ctx0, cur, ffn_inp); + cb(cur, "mtp_post_ffn", il); + + ggml_tensor * head_norm_w = layer.nextn.shared_head_norm + ? layer.nextn.shared_head_norm + : model.output_norm; + GGML_ASSERT(head_norm_w && "GLM4 MTP: missing both nextn.shared_head_norm and output_norm"); + + cur = build_norm(cur, head_norm_w, nullptr, LLM_NORM_RMS, -1); + cb(cur, "h_nextn", -1); + res->t_h_nextn = cur; + + if (inp_out_ids) { + cur = ggml_get_rows(ctx0, cur, inp_out_ids); + } + cb(cur, "mtp_shared_head_norm", -1); + + ggml_tensor * head_w = layer.nextn.shared_head_head + ? layer.nextn.shared_head_head + : model.output; + + ggml_tensor * head_s = layer.nextn.shared_head_head + ? layer.nextn.shared_head_head_s + : model.output_s; + + GGML_ASSERT(head_w && "GLM4 MTP: missing LM head (nextn.shared_head_head or model.output)"); + + cur = build_lora_mm(head_w, cur, head_s); + cb(cur, "result_output", -1); + + res->t_logits = cur; + ggml_build_forward_expand(gf, cur); +} + llama_model_deepseek2::graph::graph(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) { // lite variants include DeepSeek-V2-Lite, GigaChat3-10B-A1.8B @@ -365,7 +641,7 @@ llama_model_deepseek2::graph::graph(const llama_model & model, const llm_graph_p Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, kq_scale, il); } } - if (il == n_layer - 1 && inp_out_ids) { + if (il == n_layer - 1 && inp_out_ids && (!cparams.embeddings_nextn || cparams.embeddings_nextn_masked)) { cur = ggml_get_rows(ctx0, cur, inp_out_ids); inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids); } @@ -425,6 +701,13 @@ llama_model_deepseek2::graph::graph(const llama_model & model, const llm_graph_p cur = build_norm(cur, model.output_norm, NULL, LLM_NORM_RMS, -1); + cb(cur, "h_nextn", -1); + res->t_h_nextn = cur; + + if (cparams.embeddings_nextn && !cparams.embeddings_nextn_masked && inp_out_ids) { + cur = ggml_get_rows(ctx0, cur, inp_out_ids); + } + cb(cur, "result_norm", -1); res->t_embd = cur; diff --git a/src/models/deepseek32.cpp b/src/models/deepseek32.cpp index 32262e6840b0..8a07a0b71cae 100644 --- a/src/models/deepseek32.cpp +++ b/src/models/deepseek32.cpp @@ -44,13 +44,24 @@ void llama_model_deepseek32::load_arch_hparams(llama_model_loader & ml) { GGML_ASSERT(hparams.n_layer_nextn < hparams.n_layer_all && "n_layer_nextn must be < n_layer"); switch (hparams.n_layer()) { - case 62: type = LLM_TYPE_685B_A37B; break; + case 61: type = LLM_TYPE_685B_A37B; break; default: type = LLM_TYPE_UNKNOWN; } } -void llama_model_deepseek32::load_arch_tensors(llama_model_loader &) { +void llama_model_deepseek32::load_arch_tensors(llama_model_loader & ml) { LLAMA_LOAD_LOCALS; + + const bool mtp_only = (hparams.n_layer_nextn > 0) && (ml.get_weight("blk.0.attn_norm.weight") == nullptr); + const std::string mtp_probe = "blk." + std::to_string(n_layer) + ".nextn.eh_proj.weight"; + const bool trunk_only = (hparams.n_layer_nextn > 0) && (ml.get_weight(mtp_probe.c_str()) == nullptr); + const int trunk_flags = mtp_only ? TENSOR_NOT_REQUIRED : 0; + int mtp_flags = trunk_only ? TENSOR_NOT_REQUIRED : 0; + + if (!ml.load_mtp) { + mtp_flags |= TENSOR_SKIP; + } + const bool is_mla = hparams.is_mla(); if (!is_mla) { throw std::runtime_error("DEEPSEEK32 architecture requires MLA"); @@ -80,12 +91,7 @@ void llama_model_deepseek32::load_arch_tensors(llama_model_loader &) { } for (int i = 0; i < n_layer_all; ++i) { - int flags = 0; - if (i >= n_layer) { - // skip all tensors in the NextN layers - // TODO @ngxson : TENSOR_NOT_REQUIRED was a hack, need to remove it later - flags |= TENSOR_SKIP | TENSOR_NOT_REQUIRED; - } + const int flags = (i >= n_layer) ? mtp_flags : trunk_flags; auto & layer = layers[i]; @@ -138,7 +144,7 @@ void llama_model_deepseek32::load_arch_tensors(llama_model_loader &) { layer.ffn_up_shexp = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP, "weight", i), {n_embd, n_ff_exp * n_expert_shared}, flags); } - // NextN/MTP tensors (preserved but unused) - conditionally load for last nextn_predict_layers + // NextN/MTP tensors - conditionally load for last nextn_predict_layers if (i >= n_layer) { layer.nextn.eh_proj = create_tensor(tn(LLM_TENSOR_NEXTN_EH_PROJ, "weight", i), { 2 * n_embd, n_embd }, flags); layer.nextn.enorm = create_tensor(tn(LLM_TENSOR_NEXTN_ENORM, "weight", i), { n_embd }, flags); @@ -153,6 +159,9 @@ void llama_model_deepseek32::load_arch_tensors(llama_model_loader &) { } std::unique_ptr llama_model_deepseek32::build_arch_graph(const llm_graph_params & params) const { + if (params.gtype == LLM_GRAPH_TYPE_DECODER_MTP) { + return std::make_unique(*this, params); + } return std::make_unique(*this, params); } @@ -430,7 +439,9 @@ llama_model_deepseek32::graph::graph(const llama_model & model, const llm_graph_ Qcur, Kcur, Vcur, nullptr, nullptr, model.layers[il].wv_b, top_k, kq_scale, il); } } - if (il == n_layer - 1 && inp_out_ids) { + // when unmasked nextn embeddings are requested, t_h_nextn must keep all rows, + // so the early output masking has to be skipped (it is applied after the final norm instead) + if (il == n_layer - 1 && inp_out_ids && (!cparams.embeddings_nextn || cparams.embeddings_nextn_masked)) { cur = ggml_get_rows(ctx0, cur, inp_out_ids); inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids); } @@ -493,6 +504,14 @@ llama_model_deepseek32::graph::graph(const llama_model & model, const llm_graph_ cur = build_norm(cur, model.output_norm, NULL, LLM_NORM_RMS, -1); + // post-norm hidden state feeds the NextN/MTP draft head + cb(cur, "h_nextn", -1); + res->t_h_nextn = cur; + + if (cparams.embeddings_nextn && !cparams.embeddings_nextn_masked && inp_out_ids) { + cur = ggml_get_rows(ctx0, cur, inp_out_ids); + } + cb(cur, "result_norm", -1); res->t_embd = cur; @@ -504,3 +523,243 @@ llama_model_deepseek32::graph::graph(const llama_model & model, const llm_graph_ ggml_build_forward_expand(gf, cur); } + +// LLM_GRAPH_TYPE_DECODER_MTP draft head for DeepSeek V3.2 (DEEPSEEK32). +// Semantics mirror the deepseek-family NextN/MTP layer: +// enorm(embed) + hnorm(prev_hidden) -> concat(e, h) -> eh_proj -> +// full deepseek32 decoder block (dense MLA attention + sigmoid-gated MoE FFN +// with shared expert, exactly as the trunk deepseek2 graph builds it) -> +// shared_head_norm (fallback output_norm) -> shared LM head. +// The DSA indexer is not used at runtime. +llama_model_deepseek32::graph_mtp::graph_mtp(const llama_model & model, const llm_graph_params & params) + : llm_graph_context(params) { + GGML_ASSERT(hparams.n_layer_nextn > 0 && "DEEPSEEK32 MTP requires n_layer_nextn > 0"); + GGML_ASSERT(hparams.n_layer_nextn == 1 && "DEEPSEEK32 MTP currently only supports a single MTP block"); + GGML_ASSERT(hparams.is_mla() && "DEEPSEEK32 MTP requires MLA"); + + const int il = hparams.n_layer() + cparams.nextn_layer_offset; + GGML_ASSERT(cparams.nextn_layer_offset >= 0 && + cparams.nextn_layer_offset < (int) hparams.n_layer_nextn && + "nextn_layer_offset out of range [0, n_layer_nextn)"); + const auto & layer = model.layers[il]; + + GGML_ASSERT(layer.nextn.eh_proj && "MTP block missing nextn.eh_proj"); + GGML_ASSERT(layer.nextn.enorm && "MTP block missing nextn.enorm"); + GGML_ASSERT(layer.nextn.hnorm && "MTP block missing nextn.hnorm"); + GGML_ASSERT(layer.ffn_gate_inp && "MTP block missing ffn_gate_inp"); + + // note: these are the actual head sizes you get when treating as MHA or after "decompression" using wv_b for MLA + const int64_t n_embd_head_k = hparams.n_embd_head_k_mla(); + + const int64_t n_embd_head_qk_rope = hparams.n_rot(); + const int64_t n_embd_head_qk_nope = n_embd_head_k - n_embd_head_qk_rope; + + const uint32_t kv_lora_rank = hparams.n_lora_kv; + + // We have to pre-scale kq_scale and attn_factor to make the YaRN RoPE work correctly. + // See the deepseek2 trunk graph for the detailed explanation - this must match it EXACTLY. + GGML_ASSERT(ext_factor >= 0.0f); + const float attn_factor_org = attn_factor * (1.0f + 0.1f * logf(1.0f / freq_scale)); + + const float mscale = attn_factor_org * (1.0f + 0.1f * hparams.rope_yarn_log_mul * logf(1.0f / freq_scale)); + const float kq_scale = 1.0f * mscale * mscale / sqrtf(float(n_embd_head_k)); + + // TODO: extract in a common llm_graph_context::build_inp_embd_h() + auto inp = std::make_unique(hparams.n_embd); + + inp->tokens = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_tokens); + ggml_set_input(inp->tokens); + + inp->embd = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, hparams.n_embd_inp(), n_tokens); + ggml_set_input(inp->embd); + + ggml_tensor * tok_embd; + if (ubatch.token) { + ggml_tensor * tok_embd_w = layer.nextn.embed_tokens ? layer.nextn.embed_tokens : model.tok_embd; + + tok_embd = ggml_get_rows(ctx0, tok_embd_w, inp->tokens); + } else { + tok_embd = inp->embd; + } + cb(tok_embd, "mtp_tok_embd", il); + + inp->h = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, hparams.n_embd, n_tokens); + ggml_set_input(inp->h); + ggml_set_name(inp->h, "mtp_h_input"); + + ggml_tensor * h_embd = inp->h; + + res->add_input(std::move(inp)); + + ggml_tensor * inp_pos = build_inp_pos(); + ggml_tensor * inp_out_ids = build_inp_out_ids(); + + // MLA with the absorption optimization uses a K-only cache (V is a view of K) + auto * inp_attn = build_attn_inp_k(); + + ggml_tensor * h_norm = build_norm(h_embd, layer.nextn.hnorm, nullptr, LLM_NORM_RMS, il); + cb(h_norm, "mtp_hnorm", il); + + ggml_tensor * e_norm = build_norm(tok_embd, layer.nextn.enorm, nullptr, LLM_NORM_RMS, il); + cb(e_norm, "mtp_enorm", il); + + ggml_tensor * concat = ggml_concat(ctx0, e_norm, h_norm, /*dim=*/ 0); + cb(concat, "mtp_concat", il); + + ggml_tensor * cur = build_lora_mm(layer.nextn.eh_proj, concat, layer.nextn.eh_proj_s); + cb(cur, "mtp_eh_proj", il); + + ggml_tensor * inpSA = cur; + + cur = build_norm(cur, layer.attn_norm, nullptr, LLM_NORM_RMS, il); + cb(cur, "mtp_attn_norm", il); + + // self-attention: dense MLA, same construction as the deepseek2 trunk graph + { + ggml_tensor * q = ggml_mul_mat(ctx0, layer.wq_a, cur); + cb(q, "mtp_q", il); + + q = build_norm(q, layer.attn_q_a_norm, nullptr, LLM_NORM_RMS, il); + cb(q, "mtp_q", il); + + q = ggml_mul_mat(ctx0, layer.wq_b, q); + cb(q, "mtp_q", il); + + // split into {n_embd_head_qk_nope, n_head, n_tokens} + ggml_tensor * q_nope = + ggml_view_3d(ctx0, q, n_embd_head_qk_nope, n_head, n_tokens, ggml_row_size(q->type, n_embd_head_k), + ggml_row_size(q->type, n_embd_head_k) * n_head, 0); + cb(q_nope, "mtp_q_nope", il); + + // and {n_embd_head_qk_rope, n_head, n_tokens} + ggml_tensor * q_pe = ggml_view_3d( + ctx0, q, n_embd_head_qk_rope, n_head, n_tokens, ggml_row_size(q->type, n_embd_head_k), + ggml_row_size(q->type, n_embd_head_k) * n_head, ggml_row_size(q->type, n_embd_head_qk_nope)); + cb(q_pe, "mtp_q_pe", il); + + ggml_tensor * kv_cmpr_pe = ggml_mul_mat(ctx0, layer.wkv_a_mqa, cur); + cb(kv_cmpr_pe, "mtp_kv_cmpr_pe", il); + + // split into {kv_lora_rank, n_tokens} + ggml_tensor * kv_cmpr = + ggml_view_2d(ctx0, kv_cmpr_pe, kv_lora_rank, n_tokens, + ggml_row_size(kv_cmpr_pe->type, kv_lora_rank + n_embd_head_qk_rope), 0); + cb(kv_cmpr, "mtp_kv_cmpr", il); + + // and {n_embd_head_qk_rope, 1, n_tokens} + ggml_tensor * k_pe = ggml_view_3d(ctx0, kv_cmpr_pe, n_embd_head_qk_rope, 1, n_tokens, + ggml_row_size(kv_cmpr_pe->type, kv_lora_rank + n_embd_head_qk_rope), + ggml_row_size(kv_cmpr_pe->type, kv_lora_rank + n_embd_head_qk_rope), + ggml_row_size(kv_cmpr_pe->type, kv_lora_rank)); + cb(k_pe, "mtp_k_pe", il); + + q_pe = ggml_rope_ext(ctx0, q_pe, inp_pos, nullptr, n_rot, rope_type, n_ctx_orig, freq_base, freq_scale, + ext_factor, attn_factor, beta_fast, beta_slow); + cb(q_pe, "mtp_q_pe", il); + + k_pe = ggml_rope_ext(ctx0, k_pe, inp_pos, nullptr, n_rot, rope_type, n_ctx_orig, freq_base, freq_scale, + ext_factor, attn_factor, beta_fast, beta_slow); + cb(k_pe, "mtp_k_pe", il); + + kv_cmpr = build_norm(kv_cmpr, layer.attn_kv_a_norm, nullptr, LLM_NORM_RMS, il); + cb(kv_cmpr, "mtp_kv_cmpr", il); + + // {n_embd_head_qk_nope, n_tokens, n_head} + q_nope = ggml_permute(ctx0, q_nope, 0, 2, 1, 3); + cb(q_nope, "mtp_q_nope_perm", il); + + // {n_embd_head_qk_nope, kv_lora_rank, n_head} x {n_embd_head_qk_nope, n_tokens, n_head} + ggml_tensor * q_nope_absorbed = ggml_mul_mat(ctx0, layer.wk_b, q_nope); + cb(q_nope_absorbed, "mtp_q_nope_absorbed", il); + + // {kv_lora_rank, n_head, n_tokens} + q_nope_absorbed = ggml_permute(ctx0, q_nope_absorbed, 0, 2, 1, 3); + cb(q_nope_absorbed, "mtp_q_nope_absorbed_perm", il); + + // {n_embd_head_qk_rope + kv_lora_rank, n_head, n_tokens} + // note: rope must go first for in-place context shifting in build_rope_shift() + ggml_tensor * Qcur = ggml_concat(ctx0, q_nope_absorbed, q_pe, 0); + cb(Qcur, "mtp_Qcur", il); + + kv_cmpr = ggml_reshape_3d(ctx0, kv_cmpr, kv_lora_rank, 1, n_tokens); + cb(kv_cmpr, "mtp_kv_cmpr_reshape", il); + + // {n_embd_head_qk_rope + kv_lora_rank, 1, n_tokens} + ggml_tensor * Kcur = ggml_concat(ctx0, kv_cmpr, k_pe, 0); + cb(Kcur, "mtp_Kcur", il); + + // {kv_lora_rank, 1, n_tokens} + ggml_tensor * Vcur = kv_cmpr; + cb(Vcur, "mtp_Vcur", il); + + // note: MLA with the absorption optimization converts into MQA (ie: GQA with 1 group) + cur = build_attn(inp_attn, + layer.wo, NULL, layer.wo_s, + Qcur, Kcur, Vcur, nullptr, nullptr, layer.wv_b, kq_scale, il); + cb(cur, "mtp_attn_out", il); + } + + ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA); + cb(ffn_inp, "mtp_ffn_inp", il); + + cur = build_norm(ffn_inp, layer.ffn_norm, NULL, LLM_NORM_RMS, il); + cb(cur, "mtp_ffn_norm", il); + + // MoE FFN with shared expert - same construction as the deepseek2 trunk graph + ggml_tensor * moe_out = build_moe_ffn(cur, + layer.ffn_gate_inp, + layer.ffn_up_exps, + layer.ffn_gate_exps, + layer.ffn_down_exps, + layer.ffn_exp_probs_b, + n_expert, n_expert_used, + LLM_FFN_SILU, hparams.expert_weights_norm, + hparams.expert_weights_scale, + (llama_expert_gating_func_type) hparams.expert_gating_func, + il, + nullptr, + layer.ffn_gate_up_exps, + layer.ffn_up_exps_s, + layer.ffn_gate_exps_s, + layer.ffn_down_exps_s); + cb(moe_out, "mtp_ffn_moe_out", il); + + // FFN shared expert + ggml_tensor * ffn_shexp = + build_ffn(cur, + layer.ffn_up_shexp, NULL, layer.ffn_up_shexp_s, + layer.ffn_gate_shexp, NULL, layer.ffn_gate_shexp_s, + layer.ffn_down_shexp, NULL, layer.ffn_down_shexp_s, + NULL, LLM_FFN_SILU, LLM_FFN_PAR, il); + cb(ffn_shexp, "mtp_ffn_shexp", il); + + cur = ggml_add(ctx0, moe_out, ffn_shexp); + cb(cur, "mtp_ffn_out", il); + + cur = ggml_add(ctx0, cur, ffn_inp); + cb(cur, "mtp_post_ffn", il); + + // shared_head_norm applied after the decoder block, before the shared LM head. + // The post-norm hidden state seeds the next MTP step. + ggml_tensor * head_norm_w = layer.nextn.shared_head_norm + ? layer.nextn.shared_head_norm + : model.output_norm; + GGML_ASSERT(head_norm_w && "DEEPSEEK32 MTP: missing both nextn.shared_head_norm and output_norm"); + cur = build_norm(cur, head_norm_w, nullptr, LLM_NORM_RMS, -1); + + cb(cur, "h_nextn", -1); + res->t_h_nextn = cur; + + cur = ggml_get_rows(ctx0, cur, inp_out_ids); + cb(cur, "mtp_shared_head_norm", -1); + + ggml_tensor * head_w = layer.nextn.shared_head_head ? layer.nextn.shared_head_head : model.output; + ggml_tensor * head_s = layer.nextn.shared_head_head ? layer.nextn.shared_head_head_s : model.output_s; + GGML_ASSERT(head_w && "DEEPSEEK32 MTP: missing LM head (nextn.shared_head_head or model.output)"); + cur = build_lora_mm(head_w, cur, head_s); + cb(cur, "result_output", -1); + + res->t_logits = cur; + ggml_build_forward_expand(gf, cur); +} + diff --git a/src/models/deepseek4.cpp b/src/models/deepseek4.cpp index 2d41dace0b28..89cd461765ad 100644 --- a/src/models/deepseek4.cpp +++ b/src/models/deepseek4.cpp @@ -16,6 +16,16 @@ static float dsv4_rope_attn_factor(float freq_scale, float ext_factor) { } void llama_model_deepseek4::load_arch_hparams(llama_model_loader & ml) { + ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.n_layer_nextn, false); + if (hparams.n_layer_nextn > 0 && hparams.n_layer_nextn < hparams.n_layer_all) { + const uint32_t n_layer_main = hparams.n_layer_all - hparams.n_layer_nextn; + const std::string mtp_probe = "blk." + std::to_string(n_layer_main) + ".nextn.eh_proj.weight"; + if (ml.get_weight(mtp_probe.c_str()) == nullptr) { + hparams.n_layer_nextn = 0; + } + } + GGML_ASSERT(hparams.n_layer_nextn < hparams.n_layer_all && "n_layer_nextn must be < block_count"); + ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); ml.get_key(LLM_KV_ATTENTION_Q_LORA_RANK, hparams.n_lora_q); ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa); @@ -24,8 +34,8 @@ void llama_model_deepseek4::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_EXPERT_SHARED_COUNT, hparams.n_expert_shared); ml.get_key(LLM_KV_EXPERT_WEIGHTS_SCALE, hparams.expert_weights_scale); ml.get_key(LLM_KV_EXPERT_WEIGHTS_NORM, hparams.expert_weights_norm); - ml.get_key_or_arr(LLM_KV_SWIGLU_CLAMP_EXP, hparams.swiglu_clamp_exp, hparams.n_layer()); - if (!ml.get_key_or_arr(LLM_KV_SWIGLU_CLAMP_SHEXP, hparams.swiglu_clamp_shexp, hparams.n_layer(), 0)) { + ml.get_key_or_arr(LLM_KV_SWIGLU_CLAMP_EXP, hparams.swiglu_clamp_exp, hparams.n_layer_all); + if (!ml.get_key_or_arr(LLM_KV_SWIGLU_CLAMP_SHEXP, hparams.swiglu_clamp_shexp, hparams.n_layer_all, 0)) { hparams.swiglu_clamp_shexp = hparams.swiglu_clamp_exp; } @@ -41,9 +51,11 @@ void llama_model_deepseek4::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_HYPER_CONNECTION_EPSILON, hparams.dsv4_hc_eps); ml.get_key(LLM_KV_HASH_LAYER_COUNT, hparams.dsv4_hash_layer_count); + hparams.n_embd_out_impl = hparams.dsv4_hc_mult * hparams.n_embd; + uint32_t n_compress_ratios = 0; ml.get_arr_n(LLM_KV_ATTENTION_COMPRESS_RATIOS, n_compress_ratios); - if (n_compress_ratios < hparams.n_layer()) { + if (n_compress_ratios < hparams.n_layer_all) { throw std::runtime_error("DeepSeek-V4 compress_ratios is shorter than block_count"); } ml.get_arr(LLM_KV_ATTENTION_COMPRESS_RATIOS, hparams.dsv4_compress_ratios); @@ -54,6 +66,9 @@ void llama_model_deepseek4::load_arch_hparams(llama_model_loader & ml) { } hparams.swa_type = LLAMA_SWA_TYPE_STANDARD; hparams.set_swa_pattern(0); + for (uint32_t il = hparams.n_layer(); il < hparams.n_layer_all; ++il) { + hparams.is_swa_impl[il] = true; + } switch (hparams.n_layer()) { case 43: type = LLM_TYPE_UNKNOWN; break; @@ -61,7 +76,7 @@ void llama_model_deepseek4::load_arch_hparams(llama_model_loader & ml) { } } -void llama_model_deepseek4::load_arch_tensors(llama_model_loader &) { +void llama_model_deepseek4::load_arch_tensors(llama_model_loader & ml) { LLAMA_LOAD_LOCALS; const int64_t q_lora_rank = hparams.n_lora_q; @@ -75,6 +90,10 @@ void llama_model_deepseek4::load_arch_tensors(llama_model_loader &) { const int64_t hc_dim = hc_mult * n_embd; const int64_t hc_mix_dim = (2 + hc_mult) * hc_mult; + const bool mtp_only = (n_layer_nextn > 0) && (ml.get_weight("blk.0.attn_norm.weight") == nullptr); + const int trunk_flags = mtp_only ? TENSOR_NOT_REQUIRED : 0; + const int mtp_flags = ml.load_mtp ? 0 : TENSOR_SKIP; + tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0); output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0); @@ -84,69 +103,84 @@ void llama_model_deepseek4::load_arch_tensors(llama_model_loader &) { hc_head_base = create_tensor(tn(LLM_TENSOR_HC_HEAD_BASE, "weight"), {hc_mult}, 0); hc_head_scale = create_tensor(tn(LLM_TENSOR_HC_HEAD_SCALE, "weight"), {1}, 0); - for (int i = 0; i < n_layer; ++i) { + for (int i = 0; i < n_layer_all; ++i) { auto & layer = layers[i]; - - layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, 0); - layer.attn_sinks = create_tensor(tn(LLM_TENSOR_ATTN_SINKS, "weight", i), {n_head}, 0); - layer.wq_a = create_tensor(tn(LLM_TENSOR_ATTN_Q_A, "weight", i), {n_embd, q_lora_rank}, 0); - layer.attn_q_a_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_A_NORM, "weight", i), {q_lora_rank}, 0); - layer.wq_b = create_tensor(tn(LLM_TENSOR_ATTN_Q_B, "weight", i), {q_lora_rank, n_head * n_embd_head}, 0); - layer.wkv = create_tensor(tn(LLM_TENSOR_ATTN_KV, "weight", i), {n_embd, n_embd_head}, 0); - layer.attn_kv_norm = create_tensor(tn(LLM_TENSOR_ATTN_KV_NORM, "weight", i), {n_embd_head}, 0); - layer.wo_a = create_tensor(tn(LLM_TENSOR_ATTN_OUT_A, "weight", i), {n_head * n_embd_head / o_groups, o_lora_rank * o_groups}, 0); - layer.wo_b = create_tensor(tn(LLM_TENSOR_ATTN_OUT_B, "weight", i), {o_groups * o_lora_rank, n_embd}, 0); - - layer.hc_attn_fn = create_tensor(tn(LLM_TENSOR_HC_ATTN_FN, "weight", i), {hc_dim, hc_mix_dim}, 0); - layer.hc_attn_base = create_tensor(tn(LLM_TENSOR_HC_ATTN_BASE, "weight", i), {hc_mix_dim}, 0); - layer.hc_attn_scale = create_tensor(tn(LLM_TENSOR_HC_ATTN_SCALE, "weight", i), {3}, 0); - layer.hc_ffn_fn = create_tensor(tn(LLM_TENSOR_HC_FFN_FN, "weight", i), {hc_dim, hc_mix_dim}, 0); - layer.hc_ffn_base = create_tensor(tn(LLM_TENSOR_HC_FFN_BASE, "weight", i), {hc_mix_dim}, 0); - layer.hc_ffn_scale = create_tensor(tn(LLM_TENSOR_HC_FFN_SCALE, "weight", i), {3}, 0); + const int flags = i < n_layer ? trunk_flags : mtp_flags; + + layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, flags); + layer.attn_sinks = create_tensor(tn(LLM_TENSOR_ATTN_SINKS, "weight", i), {n_head}, flags); + layer.wq_a = create_tensor(tn(LLM_TENSOR_ATTN_Q_A, "weight", i), {n_embd, q_lora_rank}, flags); + layer.attn_q_a_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_A_NORM, "weight", i), {q_lora_rank}, flags); + layer.wq_b = create_tensor(tn(LLM_TENSOR_ATTN_Q_B, "weight", i), {q_lora_rank, n_head * n_embd_head}, flags); + layer.wkv = create_tensor(tn(LLM_TENSOR_ATTN_KV, "weight", i), {n_embd, n_embd_head}, flags); + layer.attn_kv_norm = create_tensor(tn(LLM_TENSOR_ATTN_KV_NORM, "weight", i), {n_embd_head}, flags); + // for wo_a, the shape in the file is (n_head * n_embd_head / o_groups, o_lora_rank*o_groups) + // so we reshape here, to avoid reshaping the tensor in the graph + layer.wo_a = create_tensor(tn(LLM_TENSOR_ATTN_OUT_A, "weight", i), {n_head * n_embd_head / o_groups, o_lora_rank, o_groups}, flags | TENSOR_ALLOW_RESHAPE); + layer.wo_b = create_tensor(tn(LLM_TENSOR_ATTN_OUT_B, "weight", i), {o_groups * o_lora_rank, n_embd}, flags); + + layer.hc_attn_fn = create_tensor(tn(LLM_TENSOR_HC_ATTN_FN, "weight", i), {hc_dim, hc_mix_dim}, flags); + layer.hc_attn_base = create_tensor(tn(LLM_TENSOR_HC_ATTN_BASE, "weight", i), {hc_mix_dim}, flags); + layer.hc_attn_scale = create_tensor(tn(LLM_TENSOR_HC_ATTN_SCALE, "weight", i), {3}, flags); + layer.hc_ffn_fn = create_tensor(tn(LLM_TENSOR_HC_FFN_FN, "weight", i), {hc_dim, hc_mix_dim}, flags); + layer.hc_ffn_base = create_tensor(tn(LLM_TENSOR_HC_FFN_BASE, "weight", i), {hc_mix_dim}, flags); + layer.hc_ffn_scale = create_tensor(tn(LLM_TENSOR_HC_FFN_SCALE, "weight", i), {3}, flags); const int64_t ratio = hparams.dsv4_compress_ratios[i]; if (ratio != 0) { const int64_t coff = ratio == 4 ? 2 : 1; - layer.attn_comp_wkv = create_tensor(tn(LLM_TENSOR_ATTN_COMPRESSOR_WKV, "weight", i), {n_embd, coff * n_embd_head}, 0); - layer.attn_comp_wgate = create_tensor(tn(LLM_TENSOR_ATTN_COMPRESSOR_WGATE, "weight", i), {n_embd, coff * n_embd_head}, 0); - layer.attn_comp_ape = create_tensor(tn(LLM_TENSOR_ATTN_COMPRESSOR_APE, "weight", i), {coff * n_embd_head, ratio}, 0); - layer.attn_comp_norm = create_tensor(tn(LLM_TENSOR_ATTN_COMPRESSOR_NORM, "weight", i), {n_embd_head}, 0); + layer.attn_comp_wkv = create_tensor(tn(LLM_TENSOR_ATTN_COMPRESSOR_WKV, "weight", i), {n_embd, coff * n_embd_head}, flags); + layer.attn_comp_wgate = create_tensor(tn(LLM_TENSOR_ATTN_COMPRESSOR_WGATE, "weight", i), {n_embd, coff * n_embd_head}, flags); + layer.attn_comp_ape = create_tensor(tn(LLM_TENSOR_ATTN_COMPRESSOR_APE, "weight", i), {coff * n_embd_head, ratio}, flags); + layer.attn_comp_norm = create_tensor(tn(LLM_TENSOR_ATTN_COMPRESSOR_NORM, "weight", i), {n_embd_head}, flags); if (ratio == 4) { const int64_t n_embd_indexer = hparams.indexer_head_size; - layer.indexer_proj = create_tensor(tn(LLM_TENSOR_INDEXER_PROJ, "weight", i), {n_embd, hparams.indexer_n_head}, 0); - layer.indexer_attn_q_b = create_tensor(tn(LLM_TENSOR_INDEXER_ATTN_Q_B, "weight", i), {q_lora_rank, hparams.indexer_n_head * n_embd_indexer}, 0); + layer.indexer_proj = create_tensor(tn(LLM_TENSOR_INDEXER_PROJ, "weight", i), {n_embd, hparams.indexer_n_head}, flags); + layer.indexer_attn_q_b = create_tensor(tn(LLM_TENSOR_INDEXER_ATTN_Q_B, "weight", i), {q_lora_rank, hparams.indexer_n_head * n_embd_indexer}, flags); - layer.indexer_comp_wkv = create_tensor(tn(LLM_TENSOR_INDEXER_COMPRESSOR_WKV, "weight", i), {n_embd, 2 * n_embd_indexer}, 0); - layer.indexer_comp_wgate = create_tensor(tn(LLM_TENSOR_INDEXER_COMPRESSOR_WGATE, "weight", i), {n_embd, 2 * n_embd_indexer}, 0); - layer.indexer_comp_ape = create_tensor(tn(LLM_TENSOR_INDEXER_COMPRESSOR_APE, "weight", i), {2 * n_embd_indexer, ratio}, 0); - layer.indexer_comp_norm = create_tensor(tn(LLM_TENSOR_INDEXER_COMPRESSOR_NORM, "weight", i), {n_embd_indexer}, 0); + layer.indexer_comp_wkv = create_tensor(tn(LLM_TENSOR_INDEXER_COMPRESSOR_WKV, "weight", i), {n_embd, 2 * n_embd_indexer}, flags); + layer.indexer_comp_wgate = create_tensor(tn(LLM_TENSOR_INDEXER_COMPRESSOR_WGATE, "weight", i), {n_embd, 2 * n_embd_indexer}, flags); + layer.indexer_comp_ape = create_tensor(tn(LLM_TENSOR_INDEXER_COMPRESSOR_APE, "weight", i), {2 * n_embd_indexer, ratio}, flags); + layer.indexer_comp_norm = create_tensor(tn(LLM_TENSOR_INDEXER_COMPRESSOR_NORM, "weight", i), {n_embd_indexer}, flags); } else if (ratio != 128) { throw std::runtime_error("DeepSeek-V4 loader only supports compression ratios 0, 4, and 128"); } } - layer.ffn_gate_inp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert}, 0); + layer.ffn_gate_inp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert}, flags); if ((uint32_t) i < hparams.dsv4_hash_layer_count) { - layer.ffn_gate_tid2eid = create_tensor(tn(LLM_TENSOR_FFN_GATE_TID2EID, "weight", i), {n_expert_used, n_vocab}, 0); + layer.ffn_gate_tid2eid = create_tensor(tn(LLM_TENSOR_FFN_GATE_TID2EID, "weight", i), {n_expert_used, n_vocab}, flags); } else { - layer.ffn_exp_probs_b = create_tensor(tn(LLM_TENSOR_FFN_EXP_PROBS_B, "bias", i), {n_expert}, 0); + layer.ffn_exp_probs_b = create_tensor(tn(LLM_TENSOR_FFN_EXP_PROBS_B, "bias", i), {n_expert}, flags); + } + layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, flags); + + layer.ffn_gate_exps = create_tensor(tn(LLM_TENSOR_FFN_GATE_EXPS, "weight", i), {n_embd, n_ff_exp, n_expert}, flags); + layer.ffn_down_exps = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), {n_ff_exp, n_embd, n_expert}, flags); + layer.ffn_up_exps = create_tensor(tn(LLM_TENSOR_FFN_UP_EXPS, "weight", i), {n_embd, n_ff_exp, n_expert}, flags); + + layer.ffn_gate_shexp = create_tensor(tn(LLM_TENSOR_FFN_GATE_SHEXP, "weight", i), {n_embd, n_ff_exp * n_expert_shared}, flags); + layer.ffn_down_shexp = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP, "weight", i), {n_ff_exp * n_expert_shared, n_embd }, flags); + layer.ffn_up_shexp = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP, "weight", i), {n_embd, n_ff_exp * n_expert_shared}, flags); + + if (i >= n_layer) { + layer.nextn.eh_proj = create_tensor(tn(LLM_TENSOR_NEXTN_EH_PROJ, "weight", i), {2 * n_embd, n_embd}, flags); + layer.nextn.enorm = create_tensor(tn(LLM_TENSOR_NEXTN_ENORM, "weight", i), {n_embd}, flags); + layer.nextn.hnorm = create_tensor(tn(LLM_TENSOR_NEXTN_HNORM, "weight", i), {n_embd}, flags); + layer.nextn.embed_tokens = create_tensor(tn(LLM_TENSOR_NEXTN_EMBED_TOKENS, "weight", i), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED | flags); + layer.nextn.shared_head_head = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_HEAD, "weight", i), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED | flags); + layer.nextn.shared_head_norm = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_NORM, "weight", i), {n_embd}, TENSOR_NOT_REQUIRED | flags); } - layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, 0); - - layer.ffn_gate_exps = create_tensor(tn(LLM_TENSOR_FFN_GATE_EXPS, "weight", i), {n_embd, n_ff_exp, n_expert}, 0); - layer.ffn_down_exps = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), {n_ff_exp, n_embd, n_expert}, 0); - layer.ffn_up_exps = create_tensor(tn(LLM_TENSOR_FFN_UP_EXPS, "weight", i), {n_embd, n_ff_exp, n_expert}, 0); - - layer.ffn_gate_shexp = create_tensor(tn(LLM_TENSOR_FFN_GATE_SHEXP, "weight", i), {n_embd, n_ff_exp * n_expert_shared}, 0); - layer.ffn_down_shexp = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP, "weight", i), {n_ff_exp * n_expert_shared, n_embd }, 0); - layer.ffn_up_shexp = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP, "weight", i), {n_embd, n_ff_exp * n_expert_shared}, 0); } } std::unique_ptr llama_model_deepseek4::build_arch_graph(const llm_graph_params & params) const { + if (params.gtype == LLM_GRAPH_TYPE_DECODER_MTP) { + return std::make_unique(*this, params); + } return std::make_unique(*this, params); } @@ -175,18 +209,69 @@ static ggml_tensor * dsv4_append_zero_row(ggml_context * ctx, ggml_tensor * t, b return ggml_concat(ctx, t, row, 1); } -static ggml_tensor * dsv4_with_zero_dep(ggml_context * ctx, ggml_tensor * t, ggml_tensor * dep) { - if (dep == nullptr) { - return t; +struct dsv4_state_tensors { + ggml_tensor * kv; + ggml_tensor * score; +}; + +static dsv4_state_tensors dsv4_build_state_restore( + ggml_context * ctx, + const llm_graph_input_dsv4::comp_input & inp, + const llama_dsv4_comp_state * state, + int32_t il) { + dsv4_state_tensors restored = { + state->get_kv_all(ctx, il), + state->get_score_all(ctx, il), + }; + + if (inp.state_restore_src_idxs == nullptr || inp.state_restore_dst_idxs == nullptr) { + return restored; + } + + ggml_tensor * kv_rows = ggml_get_rows(ctx, restored.kv, inp.state_restore_src_idxs); + restored.kv = state->cpy_kv(ctx, kv_rows, inp.state_restore_dst_idxs, il); + + ggml_tensor * score_rows = ggml_get_rows(ctx, restored.score, inp.state_restore_src_idxs); + restored.score = state->cpy_score(ctx, score_rows, inp.state_restore_dst_idxs, il); + + return restored; +} + +static dsv4_state_tensors dsv4_build_state_snapshot( + ggml_context * ctx, + const llm_graph_input_dsv4::comp_input & inp, + const llama_dsv4_comp_state * state, + ggml_tensor * source_kv, + ggml_tensor * source_score, + int32_t il) { + if (inp.state_snapshot_src_idxs == nullptr || inp.state_snapshot_dst_idxs == nullptr || + source_kv == nullptr || source_score == nullptr) { + return {}; } - ggml_tensor * zero = ggml_scale(ctx, ggml_sum(ctx, dep), 0.0f); - return ggml_add(ctx, t, zero); + ggml_tensor * kv_rows = ggml_get_rows(ctx, source_kv, inp.state_snapshot_src_idxs); + ggml_tensor * kv = state->cpy_kv(ctx, kv_rows, inp.state_snapshot_dst_idxs, il); + + ggml_tensor * score_rows = ggml_get_rows(ctx, source_score, inp.state_snapshot_src_idxs); + ggml_tensor * score = state->cpy_score(ctx, score_rows, inp.state_snapshot_dst_idxs, il); + + return { kv, score }; } static constexpr int64_t DSV4_CSA_RATIO = 4; static constexpr int64_t DSV4_HCA_RATIO = 128; +// mean over the hyper-connection streams: [n_embd, hc, n_tokens] -> [n_embd, n_tokens] +static ggml_tensor * dsv4_hc_mean(ggml_context * ctx, ggml_tensor * x) { + const int64_t hc = x->ne[1]; + + ggml_tensor * acc = ggml_view_2d(ctx, x, x->ne[0], x->ne[2], x->nb[2], 0); + for (int64_t s = 1; s < hc; ++s) { + acc = ggml_add(ctx, acc, ggml_view_2d(ctx, x, x->ne[0], x->ne[2], x->nb[2], s*x->nb[1])); + } + return ggml_scale(ctx, acc, 1.0f/hc); +} + static ggml_tensor * dsv4_hc_affine( ggml_context * ctx, ggml_tensor * x, @@ -804,8 +889,29 @@ ggml_tensor * llama_model_deepseek4::graph::build_attention( ggml_tensor * cur, ggml_tensor * inp_pos, int il) const { + return build_attention_impl(model, inp_dsv4, nullptr, cur, inp_pos, il); +} + +ggml_tensor * llama_model_deepseek4::graph::build_attention( + const llama_model & model, + llm_graph_input_attn_k_iswa * inp_mtp, + ggml_tensor * cur, + ggml_tensor * inp_pos, + int il) const { + return build_attention_impl(model, nullptr, inp_mtp, cur, inp_pos, il); +} + +ggml_tensor * llama_model_deepseek4::graph::build_attention_impl( + const llama_model & model, + llm_graph_input_dsv4 * inp_dsv4, + llm_graph_input_attn_k_iswa * inp_mtp, + ggml_tensor * cur, + ggml_tensor * inp_pos, + int il) const { + GGML_ASSERT((inp_dsv4 == nullptr) != (inp_mtp == nullptr)); + const auto & layer = model.layers[il]; - llm_graph_input_dsv4_raw * inp_attn = inp_dsv4->get_raw(); + llm_graph_input_dsv4_raw * inp_attn = inp_dsv4 ? inp_dsv4->get_raw() : nullptr; const int64_t n_embd_head = hparams.n_embd_head_k(); const int64_t n_embd_head_rope = hparams.n_rot(); @@ -873,9 +979,12 @@ ggml_tensor * llama_model_deepseek4::graph::build_attention( cb(kv, "kv", il); const int64_t ratio = hparams.dsv4_compress_ratios[il]; + GGML_ASSERT(inp_dsv4 || ratio == 0); ggml_tensor * hca_state_kv = nullptr; ggml_tensor * hca_state_score = nullptr; + ggml_tensor * hca_source_kv = nullptr; + ggml_tensor * hca_source_score = nullptr; if (ratio == DSV4_HCA_RATIO && inp_dsv4->get_hca().state_pos) { hca_state_kv = build_lora_mm(layer.attn_comp_wkv, cur); cb(hca_state_kv, "hca_state_kv", il); @@ -906,10 +1015,16 @@ ggml_tensor * llama_model_deepseek4::graph::build_attention( GGML_ASSERT(inp_dsv4->get_csa().state_write_idxs); - ggml_tensor * csa_source_kv = ggml_concat(ctx0, - inp_dsv4->mctx->get_csa_state()->get_kv(ctx0, il), csa_state_kv, 1); - ggml_tensor * csa_source_score = ggml_concat(ctx0, - inp_dsv4->mctx->get_csa_state()->get_score(ctx0, il), csa_state_score, 1); + const auto * csa_state = inp_dsv4->mctx->get_csa_state(); + const dsv4_state_tensors csa_restored = dsv4_build_state_restore( + ctx0, inp_dsv4->get_csa(), csa_state, il); + ggml_tensor * csa_base_kv = dsv4_view_2d( + ctx0, csa_restored.kv, csa_restored.kv->ne[0], csa_state->get_n_rows(), 0); + ggml_tensor * csa_base_score = dsv4_view_2d( + ctx0, csa_restored.score, csa_restored.score->ne[0], csa_state->get_n_rows(), 0); + + ggml_tensor * csa_source_kv = ggml_concat(ctx0, csa_base_kv, csa_state_kv, 1); + ggml_tensor * csa_source_score = ggml_concat(ctx0, csa_base_score, csa_state_score, 1); ggml_tensor * kv_comp_csa_state = build_overlap_compressed_kv_from_state( csa_source_kv, @@ -930,8 +1045,19 @@ ggml_tensor * llama_model_deepseek4::graph::build_attention( ggml_build_forward_expand(gf, inp_dsv4->mctx->get_csa()->cpy_k(ctx0, kv_comp_csa_state, inp_dsv4->get_csa().state_write_idxs, il)); - csa_state_kv = dsv4_with_zero_dep(ctx0, csa_state_kv, kv_comp_csa_state); - csa_state_score = dsv4_with_zero_dep(ctx0, csa_state_score, kv_comp_csa_state); + ggml_tensor * csa_snapshot_source_kv = ggml_concat(ctx0, + csa_restored.kv, csa_state_kv, 1); + ggml_tensor * csa_snapshot_source_score = ggml_concat(ctx0, + csa_restored.score, csa_state_score, 1); + + const dsv4_state_tensors csa_snapshot = dsv4_build_state_snapshot( + ctx0, inp_dsv4->get_csa(), csa_state, csa_snapshot_source_kv, csa_snapshot_source_score, il); + if (csa_snapshot.kv != nullptr) { + ggml_build_forward_expand(gf, csa_snapshot.kv); + } + if (csa_snapshot.score != nullptr) { + ggml_build_forward_expand(gf, csa_snapshot.score); + } ggml_tensor * csa_persist_kv = ggml_get_rows(ctx0, csa_state_kv, inp_dsv4->get_csa().state_persist_src_idxs); ggml_tensor * csa_persist_score = ggml_get_rows(ctx0, csa_state_score, inp_dsv4->get_csa().state_persist_src_idxs); @@ -958,10 +1084,16 @@ ggml_tensor * llama_model_deepseek4::graph::build_attention( GGML_ASSERT(inp_dsv4->get_lid().state_write_idxs); - ggml_tensor * lid_source_kv = ggml_concat(ctx0, - inp_dsv4->mctx->get_lid_state()->get_kv(ctx0, il), lid_state_kv, 1); - ggml_tensor * lid_source_score = ggml_concat(ctx0, - inp_dsv4->mctx->get_lid_state()->get_score(ctx0, il), lid_state_score, 1); + const auto * lid_state = inp_dsv4->mctx->get_lid_state(); + const dsv4_state_tensors lid_restored = dsv4_build_state_restore( + ctx0, inp_dsv4->get_lid(), lid_state, il); + ggml_tensor * lid_base_kv = dsv4_view_2d( + ctx0, lid_restored.kv, lid_restored.kv->ne[0], lid_state->get_n_rows(), 0); + ggml_tensor * lid_base_score = dsv4_view_2d( + ctx0, lid_restored.score, lid_restored.score->ne[0], lid_state->get_n_rows(), 0); + + ggml_tensor * lid_source_kv = ggml_concat(ctx0, lid_base_kv, lid_state_kv, 1); + ggml_tensor * lid_source_score = ggml_concat(ctx0, lid_base_score, lid_state_score, 1); ggml_tensor * kv_comp_lid_state = build_overlap_compressed_kv_from_state( lid_source_kv, @@ -982,8 +1114,19 @@ ggml_tensor * llama_model_deepseek4::graph::build_attention( ggml_build_forward_expand(gf, inp_dsv4->mctx->get_lid()->cpy_k(ctx0, kv_comp_lid_state, inp_dsv4->get_lid().state_write_idxs, il)); - lid_state_kv = dsv4_with_zero_dep(ctx0, lid_state_kv, kv_comp_lid_state); - lid_state_score = dsv4_with_zero_dep(ctx0, lid_state_score, kv_comp_lid_state); + ggml_tensor * lid_snapshot_source_kv = ggml_concat(ctx0, + lid_restored.kv, lid_state_kv, 1); + ggml_tensor * lid_snapshot_source_score = ggml_concat(ctx0, + lid_restored.score, lid_state_score, 1); + + const dsv4_state_tensors lid_snapshot = dsv4_build_state_snapshot( + ctx0, inp_dsv4->get_lid(), lid_state, lid_snapshot_source_kv, lid_snapshot_source_score, il); + if (lid_snapshot.kv != nullptr) { + ggml_build_forward_expand(gf, lid_snapshot.kv); + } + if (lid_snapshot.score != nullptr) { + ggml_build_forward_expand(gf, lid_snapshot.score); + } ggml_tensor * lid_persist_kv = ggml_get_rows(ctx0, lid_state_kv, inp_dsv4->get_lid().state_persist_src_idxs); ggml_tensor * lid_persist_score = ggml_get_rows(ctx0, lid_state_score, inp_dsv4->get_lid().state_persist_src_idxs); @@ -997,15 +1140,21 @@ ggml_tensor * llama_model_deepseek4::graph::build_attention( ggml_build_forward_expand(gf, lid_state_score); } - ggml_tensor * hca_state_dep = nullptr; + const llama_dsv4_comp_state * hca_state = nullptr; + dsv4_state_tensors hca_restored = {}; if (ratio == DSV4_HCA_RATIO && inp_dsv4->get_hca().state_write_idxs) { GGML_ASSERT(hca_state_kv); GGML_ASSERT(hca_state_score); - ggml_tensor * hca_source_kv = ggml_concat(ctx0, - inp_dsv4->mctx->get_hca_state()->get_kv(ctx0, il), hca_state_kv, 1); - ggml_tensor * hca_source_score = ggml_concat(ctx0, - inp_dsv4->mctx->get_hca_state()->get_score(ctx0, il), hca_state_score, 1); + hca_state = inp_dsv4->mctx->get_hca_state(); + hca_restored = dsv4_build_state_restore(ctx0, inp_dsv4->get_hca(), hca_state, il); + ggml_tensor * hca_base_kv = dsv4_view_2d( + ctx0, hca_restored.kv, hca_restored.kv->ne[0], hca_state->get_n_rows(), 0); + ggml_tensor * hca_base_score = dsv4_view_2d( + ctx0, hca_restored.score, hca_restored.score->ne[0], hca_state->get_n_rows(), 0); + + hca_source_kv = ggml_concat(ctx0, hca_base_kv, hca_state_kv, 1); + hca_source_score = ggml_concat(ctx0, hca_base_score, hca_state_score, 1); ggml_tensor * kv_comp_hca = build_hca_compressed_kv_from_state( hca_source_kv, @@ -1024,15 +1173,41 @@ ggml_tensor * llama_model_deepseek4::graph::build_attention( ggml_build_forward_expand(gf, inp_dsv4->mctx->get_hca()->cpy_k(ctx0, kv_comp_hca, inp_dsv4->get_hca().state_write_idxs, il)); - hca_state_dep = kv_comp_hca; } if (ratio == DSV4_HCA_RATIO && inp_dsv4->get_hca().state_pos) { GGML_ASSERT(hca_state_kv); GGML_ASSERT(hca_state_score); - hca_state_kv = dsv4_with_zero_dep(ctx0, hca_state_kv, hca_state_dep); - hca_state_score = dsv4_with_zero_dep(ctx0, hca_state_score, hca_state_dep); + if (hca_state == nullptr) { + hca_state = inp_dsv4->mctx->get_hca_state(); + } + if (hca_restored.kv == nullptr) { + hca_restored = dsv4_build_state_restore(ctx0, inp_dsv4->get_hca(), hca_state, il); + } + if (hca_source_kv == nullptr || hca_source_score == nullptr) { + ggml_tensor * hca_base_kv = dsv4_view_2d( + ctx0, hca_restored.kv, hca_restored.kv->ne[0], hca_state->get_n_rows(), 0); + ggml_tensor * hca_base_score = dsv4_view_2d( + ctx0, hca_restored.score, hca_restored.score->ne[0], hca_state->get_n_rows(), 0); + + hca_source_kv = ggml_concat(ctx0, hca_base_kv, hca_state_kv, 1); + hca_source_score = ggml_concat(ctx0, hca_base_score, hca_state_score, 1); + } + + ggml_tensor * hca_snapshot_source_kv = ggml_concat(ctx0, + hca_restored.kv, hca_state_kv, 1); + ggml_tensor * hca_snapshot_source_score = ggml_concat(ctx0, + hca_restored.score, hca_state_score, 1); + + const dsv4_state_tensors hca_snapshot = dsv4_build_state_snapshot( + ctx0, inp_dsv4->get_hca(), hca_state, hca_snapshot_source_kv, hca_snapshot_source_score, il); + if (hca_snapshot.kv != nullptr) { + ggml_build_forward_expand(gf, hca_snapshot.kv); + } + if (hca_snapshot.score != nullptr) { + ggml_build_forward_expand(gf, hca_snapshot.score); + } ggml_tensor * hca_persist_kv = ggml_get_rows(ctx0, hca_state_kv, inp_dsv4->get_hca().state_persist_src_idxs); ggml_tensor * hca_persist_score = ggml_get_rows(ctx0, hca_state_score, inp_dsv4->get_hca().state_persist_src_idxs); @@ -1047,7 +1222,14 @@ ggml_tensor * llama_model_deepseek4::graph::build_attention( } ggml_tensor * out = nullptr; - if (ratio == DSV4_CSA_RATIO && + if (inp_mtp) { + out = build_attn(inp_mtp, + nullptr, nullptr, nullptr, + q, kv, nullptr, + nullptr, layer.attn_sinks, nullptr, + 1.0f/sqrtf(float(n_embd_head)), il); + cb(out, "attn_raw", il); + } else if (ratio == DSV4_CSA_RATIO && inp_dsv4->get_csa().kq_mask && inp_dsv4->get_lid().kq_mask && inp_dsv4->get_lid().k_rot) { @@ -1078,7 +1260,7 @@ ggml_tensor * llama_model_deepseek4::graph::build_attention( out = ggml_reshape_3d(ctx0, out, o_group_dim, n_groups, nt); out = ggml_permute(ctx0, out, 0, 2, 1, 3); - ggml_tensor * oa = ggml_mul_mat(ctx0, ggml_reshape_3d(ctx0, layer.wo_a, layer.wo_a->ne[0], o_lora_rank, n_groups), out); + ggml_tensor * oa = ggml_mul_mat(ctx0, layer.wo_a, out); cb(oa, "attn_wo_a", il); oa = ggml_permute(ctx0, oa, 0, 2, 1, 3); oa = ggml_cont_2d(ctx0, oa, o_lora_rank*n_groups, nt); @@ -1106,6 +1288,12 @@ llama_model_deepseek4::graph::graph(const llama_model & model, const llm_graph_p cb(inpL, "hc_init", -1); for (int il = 0; il < n_layer; ++il) { + if ((size_t) il < cparams.embeddings_layer_inp.size() && cparams.embeddings_layer_inp[il]) { + res->t_layer_inp[il] = dsv4_hc_mean(ctx0, inpL); + cb(res->t_layer_inp[il], "layer_inp", il); + ggml_build_forward_expand(gf, res->t_layer_inp[il]); + } + ggml_tensor * residual = inpL; ggml_tensor * post = nullptr; ggml_tensor * comb = nullptr; @@ -1182,10 +1370,23 @@ llama_model_deepseek4::graph::graph(const llama_model & model, const llm_graph_p cb(inpL, "l_last", il); } + if ((size_t) n_layer < cparams.embeddings_layer_inp.size() && cparams.embeddings_layer_inp[n_layer]) { + res->t_layer_inp[n_layer] = dsv4_hc_mean(ctx0, inpL); + cb(res->t_layer_inp[n_layer], "layer_inp", n_layer); + ggml_build_forward_expand(gf, res->t_layer_inp[n_layer]); + } + + ggml_tensor * flat = ggml_reshape_2d(ctx0, inpL, n_embd*hc, n_tokens); + ggml_tensor * flat_out = inp_out_ids ? ggml_get_rows(ctx0, flat, inp_out_ids) : flat; + + if (cparams.embeddings_nextn) { + ggml_tensor * h_nextn = cparams.embeddings_nextn_masked ? flat_out : inpL; + cb(h_nextn, "h_nextn", -1); + res->t_h_nextn = h_nextn; + } + if (inp_out_ids) { - ggml_tensor * flat = ggml_reshape_2d(ctx0, inpL, n_embd*hc, n_tokens); - flat = ggml_get_rows(ctx0, flat, inp_out_ids); - inpL = ggml_reshape_3d(ctx0, flat, n_embd, hc, n_outputs); + inpL = ggml_reshape_3d(ctx0, flat_out, n_embd, hc, n_outputs); } cur = build_hc_head(inpL, model.hc_head_fn, model.hc_head_scale, model.hc_head_base); @@ -1201,3 +1402,145 @@ llama_model_deepseek4::graph::graph(const llama_model & model, const llm_graph_p ggml_build_forward_expand(gf, cur); } + + +llama_model_deepseek4::graph_mtp::graph_mtp(const llama_model & model, const llm_graph_params & params) : + graph(params) { + GGML_ASSERT(hparams.n_layer_nextn > 0 && "DEEPSEEK4 MTP requires n_layer_nextn > 0"); + GGML_ASSERT(hparams.n_layer_nextn == 1 && "DEEPSEEK4 MTP currently only supports a single MTP block"); + GGML_ASSERT(cparams.nextn_layer_offset >= 0 && + cparams.nextn_layer_offset < (int) hparams.n_layer_nextn && + "nextn_layer_offset out of range [0, n_layer_nextn)"); + GGML_ASSERT(ubatch.token && "DEEPSEEK4 MTP requires token input"); + + const int64_t hc = hparams.dsv4_hc_mult; + GGML_ASSERT(hparams.n_embd_out() == (uint32_t) (n_embd*hc) && "DEEPSEEK4 MTP hidden width mismatch"); + + const int il = hparams.n_layer() + cparams.nextn_layer_offset; + const auto & layer = model.layers[il]; + + GGML_ASSERT(layer.nextn.eh_proj && "MTP block missing nextn.eh_proj"); + GGML_ASSERT(layer.nextn.enorm && "MTP block missing nextn.enorm"); + GGML_ASSERT(layer.nextn.hnorm && "MTP block missing nextn.hnorm"); + + auto inp = std::make_unique(hparams.n_embd_out()); + + inp->tokens = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_tokens); + ggml_set_input(inp->tokens); + + inp->embd = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, hparams.n_embd_out(), n_tokens); + ggml_set_input(inp->embd); + + inp->h = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, hparams.n_embd_out(), n_tokens); + ggml_set_input(inp->h); + ggml_set_name(inp->h, "mtp_h_input"); + + ggml_tensor * tok_embd_w = layer.nextn.embed_tokens ? layer.nextn.embed_tokens : model.tok_embd; + ggml_tensor * tok_embd = ggml_get_rows(ctx0, tok_embd_w, inp->tokens); + cb(tok_embd, "mtp_tok_embd", il); + + ggml_tensor * h_state = ggml_reshape_3d(ctx0, inp->h, n_embd, hc, n_tokens); + cb(h_state, "mtp_h_state", il); + + res->add_input(std::move(inp)); + + ggml_tensor * inp_pos = build_inp_pos(); + ggml_tensor * inp_out_ids = build_inp_out_ids(); + llm_graph_input_attn_k_iswa * inp_attn = build_attn_inp_k_iswa(); + + ggml_tensor * h_norm = build_norm(h_state, layer.nextn.hnorm, nullptr, LLM_NORM_RMS, il); + cb(h_norm, "mtp_hnorm", il); + + ggml_tensor * e_norm = build_norm(tok_embd, layer.nextn.enorm, nullptr, LLM_NORM_RMS, il); + e_norm = ggml_reshape_3d(ctx0, e_norm, n_embd, 1, n_tokens); + e_norm = ggml_repeat_4d(ctx0, e_norm, n_embd, hc, n_tokens, 1); + cb(e_norm, "mtp_enorm", il); + + ggml_tensor * concat = ggml_concat(ctx0, e_norm, h_norm, 0); + cb(concat, "mtp_concat", il); + + ggml_tensor * inpL = build_lora_mm(layer.nextn.eh_proj, concat, layer.nextn.eh_proj_s); + cb(inpL, "mtp_eh_proj", il); + + ggml_tensor * residual = inpL; + ggml_tensor * post = nullptr; + ggml_tensor * comb = nullptr; + + ggml_tensor * cur = build_hc_pre(inpL, + layer.hc_attn_fn, + layer.hc_attn_scale, + layer.hc_attn_base, + &post, &comb, il); + cb(cur, "mtp_hc_attn_pre", il); + + cur = build_norm(cur, layer.attn_norm, nullptr, LLM_NORM_RMS, il); + cb(cur, "mtp_attn_norm", il); + + cur = build_attention(model, inp_attn, cur, inp_pos, il); + + inpL = build_hc_post(cur, residual, post, comb, il); + cb(inpL, "mtp_hc_attn_post", il); + + residual = inpL; + cur = build_hc_pre(inpL, + layer.hc_ffn_fn, + layer.hc_ffn_scale, + layer.hc_ffn_base, + &post, &comb, il); + cb(cur, "mtp_hc_ffn_pre", il); + + cur = build_norm(cur, layer.ffn_norm, nullptr, LLM_NORM_RMS, il); + cb(cur, "mtp_ffn_norm", il); + + GGML_ASSERT((uint32_t) il >= hparams.dsv4_hash_layer_count && "DEEPSEEK4 MTP does not support hash-routed MTP blocks"); + ggml_tensor * moe_out = build_moe_ffn(cur, + layer.ffn_gate_inp, + layer.ffn_up_exps, + layer.ffn_gate_exps, + layer.ffn_down_exps, + layer.ffn_exp_probs_b, + n_expert, hparams.n_expert_used, + LLM_FFN_SILU, hparams.expert_weights_norm, + hparams.expert_weights_scale, + (llama_expert_gating_func_type) hparams.expert_gating_func, + il); + cb(moe_out, "mtp_ffn_moe_out", il); + + ggml_tensor * ffn_shexp = build_ffn(cur, + layer.ffn_up_shexp, nullptr, nullptr, + layer.ffn_gate_shexp, nullptr, nullptr, + layer.ffn_down_shexp, nullptr, nullptr, + nullptr, LLM_FFN_SILU, LLM_FFN_PAR, il); + cb(ffn_shexp, "mtp_ffn_shexp", il); + + cur = ggml_add(ctx0, moe_out, ffn_shexp); + cb(cur, "mtp_ffn_out", il); + + inpL = build_hc_post(cur, residual, post, comb, il); + inpL = build_cvec(inpL, il); + cb(inpL, "mtp_l_out", il); + + ggml_tensor * flat = ggml_reshape_2d(ctx0, inpL, n_embd*hc, n_tokens); + ggml_tensor * h_nextn = ggml_get_rows(ctx0, flat, inp_out_ids); + cb(h_nextn, "h_nextn", -1); + res->t_h_nextn = h_nextn; + + inpL = ggml_reshape_3d(ctx0, h_nextn, n_embd, hc, n_outputs); + + cur = build_hc_head(inpL, model.hc_head_fn, model.hc_head_scale, model.hc_head_base); + cb(cur, "mtp_hc_head", -1); + + ggml_tensor * head_norm_w = layer.nextn.shared_head_norm ? layer.nextn.shared_head_norm : model.output_norm; + GGML_ASSERT(head_norm_w && "DEEPSEEK4 MTP missing shared head norm"); + cur = build_norm(cur, head_norm_w, nullptr, LLM_NORM_RMS, -1); + cb(cur, "mtp_shared_head_norm", -1); + res->t_embd = cur; + + ggml_tensor * head_w = layer.nextn.shared_head_head ? layer.nextn.shared_head_head : model.output; + GGML_ASSERT(head_w && "DEEPSEEK4 MTP missing LM head"); + cur = ggml_mul_mat(ctx0, head_w, cur); + cb(cur, "result_output", -1); + + res->t_logits = cur; + ggml_build_forward_expand(gf, cur); +} diff --git a/src/models/dflash.cpp b/src/models/dflash.cpp index dcff3aec9fa2..daff6e78f1cf 100644 --- a/src/models/dflash.cpp +++ b/src/models/dflash.cpp @@ -20,6 +20,48 @@ void llama_model_dflash::load_arch_hparams(llama_model_loader & ml) { } LLAMA_LOG_INFO("]\n"); + // DeepSeek-V4 DSpark backbone: stages are full DSV4 blocks, uniform sliding window (the draft KV ring) + ml.get_key(LLM_KV_HYPER_CONNECTION_COUNT, hparams.dsv4_hc_mult, false); + if (hparams.dsv4_hc_mult > 0) { + ml.get_key(LLM_KV_ATTENTION_Q_LORA_RANK, hparams.n_lora_q); + ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa); + ml.get_key(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp); + ml.get_key(LLM_KV_EXPERT_SHARED_COUNT, hparams.n_expert_shared); + ml.get_key(LLM_KV_EXPERT_WEIGHTS_SCALE, hparams.expert_weights_scale); + ml.get_key(LLM_KV_EXPERT_WEIGHTS_NORM, hparams.expert_weights_norm); + ml.get_key(LLM_KV_EXPERT_GATING_FUNC, hparams.expert_gating_func); + ml.get_key_or_arr(LLM_KV_SWIGLU_CLAMP_EXP, hparams.swiglu_clamp_exp, hparams.n_layer_all); + if (!ml.get_key_or_arr(LLM_KV_SWIGLU_CLAMP_SHEXP, hparams.swiglu_clamp_shexp, hparams.n_layer_all, 0)) { + hparams.swiglu_clamp_shexp = hparams.swiglu_clamp_exp; + } + ml.get_key(LLM_KV_ATTENTION_OUTPUT_GROUP_COUNT, hparams.dsv4_o_group_count); + ml.get_key(LLM_KV_ATTENTION_OUTPUT_LORA_RANK, hparams.dsv4_o_lora_rank); + ml.get_key(LLM_KV_HYPER_CONNECTION_SINKHORN_ITERATIONS, hparams.dsv4_hc_sinkhorn_iters); + ml.get_key(LLM_KV_HYPER_CONNECTION_EPSILON, hparams.dsv4_hc_eps); + ml.get_arr(LLM_KV_ATTENTION_COMPRESS_RATIOS, hparams.dsv4_compress_ratios, false); + + if (hparams.expert_gating_func != LLAMA_EXPERT_GATING_FUNC_TYPE_SQRT_SOFTPLUS) { + throw std::runtime_error("DSpark DSV4 draft expects sqrtsoftplus MoE scoring"); + } + for (uint32_t il = 0; il < hparams.n_layer_all; ++il) { + if (hparams.dsv4_compress_ratios[il] != 0) { + throw std::runtime_error("DSpark DSV4 draft expects uncompressed attention on all stages"); + } + } + + GGML_ASSERT(hparams.n_swa > 0); + hparams.swa_type = LLAMA_SWA_TYPE_STANDARD; + hparams.set_swa_pattern(0); + for (uint32_t il = 0; il < hparams.n_layer_all; ++il) { + hparams.is_swa_impl[il] = true; + } + hparams.rope_freq_base_train_swa = hparams.rope_freq_base_train; + hparams.rope_freq_scale_train_swa = hparams.rope_freq_scale_train; + + type = LLM_TYPE_UNKNOWN; + return; + } + // optional interleaved sliding-window attention with per-layer pattern array. // DFlash has a single rope, so the SWA rope == main rope. if (ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa, false) && hparams.n_swa > 0) { @@ -58,6 +100,56 @@ void llama_model_dflash::load_arch_tensors(llama_model_loader &) { output_norm_enc = create_tensor(tn(LLM_TENSOR_ENC_OUTPUT_NORM, "weight"), { n_embd }, 0); // encoder hidden_norm (after fc) output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), { n_embd }, 0); // decoder final norm + if (hparams.dsv4_hc_mult > 0) { + const int64_t q_lora_rank = hparams.n_lora_q; + const int64_t n_ff_exp = hparams.n_ff_exp; + const int64_t n_expert_shared = hparams.n_expert_shared; + const int64_t n_embd_head = hparams.n_embd_head_k(); + const int64_t o_groups = hparams.dsv4_o_group_count; + const int64_t o_lora_rank = hparams.dsv4_o_lora_rank; + const int64_t hc_mult = hparams.dsv4_hc_mult; + const int64_t hc_dim = hc_mult * n_embd; + const int64_t hc_mix_dim = (2 + hc_mult) * hc_mult; + + hc_head_fn = create_tensor(tn(LLM_TENSOR_HC_HEAD_FN, "weight"), {hc_dim, hc_mult}, 0); + hc_head_base = create_tensor(tn(LLM_TENSOR_HC_HEAD_BASE, "weight"), {hc_mult}, 0); + hc_head_scale = create_tensor(tn(LLM_TENSOR_HC_HEAD_SCALE, "weight"), {1}, 0); + + for (int i = 0; i < n_layer; ++i) { + auto & layer = layers[i]; + + layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, 0); + layer.attn_sinks = create_tensor(tn(LLM_TENSOR_ATTN_SINKS, "weight", i), {n_head}, 0); + layer.wq_a = create_tensor(tn(LLM_TENSOR_ATTN_Q_A, "weight", i), {n_embd, q_lora_rank}, 0); + layer.attn_q_a_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_A_NORM, "weight", i), {q_lora_rank}, 0); + layer.wq_b = create_tensor(tn(LLM_TENSOR_ATTN_Q_B, "weight", i), {q_lora_rank, n_head * n_embd_head}, 0); + layer.wkv = create_tensor(tn(LLM_TENSOR_ATTN_KV, "weight", i), {n_embd, n_embd_head}, 0); + layer.attn_kv_norm = create_tensor(tn(LLM_TENSOR_ATTN_KV_NORM, "weight", i), {n_embd_head}, 0); + layer.wo_a = create_tensor(tn(LLM_TENSOR_ATTN_OUT_A, "weight", i), {n_head * n_embd_head / o_groups, o_lora_rank, o_groups}, TENSOR_ALLOW_RESHAPE); + layer.wo_b = create_tensor(tn(LLM_TENSOR_ATTN_OUT_B, "weight", i), {o_groups * o_lora_rank, n_embd}, 0); + + layer.hc_attn_fn = create_tensor(tn(LLM_TENSOR_HC_ATTN_FN, "weight", i), {hc_dim, hc_mix_dim}, 0); + layer.hc_attn_base = create_tensor(tn(LLM_TENSOR_HC_ATTN_BASE, "weight", i), {hc_mix_dim}, 0); + layer.hc_attn_scale = create_tensor(tn(LLM_TENSOR_HC_ATTN_SCALE, "weight", i), {3}, 0); + layer.hc_ffn_fn = create_tensor(tn(LLM_TENSOR_HC_FFN_FN, "weight", i), {hc_dim, hc_mix_dim}, 0); + layer.hc_ffn_base = create_tensor(tn(LLM_TENSOR_HC_FFN_BASE, "weight", i), {hc_mix_dim}, 0); + layer.hc_ffn_scale = create_tensor(tn(LLM_TENSOR_HC_FFN_SCALE, "weight", i), {3}, 0); + + layer.ffn_gate_inp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), {n_embd, n_expert}, 0); + layer.ffn_exp_probs_b = create_tensor(tn(LLM_TENSOR_FFN_EXP_PROBS_B, "bias", i), {n_expert}, 0); + layer.ffn_norm = create_tensor(tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, 0); + + layer.ffn_gate_exps = create_tensor(tn(LLM_TENSOR_FFN_GATE_EXPS, "weight", i), {n_embd, n_ff_exp, n_expert}, 0); + layer.ffn_down_exps = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), {n_ff_exp, n_embd, n_expert}, 0); + layer.ffn_up_exps = create_tensor(tn(LLM_TENSOR_FFN_UP_EXPS, "weight", i), {n_embd, n_ff_exp, n_expert}, 0); + + layer.ffn_gate_shexp = create_tensor(tn(LLM_TENSOR_FFN_GATE_SHEXP, "weight", i), {n_embd, n_ff_exp * n_expert_shared}, 0); + layer.ffn_down_shexp = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP, "weight", i), {n_ff_exp * n_expert_shared, n_embd }, 0); + layer.ffn_up_shexp = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP, "weight", i), {n_embd, n_ff_exp * n_expert_shared}, 0); + } + return; + } + for (int i = 0; i < n_layer; ++i) { auto & layer = layers[i]; @@ -84,6 +176,9 @@ std::unique_ptr llama_model_dflash::build_arch_graph(const ll return std::make_unique>(*this, params); case LLM_GRAPH_TYPE_DEFAULT: case LLM_GRAPH_TYPE_DECODER: + if (hparams.dsv4_hc_mult > 0) { + return std::make_unique(*this, params); + } return std::make_unique>(*this, params); default: GGML_ABORT("invalid graph type"); @@ -403,3 +498,178 @@ llama_model_dflash::graph::graph(const llama_model & model, const llm_gra build_dspark_markov_head(*this, model, inp_tokens); } } + +// DSV4 DSpark decoder, dual-mode by batch type (see the DFlash decoder above): +// * embd batch -> project main_x through each stage's wkv and inject K into the ring cache +// * token batch -> noise block through 3 full DSV4 stages (hc + MLA + MoE), markov + confidence heads +llama_model_dflash::graph_dsv4::graph_dsv4(const llama_model & model, const llm_graph_params & params) : + llama_model_deepseek4::graph(params) { + const int64_t n_embd_head = hparams.n_embd_head_k(); + const int64_t n_embd_head_rope = hparams.n_rot(); + const int64_t n_embd_head_nope = n_embd_head - n_embd_head_rope; + + ggml_tensor * inp_pos = build_inp_pos(); + + llm_graph_input_attn_k_iswa * inp_attn = build_attn_inp_k_iswa(); + + // KV cache injection: fused target features from the encoder + if (ubatch.embd) { + auto inp = std::make_unique(n_embd); + + inp->embd = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_embd, n_tokens); + ggml_set_input(inp->embd); + + ggml_tensor * inp_g = inp->embd; + cb(inp_g, "inp_g_embeddings", -1); + + res->add_input(std::move(inp)); + + for (int il = 0; il < n_layer; ++il) { + const auto & layer = model.layers[il]; + + // main-track KV: kv_norm(wkv(main_x)) with rope on the trailing dims, same + // rope parameters as the uncompressed layers in build_attention_impl + ggml_tensor * kv = build_lora_mm(layer.wkv, inp_g); + kv = build_norm(kv, layer.attn_kv_norm, nullptr, LLM_NORM_RMS, il); + kv = ggml_reshape_3d(ctx0, kv, n_embd_head, 1, n_tokens); + + ggml_tensor * kv_nope = ggml_view_3d(ctx0, kv, n_embd_head_nope, 1, n_tokens, + ggml_row_size(kv->type, n_embd_head), + ggml_row_size(kv->type, n_embd_head), + 0); + ggml_tensor * kv_pe = ggml_view_3d(ctx0, kv, n_embd_head_rope, 1, n_tokens, + ggml_row_size(kv->type, n_embd_head), + ggml_row_size(kv->type, n_embd_head), + ggml_row_size(kv->type, n_embd_head_nope)); + kv_pe = ggml_rope_ext(ctx0, kv_pe, inp_pos, nullptr, n_embd_head_rope, rope_type, 0, + freq_base, 1.0f, 0.0f, 1.0f, 0.0f, 0.0f); + kv = ggml_concat(ctx0, kv_nope, kv_pe, 0); + cb(kv, "kv_injected", il); + + if (inp_attn->self_k_rot_swa) { + kv = llama_mul_mat_hadamard(ctx0, kv, inp_attn->self_k_rot_swa); + } + ggml_build_forward_expand(gf, inp_attn->mctx->get_swa()->cpy_k(ctx0, kv, inp_attn->get_k_idxs_swa(), il)); + } + + res->t_embd = inp_g; + + ggml_build_forward_expand(gf, inp_g); + return; + } + + // tok_embd from the target model (shared via ctx_other) + auto * tok_embd = model.tok_embd; + if (tok_embd == nullptr) { + GGML_ASSERT(cparams.ctx_other != nullptr); + const auto * model_other = llama_get_model(cparams.ctx_other); + + GGML_ASSERT(model_other->tok_embd != nullptr && "DSpark decoder requires the target model's token embeddings"); + tok_embd = model_other->tok_embd; + } + + auto inp = std::make_unique(n_embd); + + inp->tokens = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_tokens); + ggml_set_input(inp->tokens); + + ggml_tensor * inp_tokens = inp->tokens; + + ggml_tensor * inpL = ggml_get_rows(ctx0, tok_embd, inp->tokens); + cb(inpL, "inp_noise_embd", -1); + + res->add_input(std::move(inp)); + + const int64_t hc = hparams.dsv4_hc_mult; + inpL = ggml_reshape_3d(ctx0, inpL, n_embd, 1, n_tokens); + inpL = ggml_repeat_4d(ctx0, inpL, n_embd, hc, n_tokens, 1); + cb(inpL, "hc_init", -1); + + for (int il = 0; il < n_layer; ++il) { + const auto & layer = model.layers[il]; + + ggml_tensor * residual = inpL; + ggml_tensor * post = nullptr; + ggml_tensor * comb = nullptr; + + ggml_tensor * cur = build_hc_pre(inpL, + layer.hc_attn_fn, + layer.hc_attn_scale, + layer.hc_attn_base, + &post, &comb, il); + cb(cur, "hc_attn_pre", il); + + cur = build_norm(cur, layer.attn_norm, nullptr, LLM_NORM_RMS, il); + cb(cur, "attn_norm", il); + + cur = build_attention(model, inp_attn, cur, inp_pos, il); + + inpL = build_hc_post(cur, residual, post, comb, il); + cb(inpL, "hc_attn_post", il); + + residual = inpL; + cur = build_hc_pre(inpL, + layer.hc_ffn_fn, + layer.hc_ffn_scale, + layer.hc_ffn_base, + &post, &comb, il); + cb(cur, "hc_ffn_pre", il); + + cur = build_norm(cur, layer.ffn_norm, nullptr, LLM_NORM_RMS, il); + cb(cur, "ffn_norm", il); + + ggml_tensor * moe_out = build_moe_ffn(cur, + layer.ffn_gate_inp, + layer.ffn_up_exps, + layer.ffn_gate_exps, + layer.ffn_down_exps, + layer.ffn_exp_probs_b, + n_expert, hparams.n_expert_used, + LLM_FFN_SILU, hparams.expert_weights_norm, + hparams.expert_weights_scale, + (llama_expert_gating_func_type) hparams.expert_gating_func, + il); + cb(moe_out, "ffn_moe_out", il); + + ggml_tensor * ffn_shexp = build_ffn(cur, + layer.ffn_up_shexp, nullptr, nullptr, + layer.ffn_gate_shexp, nullptr, nullptr, + layer.ffn_down_shexp, nullptr, nullptr, + nullptr, LLM_FFN_SILU, LLM_FFN_PAR, il); + cb(ffn_shexp, "ffn_shexp", il); + + cur = ggml_add(ctx0, moe_out, ffn_shexp); + cb(cur, "ffn_out", il); + + inpL = build_hc_post(cur, residual, post, comb, il); + cb(inpL, "l_out", il); + } + + ggml_tensor * cur = build_hc_head(inpL, model.hc_head_fn, model.hc_head_scale, model.hc_head_base); + cb(cur, "hc_head", -1); + + // confidence head input: the reference scores the pre-norm collapsed hidden state + res->t_embd = cur; + + cur = build_norm(cur, model.output_norm, nullptr, LLM_NORM_RMS, -1); + cb(cur, "result_norm", -1); + + // lm_head from the target model (shared via ctx_other) + auto * output = model.output; + if (output == nullptr) { + GGML_ASSERT(cparams.ctx_other != nullptr); + const auto * model_other = llama_get_model(cparams.ctx_other); + GGML_ASSERT(model_other->output != nullptr && "DSpark decoder requires the target model's output projection"); + output = model_other->output; + } + + cur = build_lora_mm(output, cur); + cb(cur, "result_output", -1); + res->t_logits = cur; + + ggml_build_forward_expand(gf, cur); + + if (model.dspark_markov_w1) { + build_dspark_markov_head(*this, model, inp_tokens); + } +} diff --git a/src/models/glm-dsa.cpp b/src/models/glm-dsa.cpp index bd1c4df21281..360c2ee773f0 100644 --- a/src/models/glm-dsa.cpp +++ b/src/models/glm-dsa.cpp @@ -91,7 +91,11 @@ void llama_model_glm_dsa::load_arch_tensors(llama_model_loader & ml) { const std::string mtp_probe = "blk." + std::to_string(n_layer) + ".nextn.eh_proj.weight"; const bool trunk_only = (hparams.n_layer_nextn > 0) && (ml.get_weight(mtp_probe.c_str()) == nullptr); const int trunk_flags = mtp_only ? TENSOR_NOT_REQUIRED : 0; - const int mtp_flags = trunk_only ? TENSOR_NOT_REQUIRED : 0; + int mtp_flags = trunk_only ? TENSOR_NOT_REQUIRED : 0; + + if (!ml.load_mtp) { + mtp_flags |= TENSOR_SKIP; + } const bool is_mla = hparams.is_mla(); if (!is_mla) { diff --git a/src/models/hy-v3.cpp b/src/models/hy-v3.cpp index 47a0beaf217f..61db93af85ce 100644 --- a/src/models/hy-v3.cpp +++ b/src/models/hy-v3.cpp @@ -33,7 +33,11 @@ void llama_model_hy_v3::load_arch_tensors(llama_model_loader & ml) { const std::string mtp_probe = "blk." + std::to_string(n_layer) + ".nextn.eh_proj.weight"; const bool trunk_only = (hparams.n_layer_nextn > 0) && (ml.get_weight(mtp_probe.c_str()) == nullptr); const int trunk_flags = mtp_only ? TENSOR_NOT_REQUIRED : 0; - const int mtp_flags = trunk_only ? TENSOR_NOT_REQUIRED : 0; + int mtp_flags = trunk_only ? TENSOR_NOT_REQUIRED : 0; + + if (!ml.load_mtp) { + mtp_flags |= TENSOR_SKIP; + } tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0); diff --git a/src/models/mimo2.cpp b/src/models/mimo2.cpp index 4080a934cb98..d50e186cce92 100644 --- a/src/models/mimo2.cpp +++ b/src/models/mimo2.cpp @@ -30,7 +30,11 @@ void llama_model_mimo2::load_arch_tensors(llama_model_loader & ml) { const std::string mtp_probe = "blk." + std::to_string(n_layer) + ".nextn.eh_proj.weight"; const bool trunk_only = (hparams.n_layer_nextn > 0) && (ml.get_weight(mtp_probe.c_str()) == nullptr); - const int mtp_flags = trunk_only ? TENSOR_NOT_REQUIRED : 0; + int mtp_flags = trunk_only ? TENSOR_NOT_REQUIRED : 0; + + if (!ml.load_mtp) { + mtp_flags |= TENSOR_SKIP; + } tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0); diff --git a/src/models/minimax-m3.cpp b/src/models/minimax-m3.cpp index 3e7bada64bc9..854d5aed0f82 100644 --- a/src/models/minimax-m3.cpp +++ b/src/models/minimax-m3.cpp @@ -1,5 +1,5 @@ #include "models.h" -#include "llama-kv-cache.h" +#include "llama-kv-cache-msa.h" #include #include #include @@ -7,7 +7,8 @@ // MiniMax-M3: MiniMax-M2 style GQA (per-head QK-norm, partial rotary) with // DeepSeek-V3 leading-dense + routed/shared experts (sigmoid gating, routed scaling), // swigluoai activation, and MiniMax Sparse Attention (MSA). MTP is not in released model weights. -// Notes: Blocks are anchored to absolute KV cache slots. +// MSA blocks are defined over token positions. The graph translates between position space (block +// selection) and cell space (K/V/indexer storage) via per-ubatch pos<->cell maps populated from llama_kv_cells void llama_model_minimax_m3::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); @@ -23,7 +24,6 @@ void llama_model_minimax_m3::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_ATTENTION_INDEXER_BLOCK_SIZE, hparams.indexer_block_size); ml.get_key(LLM_KV_ATTENTION_INDEXER_LOCAL_BLOCKS, hparams.indexer_local_blocks); msa_p = { (int) hparams.indexer_block_size, (int) hparams.indexer_top_k, (int) hparams.indexer_local_blocks }; - hparams.indexer_kv = true; switch (hparams.n_layer()) { case 60: type = LLM_TYPE_428B_A23B; break; @@ -86,43 +86,83 @@ std::unique_ptr llama_model_minimax_m3::build_arch_graph(cons return std::make_unique(*this, params); } -// per-query local-force bias for MSA selection -// local window always wins a slot -class llm_graph_input_msa_local : public llm_graph_input_i { +class llm_graph_input_msa : public llm_graph_input_i { public: - llm_graph_input_msa_local(int blk, int local, int64_t nblk) : blk(blk), local(local), nblk(nblk) {} + llm_graph_input_msa(const llama_kv_cache_msa_context * mctx, int blk, int local) : + mctx(mctx), blk(blk), local(local) {} void set_input(const llama_ubatch * ubatch) override { - if (!bias || !ubatch->pos) { - return; - } - const int64_t n_tokens = ubatch->n_tokens; - std::vector data((size_t) nblk * n_tokens, 0.0f); - for (int64_t i = 0; i < n_tokens; ++i) { - const int64_t L = ubatch->pos[i] / blk; - for (int l = 0; l < local && L - l >= 0; ++l) { - if (L - l < nblk) { - data[(size_t) i * nblk + (L - l)] = 1e30f; + if (pos_slot_i) { mctx->set_input_pos_slot(pos_slot_i, ubatch); } + if (pos_slot_f) { mctx->set_input_pos_slot(pos_slot_f, ubatch); } + if (cell_blk) { mctx->set_input_cell_pos(cell_blk, ubatch, blk); } + if (pos_mask) { mctx->set_input_pos_mask(pos_mask, ubatch); } + + // local-force bias over position blocks + if (bias && ubatch->pos) { + const int64_t n_tokens = ubatch->n_tokens; + const int64_t nblk = bias->ne[0]; + std::vector data((size_t) nblk * n_tokens, 0.0f); + for (int64_t i = 0; i < n_tokens; ++i) { + const int64_t L = ubatch->pos[i] / blk; + for (int l = 0; l < local && L - l >= 0; ++l) { + if (L - l < nblk) { + data[(size_t) i * nblk + (L - l)] = 1e30f; + } } } + ggml_backend_tensor_set(bias, data.data(), 0, data.size() * sizeof(float)); } - ggml_backend_tensor_set(bias, data.data(), 0, data.size() * sizeof(float)); } - // valid as long as the bias tensor dims still match the new ubatch/cache window + // valid as long as the tensor dims still match the new ubatch/cache window and the + // ubatch is in the same regime (decode graphs have pos_slot_f, batch graphs cell_blk) bool can_reuse(const llm_graph_params & params) override { - const auto * mctx = static_cast(params.mctx); + const auto * mctx_new = static_cast(params.mctx); + + this->mctx = mctx_new; + + const int64_t n_ps = GGML_PAD((int64_t) mctx_new->get_n_pos(), blk); + const int64_t ns = params.cparams.kv_unified ? 1 : params.ubatch.n_seqs_unq; + + const bool decode = params.ubatch.n_tokens == ns; // one token per stream bool res = true; - res &= bias->ne[1] == params.ubatch.n_tokens; - res &= bias->ne[0] * blk == (int64_t) mctx->get_n_kv(); + + res &= bias->ne[0] * blk == n_ps; + res &= bias->ne[1] == params.ubatch.n_tokens; + + res &= pos_mask->ne[0] == n_ps; + res &= pos_mask->ne[1] == params.ubatch.n_tokens; + + res &= pos_slot_i->ne[0] == n_ps; + res &= pos_slot_i->ne[1] == ns; + + res &= decode == (pos_slot_f != nullptr); + res &= decode == (cell_blk == nullptr); + + if (pos_slot_f) { + res &= pos_slot_f->ne[0] == n_ps; + res &= pos_slot_f->ne[1] == ns; + } + + if (cell_blk) { + res &= cell_blk->ne[0] == (int64_t) mctx_new->get_base()->get_n_kv(); + res &= cell_blk->ne[1] == ns; + } + return res; } - ggml_tensor * bias = nullptr; - int blk; - int local; - int64_t nblk; + ggml_tensor * bias = nullptr; // F32 [nblk, n_tokens] local-force bias (position blocks) + ggml_tensor * pos_mask = nullptr; // F32 [n_ps, n_tokens] 0/-inf visibility, by position + ggml_tensor * pos_slot_i = nullptr; // I32 [n_ps, ns] pos -> cell (get_rows index) + ggml_tensor * pos_slot_f = nullptr; // F32 [n_ps, ns] pos -> cell (gatherable values, decode) + ggml_tensor * cell_blk = nullptr; // I32 [n_kv, ns] cell -> position block (batch) + + const llama_kv_cache_msa_context * mctx; + + int blk; + int local; }; // One FA call for all GQA groups (and at multi-stream decode, all streams) by mapping them onto the FA sequence dim (ne[3]) @@ -173,7 +213,9 @@ llama_model_minimax_m3::graph::graph(const llama_model & model, const llm_graph_ inpL = build_inp_embd(model.tok_embd); ggml_tensor * inp_pos = build_inp_pos(); - auto inp_attn = build_attn_inp_kv(); + + // ========================================== + // TODO: avoid such kind of complexity in the model graphs // MSA calls ggml_flash_attn_ext directly and assumes the non-transposed V layout that // llama.cpp only provides when flash attention is enabled. Block selection is anchored @@ -185,6 +227,8 @@ llama_model_minimax_m3::graph::graph(const llama_model & model, const llm_graph_ const bool streams_ok = cparams.n_seq_max == 1 || !cparams.kv_unified; const bool msa_enabled = fa_on && streams_ok; + auto * inp_attn = build_attn_inp_kv_msa(msa_enabled); + static bool warned_no_fa = false; if (!fa_on && !warned_no_fa) { LLAMA_LOG_WARN("%s: flash attention disabled; MSA requires it -> running DENSE attention " @@ -197,36 +241,54 @@ llama_model_minimax_m3::graph::graph(const llama_model & model, const llm_graph_ "-> running DENSE attention. Output may be degraded. Drop --kv-unified to enable MSA.\n", __func__); warned_unified = true; } + // ========================================== // hoisted per-graph MSA state (shared by every sparse layer) - llm_graph_input_msa_local * msa_loc = nullptr; + llm_graph_input_msa * msa = nullptr; ggml_tensor * msa_kqm = nullptr; - ggml_tensor * msa_mf = nullptr; - int64_t n_kv = 0, nblk = 0, ns = 1, n_tps = 0; + ggml_tensor * msa_mf = nullptr; // F32 copy of the FA mask for the final mask add + int64_t n_kv = 0, n_ps = 0, nblk = 0, ns = 1, n_tps = 0; bool msa_decode = false; // gather (1 token per stream) vs mask const int blk = mm.msa_p.blk; const int64_t Hd = hparams.indexer_n_head; // one indexer head per GQA group if (msa_enabled) { + const auto * mctx_msa = static_cast(mctx); + msa_kqm = inp_attn->get_kq_mask(); n_kv = msa_kqm->ne[0]; n_tps = msa_kqm->ne[1]; // tokens per stream ns = msa_kqm->ne[3]; // streams in this ubatch GGML_ASSERT(msa_kqm->type == GGML_TYPE_F16 && "MSA requires the FA (f16) mask"); GGML_ASSERT(n_tps*ns == n_tokens); - GGML_ASSERT(n_kv % blk == 0 && - "MSA: KV/mask n_kv must be a multiple of indexer.block_size (128); " - "the flash-attention KV padding must be a multiple of the block size. " - "A non-multiple would silently drop the partial tail block."); - nblk = n_kv / blk; + + // the position axis covers every position currently in the cache and is padded to whole blocks + n_ps = GGML_PAD((int64_t) mctx_msa->get_n_pos(), blk); + nblk = n_ps / blk; msa_decode = n_tps == 1; - msa_mf = ggml_cast(ctx0, msa_kqm, GGML_TYPE_F32); + auto inp = std::make_unique(mctx_msa, blk, mm.msa_p.local); + + inp->bias = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, nblk, n_tokens); // stream-grouped tokens + ggml_set_input(inp->bias); + + inp->pos_mask = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_ps, n_tokens); + ggml_set_input(inp->pos_mask); + + inp->pos_slot_i = ggml_new_tensor_2d(ctx0, GGML_TYPE_I32, n_ps, ns); + ggml_set_input(inp->pos_slot_i); + + if (msa_decode) { + inp->pos_slot_f = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_ps, ns); + ggml_set_input(inp->pos_slot_f); + } else { + inp->cell_blk = ggml_new_tensor_2d(ctx0, GGML_TYPE_I32, n_kv, ns); + ggml_set_input(inp->cell_blk); + + msa_mf = ggml_cast(ctx0, msa_kqm, GGML_TYPE_F32); + } - auto loc = std::make_unique(blk, mm.msa_p.local, nblk); - loc->bias = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, nblk, n_tokens); // stream-grouped tokens - ggml_set_input(loc->bias); - msa_loc = (llm_graph_input_msa_local *) res->add_input(std::move(loc)); + msa = (llm_graph_input_msa *) res->add_input(std::move(inp)); } ggml_tensor * inp_out_ids = build_inp_out_ids(); @@ -271,8 +333,6 @@ llama_model_minimax_m3::graph::graph(const llama_model & model, const llm_graph_ } else { const int64_t n_idx_dim = hparams.indexer_head_size; // 128 - GGML_ASSERT(!inp_attn->self_k_rot && !inp_attn->self_v_rot && "MSA: attn-rot not supported"); - // Index Branch, project, norm, partial RoPE, cache ggml_tensor * iq = build_lora_mm(model.layers[il].index_q_proj, cur); ggml_tensor * ik = build_lora_mm(model.layers[il].index_k_proj, cur); @@ -285,9 +345,19 @@ llama_model_minimax_m3::graph::graph(const llama_model & model, const llm_graph_ ik = ggml_rope_ext(ctx0, ik, inp_pos, nullptr, n_rot, rope_type, n_ctx_orig, freq_base, freq_scale, ext_factor, attn_factor, beta_fast, beta_slow); - const auto * mctx_cur = inp_attn->mctx; - ggml_build_forward_expand(gf, mctx_cur->cpy_k_idx(ctx0, ik, inp_attn->get_k_idxs(), il)); - ggml_tensor * ik_kv = mctx_cur->get_k_idx(ctx0, il); + const auto * mctx_msa_l = static_cast(mctx); + const auto * mctx_cur = mctx_msa_l->get_base(); + const auto * mctx_idx = mctx_msa_l->get_idx(); + ggml_build_forward_expand(gf, mctx_idx->cpy_k(ctx0, ik, inp_attn->get_k_idxs_idx(), il)); + ggml_tensor * ik_kv = mctx_idx->get_k(ctx0, il); + + if (inp_attn->self_k_rot) { + Qcur = llama_mul_mat_hadamard(ctx0, Qcur, inp_attn->self_k_rot); + Kcur = llama_mul_mat_hadamard(ctx0, Kcur, inp_attn->self_k_rot); + } + if (inp_attn->self_v_rot) { + Vcur = llama_mul_mat_hadamard(ctx0, Vcur, inp_attn->self_v_rot); + } // Main branch: store K/V, take cache views ggml_build_forward_expand(gf, Qcur); @@ -310,42 +380,52 @@ llama_model_minimax_m3::graph::graph(const llama_model & model, const llm_graph_ if (msa_decode) { // decode: batched over streams top-k + gather, one grouped FA - // scores: per-stream batched matmul over the stream dim (ne[3]). - // the cache views are not contiguous across streams (stride = kv_size, not n_kv) - ggml_tensor * ikv4 = ggml_view_4d(ctx0, ik_kv, n_idx_dim, n_kv, 1, ns, - ik_kv->nb[2], ik_kv->nb[3], ik_kv->nb[3], 0); + // gather the indexer keys through the pos -> cell map + ggml_tensor * ik3 = ggml_view_3d(ctx0, ik_kv, n_idx_dim, n_kv, ns, + ik_kv->nb[2], ik_kv->nb[3], 0); + ggml_tensor * ikp = ggml_get_rows(ctx0, ik3, msa->pos_slot_i); // [n_idx_dim, n_ps, ns] ggml_tensor * iq4 = ggml_reshape_4d(ctx0, iq, n_idx_dim, Hd, 1, ns); - ggml_tensor * sc = ggml_mul_mat(ctx0, ikv4, iq4); + ggml_tensor * sc = ggml_mul_mat(ctx0, + ggml_reshape_4d(ctx0, ikp, n_idx_dim, n_ps, 1, ns), iq4); ggml_mul_mat_set_prec(sc, GGML_PREC_F32); - sc = ggml_add_inplace(ctx0, sc, msa_mf); + // unmapped positions come out -inf, so they can never rank into the top-k + sc = ggml_add_inplace(ctx0, sc, + ggml_reshape_4d(ctx0, msa->pos_mask, n_ps, 1, 1, ns)); ggml_tensor * bs = ggml_pool_2d(ctx0, sc, GGML_OP_POOL_MAX, blk, 1, blk, 1, 0, 0); cb(bs, "msa_bs", il); ggml_tensor * bsf = ggml_add(ctx0, bs, - ggml_reshape_4d(ctx0, msa_loc->bias, nblk, 1, 1, ns)); - ggml_tensor * idx = ggml_top_k(ctx0, bsf, K); + ggml_reshape_4d(ctx0, msa->bias, nblk, 1, 1, ns)); + ggml_tensor * idx = ggml_top_k(ctx0, bsf, K); // position blocks - // token idx: tj[t,k,h,s] = blk*idx[k,h,s] + t (for the mask gather) - // row idx: tr[t,k,h,s] = tj*HKV + h (for the per-stream K/V gather) + // pos idx: tj[t,k,h,s] = blk*idx[k,h,s] + t (positions - mask gather) + // cell idx: cs[t,k,h,s] = pos_slot[tj] (pos -> cell translation) + // row idx: tr[t,k,h,s] = cs*HKV + h (per-stream K/V gather) ggml_tensor * a = ggml_scale(ctx0, ggml_cast(ctx0, idx, GGML_TYPE_F32), (float) blk); a = ggml_reshape_4d(ctx0, a, 1, K, Hd, ns); ggml_tensor * tj = ggml_add(ctx0, ggml_repeat_4d(ctx0, a, blk, K, Hd, ns), ggml_reshape_3d(ctx0, ggml_arange(ctx0, 0.0f, (float) blk, 1.0f), blk, 1, 1)); + + ggml_tensor * tokj = ggml_cast(ctx0, ggml_reshape_2d(ctx0, tj, (int64_t) blk*K*Hd, ns), GGML_TYPE_I32); + + ggml_tensor * cs = ggml_get_rows(ctx0, + ggml_reshape_3d(ctx0, msa->pos_slot_f, 1, n_ps, ns), tokj); // [1, blk*K*Hd, ns] + cs = ggml_reshape_4d(ctx0, cs, blk, K, Hd, ns); + ggml_tensor * tr = ggml_add(ctx0, - ggml_scale(ctx0, tj, (float) HKV), + ggml_scale(ctx0, cs, (float) HKV), ggml_reshape_3d(ctx0, ggml_arange(ctx0, 0.0f, (float) HKV, 1.0f), 1, 1, Hd)); - ggml_tensor * tokj = ggml_cast(ctx0, ggml_reshape_2d(ctx0, tj, (int64_t) blk*K*Hd, ns), GGML_TYPE_I32); ggml_tensor * tokr = ggml_cast(ctx0, ggml_reshape_2d(ctx0, tr, (int64_t) blk*K*Hd, ns), GGML_TYPE_I32); ggml_tensor * k3 = ggml_view_3d(ctx0, k, D, HKV*n_kv, ns, k->nb[1], k->nb[3], 0); ggml_tensor * v3 = ggml_view_3d(ctx0, v, D, HKV*n_kv, ns, v->nb[1], v->nb[3], 0); - ggml_tensor * m3 = ggml_reshape_3d(ctx0, msa_kqm, 1, n_kv, ns); + ggml_tensor * mp = ggml_reshape_3d(ctx0, msa->pos_mask, 1, n_ps, ns); ggml_tensor * kg = ggml_get_rows(ctx0, k3, tokr); ggml_tensor * vg = ggml_get_rows(ctx0, v3, tokr); - ggml_tensor * mg = ggml_get_rows(ctx0, m3, tokj); + ggml_tensor * mg = ggml_get_rows(ctx0, mp, tokj); // fold (group, stream) onto the FA channel dim const ggml_type kt = ggml_is_quantized(k->type) ? GGML_TYPE_F16 : k->type; @@ -366,12 +446,16 @@ llama_model_minimax_m3::graph::graph(const llama_model & model, const llm_graph_ iq->nb[1], iq->nb[2], st*n_tps*iq->nb[2]); ggml_tensor * ik_s = ggml_view_2d(ctx0, ik_kv, n_idx_dim, n_kv, ik_kv->nb[2], st*ik_kv->nb[3]); - ggml_tensor * mf_s = ggml_view_3d(ctx0, msa_mf, n_kv, 1, n_tps, - msa_mf->nb[1], msa_mf->nb[1], st*msa_mf->nb[3]); - ggml_tensor * km_s = ggml_view_3d(ctx0, msa_kqm, n_kv, n_tps, 1, - msa_kqm->nb[1], msa_kqm->nb[3], st*msa_kqm->nb[3]); - ggml_tensor * bias_s = ggml_view_3d(ctx0, msa_loc->bias, nblk, 1, n_tps, - msa_loc->bias->nb[1], msa_loc->bias->nb[1], st*n_tps*msa_loc->bias->nb[1]); + ggml_tensor * psl_s = ggml_view_1d(ctx0, msa->pos_slot_i, n_ps, + st*msa->pos_slot_i->nb[1]); + ggml_tensor * pm_s = ggml_view_3d(ctx0, msa->pos_mask, n_ps, 1, n_tps, + msa->pos_mask->nb[1], msa->pos_mask->nb[1], st*n_tps*msa->pos_mask->nb[1]); + ggml_tensor * cb_s = ggml_view_1d(ctx0, msa->cell_blk, n_kv, + st*msa->cell_blk->nb[1]); + ggml_tensor * mf_s = ggml_view_3d(ctx0, msa_mf, n_kv, n_tps, 1, + msa_mf->nb[1], msa_mf->nb[3], st*msa_mf->nb[3]); + ggml_tensor * bias_s = ggml_view_3d(ctx0, msa->bias, nblk, 1, n_tps, + msa->bias->nb[1], msa->bias->nb[1], st*n_tps*msa->bias->nb[1]); ggml_tensor * q_s = ggml_view_3d(ctx0, Qcur, D, n_head, n_tps, Qcur->nb[1], Qcur->nb[2], st*n_tps*Qcur->nb[2]); ggml_tensor * k_s = ggml_view_4d(ctx0, k, D, HKV, n_kv, 1, @@ -379,14 +463,16 @@ llama_model_minimax_m3::graph::graph(const llama_model & model, const llm_graph_ ggml_tensor * v_s = ggml_view_4d(ctx0, v, D, HKV, n_kv, 1, v->nb[1], v->nb[2], v->nb[3], st*v->nb[3]); - // block scores: bs = maxpool_blk(idx_q * idx_k^T + causal mask) + // block scores: the indexer keys are gathered through the pos -> cell map first // scores are unscaled, only the top-k ordering matters - ggml_tensor * sc = ggml_mul_mat(ctx0, ik_s, + ggml_tensor * ikp = ggml_get_rows(ctx0, ik_s, psl_s); // [n_idx_dim, n_ps] + ggml_tensor * sc = ggml_mul_mat(ctx0, ikp, ggml_reshape_2d(ctx0, iq_s, n_idx_dim, Hd*n_tps)); // indexer scores run in F32 ggml_mul_mat_set_prec(sc, GGML_PREC_F32); - sc = ggml_reshape_3d(ctx0, sc, n_kv, Hd, n_tps); - sc = ggml_add_inplace(ctx0, sc, mf_s); + sc = ggml_reshape_3d(ctx0, sc, n_ps, Hd, n_tps); + // unmapped positions (holes, padding, empty cells) come out -inf + sc = ggml_add_inplace(ctx0, sc, pm_s); ggml_tensor * bs = ggml_pool_2d(ctx0, sc, GGML_OP_POOL_MAX, blk, 1, blk, 1, 0, 0); cb(bs, "msa_bs", il); @@ -410,14 +496,16 @@ llama_model_minimax_m3::graph::graph(const llama_model & model, const llm_graph_ bm = ggml_cont(ctx0, ggml_permute(ctx0, bm, 0, 2, 1, 3)); // [nblk, n_tps, Hd] cb(bm, "msa_block_mask", il); - // expand block -> token granularity (j = bk*blk + t), - // then combine with the causal mask in place - ggml_tensor * bmx = ggml_repeat_4d(ctx0, - ggml_reshape_3d(ctx0, bm, 1, nblk, n_tps*Hd), - blk, nblk, n_tps*Hd, 1); + // expand block -> cell granularity through the cell -> position block + // map, then combine with the causal mask. empty cells are masked by the causal mask. + ggml_tensor * bm2 = ggml_cont(ctx0, ggml_transpose(ctx0, + ggml_reshape_2d(ctx0, bm, nblk, n_tps*Hd))); // [n_tps*Hd, nblk] + ggml_tensor * bmc = ggml_get_rows(ctx0, bm2, cb_s); // [n_tps*Hd, n_kv] F32 + ggml_tensor * bmx = ggml_cont(ctx0, ggml_transpose(ctx0, bmc)); bmx = ggml_reshape_3d(ctx0, bmx, n_kv, n_tps, Hd); - ggml_tensor * mask4 = ggml_add_inplace(ctx0, bmx, km_s); - mask4 = ggml_reshape_4d(ctx0, mask4, n_kv, n_tps, 1, Hd); + ggml_tensor * mask4 = ggml_add_inplace(ctx0, bmx, mf_s); + mask4 = ggml_cast(ctx0, + ggml_reshape_4d(ctx0, mask4, n_kv, n_tps, 1, Hd), GGML_TYPE_F16); cb(mask4, "msa_mask4", il); // cache views with groups on ne[3]; @@ -431,7 +519,9 @@ llama_model_minimax_m3::graph::graph(const llama_model & model, const llm_graph_ cur = ggml_concat(ctx0, cur, outs[st], 1); } } - + if (inp_attn->self_v_rot) { + cur = llama_mul_mat_hadamard(ctx0, cur, inp_attn->self_v_rot); + } cb(cur, "kqv_out", il); if (model.layers[il].wo) { cur = build_lora_mm(model.layers[il].wo, cur, model.layers[il].wo_s); diff --git a/src/models/models.h b/src/models/models.h index bb372ece81ee..ad3dadaf3932 100644 --- a/src/models/models.h +++ b/src/models/models.h @@ -596,6 +596,11 @@ struct llama_model_qwen3vlmoe : public llama_model_base { }; +struct llama_model_qwen3tts : public llama_model_qwen3vl { + llama_model_qwen3tts(const struct llama_model_params & params) : llama_model_qwen3vl(params) {} +}; + + struct llama_model_phi2 : public llama_model_base { llama_model_phi2(const struct llama_model_params & params) : llama_model_base(params) {} void load_arch_hparams(llama_model_loader & ml) override; @@ -1084,6 +1089,10 @@ struct llama_model_deepseek2 : public llama_model_base { graph(const llama_model & model, const llm_graph_params & params); }; + struct graph_mtp : public llm_graph_context { + graph_mtp(const llama_model & model, const llm_graph_params & params); + }; + std::unique_ptr build_arch_graph(const llm_graph_params & params) const override; }; @@ -1097,6 +1106,10 @@ struct llama_model_deepseek32 : public llama_model_base { graph(const llama_model & model, const llm_graph_params & params); }; + struct graph_mtp : public llm_graph_context { + graph_mtp(const llama_model & model, const llm_graph_params & params); + }; + std::unique_ptr build_arch_graph(const llm_graph_params & params) const override; }; @@ -1107,6 +1120,7 @@ struct llama_model_deepseek4 : public llama_model_base { void load_arch_tensors(llama_model_loader & ml) override; struct graph : public llm_graph_context { + graph(const llm_graph_params & params) : llm_graph_context(params) {} graph(const llama_model & model, const llm_graph_params & params); ggml_tensor * build_hc_pre( @@ -1138,6 +1152,21 @@ struct llama_model_deepseek4 : public llama_model_base { ggml_tensor * inp_pos, int il) const; + ggml_tensor * build_attention( + const llama_model & model, + llm_graph_input_attn_k_iswa * inp_mtp, + ggml_tensor * cur, + ggml_tensor * inp_pos, + int il) const; + + ggml_tensor * build_attention_impl( + const llama_model & model, + llm_graph_input_dsv4 * inp_dsv4, + llm_graph_input_attn_k_iswa * inp_mtp, + ggml_tensor * cur, + ggml_tensor * inp_pos, + int il) const; + ggml_tensor * build_hca_compressed_kv_from_state( ggml_tensor * kv_state, ggml_tensor * score_state, @@ -1213,6 +1242,10 @@ struct llama_model_deepseek4 : public llama_model_base { int il) const; }; + struct graph_mtp : public graph { + graph_mtp(const llama_model & model, const llm_graph_params & params); + }; + std::unique_ptr build_arch_graph(const llm_graph_params & params) const override; }; @@ -1272,6 +1305,10 @@ struct llama_model_dflash : public llama_model_base { ggml_tensor * build_inp_embd_enc() const; }; + struct graph_dsv4 : public llama_model_deepseek4::graph { + graph_dsv4(const llama_model & model, const llm_graph_params & params); + }; + std::unique_ptr build_arch_graph(const llm_graph_params & params) const override; }; @@ -2009,6 +2046,10 @@ struct llama_model_qwen3next : public llama_model_base { const llama_model & model; }; + struct graph_mtp : public llm_graph_context { + graph_mtp(const llama_model & model, const llm_graph_params & params); + }; + std::unique_ptr build_arch_graph(const llm_graph_params & params) const override; }; diff --git a/src/models/qwen35.cpp b/src/models/qwen35.cpp index d8ffe43ae76c..309dd432447c 100644 --- a/src/models/qwen35.cpp +++ b/src/models/qwen35.cpp @@ -39,6 +39,7 @@ void llama_model_qwen35::load_arch_tensors(llama_model_loader & ml) { const bool mtp_only = (hparams.n_layer_nextn > 0) && (ml.get_weight("blk.0.attn_norm.weight") == nullptr); const int trunk_flags = mtp_only ? TENSOR_NOT_REQUIRED : 0; + int mtp_flags = !ml.load_mtp ? TENSOR_SKIP : 0; tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), { n_embd, n_vocab }, 0); @@ -97,25 +98,25 @@ void llama_model_qwen35::load_arch_tensors(llama_model_loader & ml) { auto & layer = layers[il]; // MTP block looks like a full-attention Qwen3.5 decoder block. - layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", il), { n_embd }, 0); - layer.attn_post_norm = create_tensor(tn(LLM_TENSOR_ATTN_POST_NORM, "weight", il), { n_embd }, 0); + layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", il), { n_embd }, mtp_flags); + layer.attn_post_norm = create_tensor(tn(LLM_TENSOR_ATTN_POST_NORM, "weight", il), { n_embd }, mtp_flags); - create_tensor_qkv(layer, il, n_embd, n_embd_head_k * n_head * 2, n_embd_k_gqa, n_embd_v_gqa, 0); - layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", il), { n_embd_head_k * n_head, n_embd }, 0); - layer.attn_q_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_NORM, "weight", il), { n_embd_head_k }, 0); - layer.attn_k_norm = create_tensor(tn(LLM_TENSOR_ATTN_K_NORM, "weight", il), { n_embd_head_k }, 0); + create_tensor_qkv(layer, il, n_embd, n_embd_head_k * n_head * 2, n_embd_k_gqa, n_embd_v_gqa, mtp_flags); + layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", il), { n_embd_head_k * n_head, n_embd }, mtp_flags); + layer.attn_q_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_NORM, "weight", il), { n_embd_head_k }, mtp_flags); + layer.attn_k_norm = create_tensor(tn(LLM_TENSOR_ATTN_K_NORM, "weight", il), { n_embd_head_k }, mtp_flags); - layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", il), {n_embd, n_ff}, 0); - layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", il), { n_ff, n_embd}, 0); - layer.ffn_up = create_tensor(tn(LLM_TENSOR_FFN_UP, "weight", il), {n_embd, n_ff}, 0); + layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", il), {n_embd, n_ff}, mtp_flags); + layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", il), { n_ff, n_embd}, mtp_flags); + layer.ffn_up = create_tensor(tn(LLM_TENSOR_FFN_UP, "weight", il), {n_embd, n_ff}, mtp_flags); // NextN-specific tensors that define the MTP block. - layer.nextn.eh_proj = create_tensor(tn(LLM_TENSOR_NEXTN_EH_PROJ, "weight", il), { 2 * n_embd, n_embd }, 0); - layer.nextn.enorm = create_tensor(tn(LLM_TENSOR_NEXTN_ENORM, "weight", il), { n_embd }, 0); - layer.nextn.hnorm = create_tensor(tn(LLM_TENSOR_NEXTN_HNORM, "weight", il), { n_embd }, 0); - layer.nextn.embed_tokens = create_tensor(tn(LLM_TENSOR_NEXTN_EMBED_TOKENS, "weight", il), { n_embd, n_vocab }, TENSOR_NOT_REQUIRED); - layer.nextn.shared_head_head = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_HEAD, "weight", il), { n_embd, n_vocab }, TENSOR_NOT_REQUIRED); - layer.nextn.shared_head_norm = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_NORM, "weight", il), { n_embd }, TENSOR_NOT_REQUIRED); + layer.nextn.eh_proj = create_tensor(tn(LLM_TENSOR_NEXTN_EH_PROJ, "weight", il), { 2 * n_embd, n_embd }, mtp_flags); + layer.nextn.enorm = create_tensor(tn(LLM_TENSOR_NEXTN_ENORM, "weight", il), { n_embd }, mtp_flags); + layer.nextn.hnorm = create_tensor(tn(LLM_TENSOR_NEXTN_HNORM, "weight", il), { n_embd }, mtp_flags); + layer.nextn.embed_tokens = create_tensor(tn(LLM_TENSOR_NEXTN_EMBED_TOKENS, "weight", il), { n_embd, n_vocab }, mtp_flags|TENSOR_NOT_REQUIRED); + layer.nextn.shared_head_head = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_HEAD, "weight", il), { n_embd, n_vocab }, mtp_flags|TENSOR_NOT_REQUIRED); + layer.nextn.shared_head_norm = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_NORM, "weight", il), { n_embd }, mtp_flags|TENSOR_NOT_REQUIRED); }; for (int i = 0; i < n_layer; ++i) { diff --git a/src/models/qwen35moe.cpp b/src/models/qwen35moe.cpp index 7b0876cbb04b..38f2a57985a9 100644 --- a/src/models/qwen35moe.cpp +++ b/src/models/qwen35moe.cpp @@ -42,6 +42,7 @@ void llama_model_qwen35moe::load_arch_tensors(llama_model_loader & ml) { const bool mtp_only = (hparams.n_layer_nextn > 0) && (ml.get_weight("blk.0.attn_norm.weight") == nullptr); const int trunk_flags = mtp_only ? TENSOR_NOT_REQUIRED : 0; + int mtp_flags = !ml.load_mtp ? TENSOR_SKIP : 0; tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), { n_embd, n_vocab }, 0); @@ -113,32 +114,32 @@ void llama_model_qwen35moe::load_arch_tensors(llama_model_loader & ml) { const int64_t n_ff_shexp = hparams.n_ff_shexp ? hparams.n_ff_shexp : n_ff; // MTP block looks like a full-attention Qwen3.5 decoder block with MoE FFN. - layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", il), { n_embd }, 0); - layer.attn_post_norm = create_tensor(tn(LLM_TENSOR_ATTN_POST_NORM, "weight", il), { n_embd }, 0); + layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", il), { n_embd }, mtp_flags); + layer.attn_post_norm = create_tensor(tn(LLM_TENSOR_ATTN_POST_NORM, "weight", il), { n_embd }, mtp_flags); - create_tensor_qkv(layer, il, n_embd, n_embd_head_k * n_head * 2, n_embd_k_gqa, n_embd_v_gqa, 0); - layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", il), { n_embd_head_k * n_head, n_embd }, 0); - layer.attn_q_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_NORM, "weight", il), { n_embd_head_k }, 0); - layer.attn_k_norm = create_tensor(tn(LLM_TENSOR_ATTN_K_NORM, "weight", il), { n_embd_head_k }, 0); + create_tensor_qkv(layer, il, n_embd, n_embd_head_k * n_head * 2, n_embd_k_gqa, n_embd_v_gqa, mtp_flags); + layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", il), { n_embd_head_k * n_head, n_embd }, mtp_flags); + layer.attn_q_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_NORM, "weight", il), { n_embd_head_k }, mtp_flags); + layer.attn_k_norm = create_tensor(tn(LLM_TENSOR_ATTN_K_NORM, "weight", il), { n_embd_head_k }, mtp_flags); // Routed experts - layer.ffn_gate_inp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP, "weight", il), { n_embd, n_expert }, 0); - layer.ffn_down_exps = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", il), { n_ff_exp, n_embd, n_expert }, 0); - create_tensor_gate_up_exps(layer, il, n_embd, n_ff_exp, n_expert, 0); + layer.ffn_gate_inp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP, "weight", il), { n_embd, n_expert }, mtp_flags); + layer.ffn_down_exps = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", il), { n_ff_exp, n_embd, n_expert }, mtp_flags); + create_tensor_gate_up_exps(layer, il, n_embd, n_ff_exp, n_expert, mtp_flags); // Shared experts - layer.ffn_gate_inp_shexp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP_SHEXP, "weight", il), { n_embd }, 0); - layer.ffn_gate_shexp = create_tensor(tn(LLM_TENSOR_FFN_GATE_SHEXP, "weight", il), { n_embd, n_ff_shexp }, 0); - layer.ffn_up_shexp = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP, "weight", il), { n_embd, n_ff_shexp }, 0); - layer.ffn_down_shexp = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP, "weight", il), { n_ff_shexp, n_embd }, 0); + layer.ffn_gate_inp_shexp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP_SHEXP, "weight", il), { n_embd }, mtp_flags); + layer.ffn_gate_shexp = create_tensor(tn(LLM_TENSOR_FFN_GATE_SHEXP, "weight", il), { n_embd, n_ff_shexp }, mtp_flags); + layer.ffn_up_shexp = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP, "weight", il), { n_embd, n_ff_shexp }, mtp_flags); + layer.ffn_down_shexp = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP, "weight", il), { n_ff_shexp, n_embd }, mtp_flags); // NextN-specific tensors that define the MTP block. - layer.nextn.eh_proj = create_tensor(tn(LLM_TENSOR_NEXTN_EH_PROJ, "weight", il), { 2 * n_embd, n_embd }, 0); - layer.nextn.enorm = create_tensor(tn(LLM_TENSOR_NEXTN_ENORM, "weight", il), { n_embd }, 0); - layer.nextn.hnorm = create_tensor(tn(LLM_TENSOR_NEXTN_HNORM, "weight", il), { n_embd }, 0); - layer.nextn.embed_tokens = create_tensor(tn(LLM_TENSOR_NEXTN_EMBED_TOKENS, "weight", il), { n_embd, n_vocab }, TENSOR_NOT_REQUIRED); - layer.nextn.shared_head_head = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_HEAD, "weight", il), { n_embd, n_vocab }, TENSOR_NOT_REQUIRED); - layer.nextn.shared_head_norm = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_NORM, "weight", il), { n_embd }, TENSOR_NOT_REQUIRED); + layer.nextn.eh_proj = create_tensor(tn(LLM_TENSOR_NEXTN_EH_PROJ, "weight", il), { 2 * n_embd, n_embd }, mtp_flags); + layer.nextn.enorm = create_tensor(tn(LLM_TENSOR_NEXTN_ENORM, "weight", il), { n_embd }, mtp_flags); + layer.nextn.hnorm = create_tensor(tn(LLM_TENSOR_NEXTN_HNORM, "weight", il), { n_embd }, mtp_flags); + layer.nextn.embed_tokens = create_tensor(tn(LLM_TENSOR_NEXTN_EMBED_TOKENS, "weight", il), { n_embd, n_vocab }, mtp_flags|TENSOR_NOT_REQUIRED); + layer.nextn.shared_head_head = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_HEAD, "weight", il), { n_embd, n_vocab }, mtp_flags|TENSOR_NOT_REQUIRED); + layer.nextn.shared_head_norm = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_NORM, "weight", il), { n_embd }, mtp_flags|TENSOR_NOT_REQUIRED); }; for (int i = 0; i < n_layer; ++i) { diff --git a/src/models/qwen3next.cpp b/src/models/qwen3next.cpp index 09b66423d5a8..0808fd87aa0e 100644 --- a/src/models/qwen3next.cpp +++ b/src/models/qwen3next.cpp @@ -13,7 +13,11 @@ void llama_model_qwen3next::load_arch_hparams(llama_model_loader & ml) { ml.get_key(LLM_KV_SSM_TIME_STEP_RANK, hparams.ssm_dt_rank); ml.get_key(LLM_KV_SSM_GROUP_COUNT, hparams.ssm_n_group); - // Mark recurrent layers (linear attention layers) + // NextN/MTP: extra decoder block appended beyond the main stack + ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.n_layer_nextn, false); + GGML_ASSERT(hparams.n_layer_nextn < hparams.n_layer_all && "n_layer_nextn must be < n_layer_all"); + + // Mark recurrent layers (linear attention layers). if (!ml.get_key_or_arr(LLM_KV_ATTENTION_RECURRENT_LAYERS, hparams.is_recr_impl, hparams.n_layer_all, false)) { uint32_t full_attn_interval = 4; ml.get_key(LLM_KV_FULL_ATTENTION_INTERVAL, full_attn_interval, false); @@ -28,13 +32,17 @@ void llama_model_qwen3next::load_arch_hparams(llama_model_loader & ml) { } } -void llama_model_qwen3next::load_arch_tensors(llama_model_loader &) { +void llama_model_qwen3next::load_arch_tensors(llama_model_loader & ml) { LLAMA_LOAD_LOCALS; if (n_expert == 0) { throw std::runtime_error(arch_name() + " model cannot have zero experts"); } + const bool mtp_only = (hparams.n_layer_nextn > 0) && (ml.get_weight("blk.0.attn_norm.weight") == nullptr); + const int trunk_flags = mtp_only ? TENSOR_NOT_REQUIRED : 0; + int mtp_flags = !ml.load_mtp ? TENSOR_SKIP : 0; + tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), { n_embd, n_vocab }, 0); // output @@ -61,49 +69,73 @@ void llama_model_qwen3next::load_arch_tensors(llama_model_loader &) { const int64_t qkvz_dim = key_dim * 2 + value_dim * 2; const int64_t ba_dim = n_v_heads * 2; - for (int i = 0; i < n_layer; ++i) { - auto & layer = layers[i]; - const uint32_t n_ff_shexp = hparams.n_ff_shexp > 0 ? hparams.n_ff_shexp : hparams.n_ff(i); + auto load_block_trunk = [&](int il, int flags) { + auto & layer = layers[il]; + const uint32_t n_ff_shexp = hparams.n_ff_shexp > 0 ? hparams.n_ff_shexp : hparams.n_ff(il); - layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), { n_embd }, 0); - layer.attn_post_norm = create_tensor(tn(LLM_TENSOR_ATTN_POST_NORM, "weight", i), { n_embd }, 0); + layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", il), { n_embd }, flags); + layer.attn_post_norm = create_tensor(tn(LLM_TENSOR_ATTN_POST_NORM, "weight", il), { n_embd }, flags); - if (!hparams.is_recr(i)) { + if (!hparams.is_recr(il)) { // Attention layers - create_tensor_qkv(layer, i, n_embd, n_embd_head_k * n_head * 2, n_embd_k_gqa, n_embd_v_gqa, 0); - layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), { n_embd_head_k * n_head, n_embd }, 0); - + create_tensor_qkv(layer, il, n_embd, n_embd_head_k * n_head * 2, n_embd_k_gqa, n_embd_v_gqa, flags); + layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", il), { n_embd_head_k * n_head, n_embd }, flags); // Q/K normalization for attention layers - layer.attn_q_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), { n_embd_head_k }, 0); - layer.attn_k_norm = create_tensor(tn(LLM_TENSOR_ATTN_K_NORM, "weight", i), { n_embd_head_k }, 0); + layer.attn_q_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_NORM, "weight", il), { n_embd_head_k }, flags); + layer.attn_k_norm = create_tensor(tn(LLM_TENSOR_ATTN_K_NORM, "weight", il), { n_embd_head_k }, flags); } else { // Linear attention (gated delta net) specific tensors // Create tensors with calculated dimensions // note: ssm_in is used by legacy GGUF - layer.ssm_in = create_tensor(tn(LLM_TENSOR_SSM_IN, "weight", i), { n_embd, qkvz_dim }, TENSOR_NOT_REQUIRED); - layer.wqkv = create_tensor(tn(LLM_TENSOR_ATTN_QKV, "weight", i), { n_embd, key_dim * 2 + value_dim }, TENSOR_NOT_REQUIRED); - layer.wqkv_gate = create_tensor(tn(LLM_TENSOR_ATTN_GATE, "weight", i), { n_embd, value_dim }, TENSOR_NOT_REQUIRED); - layer.ssm_conv1d = create_tensor(tn(LLM_TENSOR_SSM_CONV1D, "weight", i), { hparams.ssm_d_conv, conv_dim }, 0); - layer.ssm_dt = create_tensor(tn(LLM_TENSOR_SSM_DT, "bias", i), { hparams.ssm_dt_rank }, 0); - layer.ssm_a = create_tensor(tn(LLM_TENSOR_SSM_A_NOSCAN, i), { hparams.ssm_dt_rank }, 0); - layer.ssm_beta_alpha = create_tensor(tn(LLM_TENSOR_SSM_BETA_ALPHA, "weight", i), { n_embd, ba_dim }, 0); - layer.ssm_norm = create_tensor(tn(LLM_TENSOR_SSM_NORM, "weight", i), { head_v_dim }, 0); - layer.ssm_out = create_tensor(tn(LLM_TENSOR_SSM_OUT, "weight", i), { value_dim, n_embd }, 0); + layer.ssm_in = create_tensor(tn(LLM_TENSOR_SSM_IN, "weight", il), { n_embd, qkvz_dim }, TENSOR_NOT_REQUIRED | flags); + layer.wqkv = create_tensor(tn(LLM_TENSOR_ATTN_QKV, "weight", il), { n_embd, key_dim * 2 + value_dim }, TENSOR_NOT_REQUIRED | flags); + layer.wqkv_gate = create_tensor(tn(LLM_TENSOR_ATTN_GATE, "weight", il), { n_embd, value_dim }, TENSOR_NOT_REQUIRED | flags); + layer.ssm_conv1d = create_tensor(tn(LLM_TENSOR_SSM_CONV1D, "weight", il), { hparams.ssm_d_conv, conv_dim }, flags); + layer.ssm_dt = create_tensor(tn(LLM_TENSOR_SSM_DT, "bias", il), { hparams.ssm_dt_rank }, flags); + layer.ssm_a = create_tensor(tn(LLM_TENSOR_SSM_A_NOSCAN, il), { hparams.ssm_dt_rank }, flags); + layer.ssm_beta_alpha = create_tensor(tn(LLM_TENSOR_SSM_BETA_ALPHA, "weight", il), { n_embd, ba_dim }, flags); + layer.ssm_norm = create_tensor(tn(LLM_TENSOR_SSM_NORM, "weight", il), { head_v_dim }, flags); + layer.ssm_out = create_tensor(tn(LLM_TENSOR_SSM_OUT, "weight", il), { value_dim, n_embd }, flags); } - layer.ffn_gate_inp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP, "weight", i), { n_embd, n_expert }, 0); - layer.ffn_down_exps = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), { n_ff_exp, n_embd, n_expert }, 0); - create_tensor_gate_up_exps(layer, i, n_embd, n_ff_exp, n_expert, 0); + layer.ffn_gate_inp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP, "weight", il), { n_embd, n_expert }, flags); + layer.ffn_down_exps = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", il), { n_ff_exp, n_embd, n_expert }, flags); + create_tensor_gate_up_exps(layer, il, n_embd, n_ff_exp, n_expert, flags); // Shared experts - layer.ffn_gate_inp_shexp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP_SHEXP, "weight", i), { n_embd }, 0); - layer.ffn_gate_shexp = create_tensor(tn(LLM_TENSOR_FFN_GATE_SHEXP, "weight", i), { n_embd, n_ff_shexp }, 0); - layer.ffn_up_shexp = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP, "weight", i), { n_embd, n_ff_shexp }, 0); - layer.ffn_down_shexp = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP, "weight", i), { n_ff_shexp, n_embd }, 0); + layer.ffn_gate_inp_shexp = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP_SHEXP, "weight", il), { n_embd }, flags); + layer.ffn_gate_shexp = create_tensor(tn(LLM_TENSOR_FFN_GATE_SHEXP, "weight", il), { n_embd, n_ff_shexp }, flags); + layer.ffn_up_shexp = create_tensor(tn(LLM_TENSOR_FFN_UP_SHEXP, "weight", il), { n_embd, n_ff_shexp }, flags); + layer.ffn_down_shexp = create_tensor(tn(LLM_TENSOR_FFN_DOWN_SHEXP, "weight", il), { n_ff_shexp, n_embd }, flags); + }; + + auto load_block_mtp = [&](int il) { + // MTP head is identical to the trunk block (full attention + FFN) + load_block_trunk(il, mtp_flags); + + auto & layer = layers[il]; + + // NextN-specific tensors that define the MTP block. + layer.nextn.eh_proj = create_tensor(tn(LLM_TENSOR_NEXTN_EH_PROJ, "weight", il), { 2 * n_embd, n_embd }, mtp_flags); + layer.nextn.enorm = create_tensor(tn(LLM_TENSOR_NEXTN_ENORM, "weight", il), { n_embd }, mtp_flags); + layer.nextn.hnorm = create_tensor(tn(LLM_TENSOR_NEXTN_HNORM, "weight", il), { n_embd }, mtp_flags); + layer.nextn.embed_tokens = create_tensor(tn(LLM_TENSOR_NEXTN_EMBED_TOKENS, "weight", il), { n_embd, n_vocab }, mtp_flags | TENSOR_NOT_REQUIRED); + layer.nextn.shared_head_head = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_HEAD, "weight", il), { n_embd, n_vocab }, mtp_flags | TENSOR_NOT_REQUIRED); + layer.nextn.shared_head_norm = create_tensor(tn(LLM_TENSOR_NEXTN_SHARED_HEAD_NORM, "weight", il), { n_embd }, mtp_flags | TENSOR_NOT_REQUIRED); + }; + + for (int i = 0; i < n_layer; i++) { + load_block_trunk(i, trunk_flags); + } + for (int i = n_layer; i < n_layer_all; i++) { + load_block_mtp(i); } } std::unique_ptr llama_model_qwen3next::build_arch_graph(const llm_graph_params & params) const { + if (params.gtype == LLM_GRAPH_TYPE_DECODER_MTP) { + return std::make_unique(*this, params); + } return std::make_unique(*this, params); } @@ -120,6 +152,7 @@ llama_model_qwen3next::graph::graph(const llama_model & model, const llm_graph_p ggml_tensor * inp_pos = build_inp_pos(); ggml_tensor * inp_out_ids = build_inp_out_ids(); + // MTP/NextN layers are loaded as extra decoder blocks but not executed in the main pass. for (int il = 0; il < n_layer; ++il) { res->t_layer_inp[il] = inpL; @@ -139,7 +172,7 @@ llama_model_qwen3next::graph::graph(const llama_model & model, const llm_graph_p cur = build_layer_attn(inp->get_attn(), cur, inp_pos, il); } - if (il == n_layer - 1 && inp_out_ids) { + if (il == n_layer - 1 && inp_out_ids && cparams.embeddings_nextn_masked) { cur = ggml_get_rows(ctx0, cur, inp_out_ids); inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids); } @@ -171,9 +204,16 @@ llama_model_qwen3next::graph::graph(const llama_model & model, const llm_graph_p } cur = inpL; - // Final norm + // post-norm hidden state is input to both the LM head and the MTP head cur = build_norm(cur, model.output_norm, nullptr, LLM_NORM_RMS, -1); + cb(cur, "h_nextn", -1); + res->t_h_nextn = cur; + + if (!cparams.embeddings_nextn_masked && inp_out_ids) { + cur = ggml_get_rows(ctx0, cur, inp_out_ids); + } + cb(cur, "result_norm", -1); res->t_embd = cur; @@ -186,14 +226,6 @@ llama_model_qwen3next::graph::graph(const llama_model & model, const llm_graph_p ggml_build_forward_expand(gf, cur); } -// utility to get one slice from the third dimension -// input dim: [x, y, c, b] -// output dim: [x, y, 1, b] -static ggml_tensor * get_slice_2d(ggml_context * ctx0, ggml_tensor * t, int64_t c) { - return ggml_view_4d(ctx0, t, t->ne[0], t->ne[1], 1, t->ne[3], - t->nb[1], t->nb[2], t->nb[3], t->nb[2] * c); -} - ggml_tensor * llama_model_qwen3next::graph::build_norm_gated( ggml_tensor * input, ggml_tensor * weights, @@ -216,7 +248,7 @@ ggml_tensor * llama_model_qwen3next::graph::build_layer_attn( // Order: joint QG projection, QG split, Q norm, KV projection, K norm, RoPE, attention // Qwen3Next uses a single Q projection that outputs query + gate - ggml_tensor * Qcur_full = build_lora_mm(model.layers[il].wq, cur); + ggml_tensor * Qcur_full = build_lora_mm(model.layers[il].wq, cur, model.layers[il].wq_s); cb(Qcur_full, "Qcur_full", il); Qcur_full = ggml_reshape_4d(ctx0, Qcur_full, n_embd_head * 2, n_head, n_tokens, 1); @@ -232,10 +264,10 @@ ggml_tensor * llama_model_qwen3next::graph::build_layer_attn( Qcur_full->nb[1], Qcur_full->nb[2], Qcur_full->nb[3], n_embd_head * ggml_element_size(Qcur_full)); cb(gate, "gate", il); - ggml_tensor * Kcur = build_lora_mm(model.layers[il].wk, cur); + ggml_tensor * Kcur = build_lora_mm(model.layers[il].wk, cur, model.layers[il].wk_s); cb(Kcur, "Kcur", il); - ggml_tensor * Vcur = build_lora_mm(model.layers[il].wv, cur); + ggml_tensor * Vcur = build_lora_mm(model.layers[il].wv, cur, model.layers[il].wv_s); cb(Vcur, "Vcur", il); Kcur = ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens); @@ -274,8 +306,6 @@ ggml_tensor * llama_model_qwen3next::graph::build_layer_attn( gate = ggml_sigmoid(ctx0, gate); cb(gate, "gate_sigmoid", il); - gate = ggml_reshape_2d(ctx0, gate, n_embd_head * n_head, n_tokens); - cur = ggml_mul(ctx0, cur, gate); cb(cur, "attn_gated", il); @@ -550,16 +580,19 @@ ggml_tensor * llama_model_qwen3next::graph::build_layer_ffn(ggml_tensor * cur, c LLM_FFN_SILU, true, hparams.expert_weights_scale, LLAMA_EXPERT_GATING_FUNC_TYPE_SOFTMAX, il, - nullptr, model.layers[il].ffn_gate_up_exps); + nullptr, model.layers[il].ffn_gate_up_exps, + model.layers[il].ffn_up_exps_s, + model.layers[il].ffn_gate_exps_s, + model.layers[il].ffn_down_exps_s); cb(moe_out, "ffn_moe_out", il); // Add shared experts if present - following Qwen3Next reference implementation if (model.layers[il].ffn_up_shexp != nullptr) { ggml_tensor * ffn_shexp = build_ffn(cur, - model.layers[il].ffn_up_shexp, NULL, NULL, - model.layers[il].ffn_gate_shexp, NULL, NULL, - model.layers[il].ffn_down_shexp, NULL, NULL, + model.layers[il].ffn_up_shexp, NULL, model.layers[il].ffn_up_shexp_s, + model.layers[il].ffn_gate_shexp, NULL, model.layers[il].ffn_gate_shexp_s, + model.layers[il].ffn_down_shexp, NULL, model.layers[il].ffn_down_shexp_s, NULL, LLM_FFN_SILU, LLM_FFN_PAR, il); cb(ffn_shexp, "ffn_shexp", il); @@ -593,3 +626,198 @@ ggml_tensor * llama_model_qwen3next::graph::build_layer_ffn(ggml_tensor * cur, c } return cur; } + +// LLM_GRAPH_TYPE_DECODER_MTP draft head for Qwen3-Next +llama_model_qwen3next::graph_mtp::graph_mtp(const llama_model & model, const llm_graph_params & params) + : llm_graph_context(params) { + GGML_ASSERT(hparams.n_layer_nextn > 0 && "QWEN3NEXT MTP requires n_layer_nextn > 0"); + GGML_ASSERT(hparams.n_layer_nextn == 1 && "QWEN3NEXT MTP currently only supports a single MTP block"); + + const int64_t n_embd_head = hparams.n_embd_head_v(); + GGML_ASSERT(n_embd_head == hparams.n_embd_head_k()); + + const int il = hparams.n_layer(); + const auto & layer = model.layers[il]; + + GGML_ASSERT(layer.nextn.eh_proj && "MTP block missing nextn.eh_proj"); + GGML_ASSERT(layer.nextn.enorm && "MTP block missing nextn.enorm"); + GGML_ASSERT(layer.nextn.hnorm && "MTP block missing nextn.hnorm"); + GGML_ASSERT(layer.ffn_gate_inp && "MTP block missing ffn_gate_inp"); + + // TODO: extract in a common llm_graph_context::build_inp_embd_h() + auto inp = std::make_unique(hparams.n_embd); + + inp->tokens = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_tokens); + ggml_set_input(inp->tokens); + + inp->embd = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, hparams.n_embd_inp(), n_tokens); + ggml_set_input(inp->embd); + + // TODO: make static using `ggml_build_forward_select()` + // see llm_graph_context::build_inp_embd() for reference + ggml_tensor * tok_embd; + if (ubatch.token) { + ggml_tensor * tok_embd_w = layer.nextn.embed_tokens ? layer.nextn.embed_tokens : model.tok_embd; + + tok_embd = ggml_get_rows(ctx0, tok_embd_w, inp->tokens); + } else { + tok_embd = inp->embd; + } + cb(tok_embd, "mtp_tok_embd", il); + + inp->h = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, hparams.n_embd, n_tokens); + ggml_set_input(inp->h); + ggml_set_name(inp->h, "mtp_h_input"); + + ggml_tensor * h_embd = inp->h; + + res->add_input(std::move(inp)); + + ggml_tensor * inp_pos = build_inp_pos(); + ggml_tensor * inp_out_ids = build_inp_out_ids(); + + auto * inp_attn = build_attn_inp_kv(); + + ggml_tensor * h_norm = build_norm(h_embd, layer.nextn.hnorm, nullptr, LLM_NORM_RMS, il); + cb(h_norm, "mtp_hnorm", il); + + ggml_tensor * e_norm = build_norm(tok_embd, layer.nextn.enorm, nullptr, LLM_NORM_RMS, il); + cb(e_norm, "mtp_enorm", il); + + ggml_tensor * concat = ggml_concat(ctx0, e_norm, h_norm, /*dim=*/ 0); + cb(concat, "mtp_concat", il); + + ggml_tensor * cur = build_lora_mm(layer.nextn.eh_proj, concat, layer.nextn.eh_proj_s); + cb(cur, "mtp_eh_proj", il); + + ggml_tensor * inpSA = cur; + + cur = build_norm(cur, layer.attn_norm, nullptr, LLM_NORM_RMS, il); + cb(cur, "mtp_attn_norm", il); + + ggml_tensor * Qcur_full = build_lora_mm(layer.wq, cur, layer.wq_s); + cb(Qcur_full, "mtp_Qcur_full", il); + + ggml_tensor * Qcur = ggml_view_3d(ctx0, Qcur_full, + n_embd_head, n_head, n_tokens, + ggml_element_size(Qcur_full) * n_embd_head * 2, + ggml_element_size(Qcur_full) * n_embd_head * 2 * n_head, + 0); + Qcur = build_norm(Qcur, layer.attn_q_norm, nullptr, LLM_NORM_RMS, il); + cb(Qcur, "mtp_Qcur_normed", il); + + ggml_tensor * Kcur = build_lora_mm(layer.wk, cur, layer.wk_s); + Kcur = ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens); + Kcur = build_norm(Kcur, layer.attn_k_norm, nullptr, LLM_NORM_RMS, il); + cb(Kcur, "mtp_Kcur_normed", il); + + ggml_tensor * Vcur = build_lora_mm(layer.wv, cur, layer.wv_s); + Vcur = ggml_reshape_3d(ctx0, Vcur, n_embd_head, n_head_kv, n_tokens); + + Qcur = ggml_rope_ext(ctx0, Qcur, inp_pos, nullptr, + n_rot, rope_type, n_ctx_orig, freq_base, freq_scale, + ext_factor, attn_factor, beta_fast, beta_slow); + Kcur = ggml_rope_ext(ctx0, Kcur, inp_pos, nullptr, + n_rot, rope_type, n_ctx_orig, freq_base, freq_scale, + ext_factor, attn_factor, beta_fast, beta_slow); + + cb(Qcur, "mtp_Qcur", il); + cb(Kcur, "mtp_Kcur", il); + cb(Vcur, "mtp_Vcur", il); + + const float kq_scale = hparams.f_attention_scale == 0.0f + ? 1.0f / sqrtf(float(n_embd_head)) : hparams.f_attention_scale; + + cur = build_attn(inp_attn, + nullptr, nullptr, nullptr, + Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, kq_scale, il); + cb(cur, "mtp_attn_pregate", il); + + ggml_tensor * gate = ggml_view_3d(ctx0, Qcur_full, + n_embd_head, n_head, n_tokens, + ggml_element_size(Qcur_full) * n_embd_head * 2, + ggml_element_size(Qcur_full) * n_embd_head * 2 * n_head, + ggml_element_size(Qcur_full) * n_embd_head); + + // TODO: CUDA is missing non-contiguous unary ops. when implemented: remove this cont + gate = ggml_cont_2d(ctx0, gate, n_embd_head * n_head, n_tokens); + cb(gate, "mtp_gate", il); + + cur = ggml_mul(ctx0, cur, ggml_sigmoid(ctx0, gate)); + cur = build_lora_mm(layer.wo, cur, layer.wo_s); + cb(cur, "mtp_attn_out", il); + + if (inp_out_ids) { + cur = ggml_get_rows(ctx0, cur, inp_out_ids); + inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids); + } + + cur = ggml_add(ctx0, cur, inpSA); + cb(cur, "mtp_attn_residual", il); + + ggml_tensor * ffn_residual = cur; + cur = build_norm(cur, layer.attn_post_norm, nullptr, LLM_NORM_RMS, il); + cb(cur, "mtp_attn_post_norm", il); + + // MoE FFN — routed experts plus gated shared expert (mirrors the trunk). + ggml_tensor * moe_out = + build_moe_ffn(cur, + layer.ffn_gate_inp, + layer.ffn_up_exps, + layer.ffn_gate_exps, + layer.ffn_down_exps, + nullptr, + n_expert, n_expert_used, + LLM_FFN_SILU, true, + hparams.expert_weights_scale, + LLAMA_EXPERT_GATING_FUNC_TYPE_SOFTMAX, il, + nullptr, layer.ffn_gate_up_exps, + layer.ffn_up_exps_s, + layer.ffn_gate_exps_s, + layer.ffn_down_exps_s); + cb(moe_out, "mtp_ffn_moe_out", il); + + if (layer.ffn_up_shexp != nullptr) { + ggml_tensor * ffn_shexp = + build_ffn(cur, + layer.ffn_up_shexp, nullptr, layer.ffn_up_shexp_s, + layer.ffn_gate_shexp, nullptr, layer.ffn_gate_shexp_s, + layer.ffn_down_shexp, nullptr, layer.ffn_down_shexp_s, + nullptr, + LLM_FFN_SILU, LLM_FFN_PAR, il); + cb(ffn_shexp, "mtp_ffn_shexp", il); + + ggml_tensor * shared_gate = build_lora_mm(layer.ffn_gate_inp_shexp, cur); + shared_gate = ggml_sigmoid(ctx0, shared_gate); + cb(shared_gate, "mtp_shared_expert_gate_sigmoid", il); + + ffn_shexp = ggml_mul(ctx0, ffn_shexp, shared_gate); + cb(ffn_shexp, "mtp_ffn_shexp_gated", il); + + cur = ggml_add(ctx0, moe_out, ffn_shexp); + } else { + cur = moe_out; + } + cb(cur, "mtp_ffn_out", il); + + cur = ggml_add(ctx0, cur, ffn_residual); + cb(cur, "mtp_post_ffn", il); + + ggml_tensor * head_norm_w = layer.nextn.shared_head_norm + ? layer.nextn.shared_head_norm + : model.output_norm; + GGML_ASSERT(head_norm_w && "QWEN3NEXT MTP: missing both nextn.shared_head_norm and output_norm"); + cur = build_norm(cur, head_norm_w, nullptr, LLM_NORM_RMS, -1); + + cb(cur, "h_nextn", -1); + res->t_h_nextn = cur; + + ggml_tensor * head_w = layer.nextn.shared_head_head ? layer.nextn.shared_head_head : model.output; + ggml_tensor * head_s = layer.nextn.shared_head_head ? layer.nextn.shared_head_head_s : model.output_s; + GGML_ASSERT(head_w && "QWEN3NEXT MTP: missing LM head (nextn.shared_head_head or model.output)"); + cur = build_lora_mm(head_w, cur, head_s); + cb(cur, "result_output", -1); + + res->t_logits = cur; + ggml_build_forward_expand(gf, cur); +} diff --git a/src/models/qwen3tts.cpp b/src/models/qwen3tts.cpp new file mode 100644 index 000000000000..3604f844c393 --- /dev/null +++ b/src/models/qwen3tts.cpp @@ -0,0 +1,3 @@ +#include "models.h" + +// llama_model_qwen3tts reuses llama_model_qwen3vl's hparams/tensors/graph logic diff --git a/src/models/qwen3vl.cpp b/src/models/qwen3vl.cpp index 724d6140d193..5596620f0782 100644 --- a/src/models/qwen3vl.cpp +++ b/src/models/qwen3vl.cpp @@ -16,11 +16,16 @@ void llama_model_qwen3vl::load_arch_hparams(llama_model_loader & ml) { void llama_model_qwen3vl::load_arch_tensors(llama_model_loader &) { LLAMA_LOAD_LOCALS; + int64_t n_vocab_out = n_vocab; + if (arch == LLM_ARCH_QWEN3TTS) { + n_vocab_out = 3072; + } + tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0); // output output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0); - output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED); + output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab_out}, TENSOR_NOT_REQUIRED); // if output is NULL, init from the input tok embed if (output == NULL) { output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED); @@ -166,6 +171,24 @@ llama_model_qwen3vl::graph::graph(const llama_model & model, const llm_graph_par // lm_head cur = build_lora_mm(model.output, cur, model.output_s); + int64_t n_vocab_in = model.tok_embd->ne[1]; + int64_t n_vocab_out = model.output->ne[1]; + if (n_vocab_in > n_vocab_out) { + // case: Qwen3TTS model with codec_head as output + GGML_ASSERT(model.output_norm); + int64_t pad = n_vocab_in - n_vocab_out; + + // using this trick to get a scalar -inf tensor to pad the output + ggml_tensor * neg_inf = ggml_scale_bias(ctx0, + ggml_view_1d(ctx0, model.output_norm, 1, 0), + 0.0f, -INFINITY); + neg_inf = ggml_repeat_4d(ctx0, neg_inf, pad, cur->ne[1], 1, 1); + cur = ggml_concat(ctx0, neg_inf, cur, 0); // [padded .. n_vocab_out, n_stream] + + } else if (n_vocab_in < n_vocab_out) { + GGML_ABORT("invalid case"); + } + cb(cur, "result_output", -1); res->t_logits = cur; diff --git a/src/models/step35.cpp b/src/models/step35.cpp index 9b7b18a3678b..5b1d902581e6 100644 --- a/src/models/step35.cpp +++ b/src/models/step35.cpp @@ -48,7 +48,11 @@ void llama_model_step35::load_arch_tensors(llama_model_loader & ml) { const std::string mtp_probe = "blk." + std::to_string(n_layer) + ".nextn.eh_proj.weight"; const bool trunk_only = (hparams.n_layer_nextn > 0) && (ml.get_weight(mtp_probe.c_str()) == nullptr); const int trunk_flags = mtp_only ? TENSOR_NOT_REQUIRED : 0; - const int mtp_flags = trunk_only ? TENSOR_NOT_REQUIRED : 0; + int mtp_flags = trunk_only ? TENSOR_NOT_REQUIRED : 0; + + if (!ml.load_mtp) { + mtp_flags |= TENSOR_SKIP; + } tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0); diff --git a/tests/CMakeLists.txt b/tests/CMakeLists.txt index 881e55c75a1d..419e1eba4c2c 100644 --- a/tests/CMakeLists.txt +++ b/tests/CMakeLists.txt @@ -258,6 +258,9 @@ llama_build_and_test(test-thread-safety.cpp ARGS -m "${MODEL_DEST}" -ngl 99 -p " set_tests_properties(test-thread-safety PROPERTIES FIXTURES_REQUIRED test-download-model) llama_build_and_test(test-arg-parser.cpp) +llama_build_and_test(test-model-resolution.cpp) +# the test serves its repos from an httplib server, and the library links it privately +target_link_libraries(test-model-resolution PRIVATE cpp-httplib) if (NOT LLAMA_SANITIZE_ADDRESS AND NOT GGML_SCHED_NO_REALLOC) # TODO: repair known memory leaks diff --git a/tests/test-arg-parser.cpp b/tests/test-arg-parser.cpp index 1d3584f903c4..50db29727452 100644 --- a/tests/test-arg-parser.cpp +++ b/tests/test-arg-parser.cpp @@ -99,6 +99,42 @@ static void test(void) { argv = {"binary_name", "-sm", "hello"}; assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_COMMON)); + { + common_params penalty_params; + assert(penalty_params.sampling.penalty_last_n == 64); + assert(penalty_params.sampling.dry_penalty_last_n == 64); + + argv = {"binary_name", "--repeat-last-n", "-1"}; + assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), penalty_params, LLAMA_EXAMPLE_COMMON)); + + argv = {"binary_name", "--dry-penalty-last-n", "-1"}; + assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), penalty_params, LLAMA_EXAMPLE_COMMON)); + + argv = {"binary_name", "--repeat-penalty", "0"}; + assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), penalty_params, LLAMA_EXAMPLE_COMMON)); + + argv = {"binary_name", "--repeat-penalty", "-1"}; + assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), penalty_params, LLAMA_EXAMPLE_COMMON)); + + argv = {"binary_name", "--repeat-penalty", "nan"}; + assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), penalty_params, LLAMA_EXAMPLE_COMMON)); + + argv = {"binary_name", "--repeat-penalty", "inf"}; + assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), penalty_params, LLAMA_EXAMPLE_COMMON)); + + argv = {"binary_name", "--repeat-penalty", "-inf"}; + assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), penalty_params, LLAMA_EXAMPLE_COMMON)); + + const char * penalty_options[] = {"--frequency-penalty", "--presence-penalty"}; + const char * nonfinite_values[] = {"nan", "inf", "-inf"}; + for (const char * option : penalty_options) { + for (const char * value : nonfinite_values) { + argv = {"binary_name", option, value}; + assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), penalty_params, LLAMA_EXAMPLE_COMMON)); + } + } + } + // non-existence arg in specific example (--draft cannot be used outside llama-speculative) argv = {"binary_name", "--draft", "123"}; assert(false == common_params_parse(argv.size(), list_str_to_char(argv).data(), params, LLAMA_EXAMPLE_EMBEDDING)); diff --git a/tests/test-backend-ops.cpp b/tests/test-backend-ops.cpp index 162bfc98c8b3..8cb598935861 100644 --- a/tests/test-backend-ops.cpp +++ b/tests/test-backend-ops.cpp @@ -8069,6 +8069,7 @@ static std::vector> make_test_cases_eval() { test_cases.emplace_back(new test_dsv4_hc_comb(1, 1)); test_cases.emplace_back(new test_dsv4_hc_comb(17, 4)); test_cases.emplace_back(new test_dsv4_hc_comb(257, 8)); + test_cases.emplace_back(new test_dsv4_hc_comb(17, 20)); test_cases.emplace_back(new test_dsv4_hc_pre(1, 1)); test_cases.emplace_back(new test_dsv4_hc_pre(31, 17)); @@ -8078,6 +8079,7 @@ static std::vector> make_test_cases_eval() { test_cases.emplace_back(new test_dsv4_hc_post(1, 1)); test_cases.emplace_back(new test_dsv4_hc_post(31, 17)); test_cases.emplace_back(new test_dsv4_hc_post(128, 257)); + test_cases.emplace_back(new test_dsv4_hc_post(4096, 21)); // glu ops for (ggml_type type : {GGML_TYPE_F16, GGML_TYPE_F32}) { @@ -8192,9 +8194,9 @@ static std::vector> make_test_cases_eval() { for (ggml_type type_input : {GGML_TYPE_F32}) { for (ggml_op_pool pool_type : {GGML_OP_POOL_AVG, GGML_OP_POOL_MAX}) { - for (int k0 : {1, 3}) { - for (int s0 : {1, 2}) { - for (int p0 : {0, 1}) { + for (int k0 : {1, 2, 3}) { + for (int s0 : {1, 2, 3}) { + for (int p0 : {0, 1, 2, 3}) { test_cases.emplace_back(new test_pool1d(pool_type, type_input, { 10, 3, 2, 1 }, k0, s0, p0)); test_cases.emplace_back(new test_pool1d(pool_type, type_input, { 11, 1, 3, 2 }, k0, s0, p0)); test_cases.emplace_back(new test_pool1d(pool_type, type_input, { 128, 2, 1, 3 }, k0, s0, p0)); @@ -8511,6 +8513,7 @@ static std::vector> make_test_cases_eval() { test_cases.emplace_back(new test_repeat(GGML_TYPE_F32, {10, 5, 4, ne3}, {1, 2, 1, 1})); test_cases.emplace_back(new test_repeat(GGML_TYPE_F32, {10, 5, 4, ne3}, {1, 1, 2, 1})); test_cases.emplace_back(new test_repeat(GGML_TYPE_F32, {10, 5, 4, ne3}, {1, 1, 1, 2})); + test_cases.emplace_back(new test_repeat(GGML_TYPE_F16, {10, 5, 4, ne3}, {2, 1, 1, 1})); test_cases.emplace_back(new test_repeat(GGML_TYPE_I32, {10, 5, 4, ne3}, {2, 1, 1, 1})); test_cases.emplace_back(new test_repeat(GGML_TYPE_I16, {10, 5, 4, ne3}, {1, 1, 1, 2})); test_cases.emplace_back(new test_repeat(GGML_TYPE_BF16, {10, 5, 4, ne3}, {2, 1, 1, 1})); @@ -9513,6 +9516,18 @@ static std::vector> make_test_cases_eval() { } } + // prefill-shaped cases with long KV (nb >= 32, kv >= 1024): covers the + // XMX/GEMM-accelerated SYCL FA path which only activates for these shapes. + for (int kv : { 1024, 2048, }) { + for (int hs : { 64, 128, 256, }) { + for (int nb : { 32, 64, }) { + for (ggml_type type_KV : { GGML_TYPE_F16, GGML_TYPE_Q8_0, GGML_TYPE_Q4_0, }) { + test_cases.emplace_back(new test_flash_attn_ext(hs, hs, 8, {4, 1}, kv, nb, true, false, 0, 0, GGML_PREC_F32, type_KV, type_KV)); + } + } + } + } + for (int hsk : { 40, 64, 72, 80, 96, 128, 192, 256, 320, 512, 576 }) { for (int hsv : { 40, 64, 72, 80, 96, 128, 192, 256, 512 }) { if (hsk != 192 && hsk != 320 && hsk != 576 && hsk != hsv) continue; @@ -9716,6 +9731,12 @@ static std::vector> make_test_cases_eval() { } } + for (int kv : { 1, 7, 8, 63, 64, 65 }) { + for (ggml_type type_K : {GGML_TYPE_F32, GGML_TYPE_F16, GGML_TYPE_BF16, GGML_TYPE_Q8_0, GGML_TYPE_Q5_1, GGML_TYPE_Q5_0, GGML_TYPE_Q4_1, GGML_TYPE_Q4_0}) { + test_cases.emplace_back(new test_lightning_indexer(128, 64, kv, 32, 4, 1, type_K)); + } + } + return test_cases; } #ifdef _MSC_VER diff --git a/tests/test-backend-sampler.cpp b/tests/test-backend-sampler.cpp index c24076e31372..1165f46f0c92 100644 --- a/tests/test-backend-sampler.cpp +++ b/tests/test-backend-sampler.cpp @@ -8,12 +8,15 @@ #endif #include +#include #include #include #include +#include #include #include #include +#include #include struct test_args { @@ -761,6 +764,564 @@ static void test_backend_logit_bias_sampling(const test_params & params) { printf("backend logit bias sampling test PASSED\n"); } +static void accept_prompt(llama_sampler * smpl, const llama_vocab * vocab, const std::string & prompt) { + const llama_token bos = llama_vocab_bos(vocab); + if (bos != LLAMA_TOKEN_NULL) { + llama_sampler_accept(smpl, bos); + } + + std::vector tokens(64); + int32_t n_tokens = llama_tokenize(vocab, prompt.c_str(), (int32_t) prompt.size(), + tokens.data(), (int32_t) tokens.size(), false, false); + if (n_tokens < 0) { + tokens.resize(-n_tokens); + n_tokens = llama_tokenize(vocab, prompt.c_str(), (int32_t) prompt.size(), + tokens.data(), (int32_t) tokens.size(), false, false); + } + + for (int32_t i = 0; i < n_tokens; ++i) { + llama_sampler_accept(smpl, tokens[i]); + } +} + +static std::vector decode_raw_logits(const test_params & params, const std::string & prompt) { + const int seq_id = 0; + const int n_vocab = llama_vocab_n_tokens(llama_model_get_vocab(params.model.get())); + std::vector empty_configs; + test_context ctx(params, empty_configs); + + GGML_ASSERT(ctx.decode({{ seq_id, prompt }})); + + float * logits = llama_get_logits_ith(ctx.ctx.get(), ctx.idx_for_seq(seq_id)); + GGML_ASSERT(logits != nullptr); + return std::vector(logits, logits + n_vocab); +} + +static std::vector apply_cpu_sampler( + const std::vector & raw_logits, + llama_sampler * sampler) { + std::vector data; + data.reserve(raw_logits.size()); + for (llama_token token = 0; token < (llama_token) raw_logits.size(); ++token) { + data.push_back({ token, raw_logits[token], 0.0f }); + } + + llama_token_data_array cur_p = { data.data(), data.size(), -1, false }; + llama_sampler_apply(sampler, &cur_p); + data.resize(cur_p.size); + return data; +} + +using sampler_setup_fn = std::function; +using sampler_init_fn = std::function; + +enum class penalties_position { + before_filter, + after_filter, +}; + +static void add_filter_and_penalties( + llama_sampler * chain, + const sampler_init_fn & init_filter, + int32_t n_vocab, + int32_t penalty_last_n, + float penalty_repeat, + float penalty_freq, + float penalty_present, + penalties_position position) { + const auto add_penalties = [&]() { + llama_sampler_chain_add(chain, llama_sampler_init_penalties( + n_vocab, penalty_last_n, penalty_repeat, penalty_freq, penalty_present)); + }; + + if (position == penalties_position::before_filter) { + add_penalties(); + llama_sampler_chain_add(chain, init_filter()); + } else { + llama_sampler_chain_add(chain, init_filter()); + add_penalties(); + } +} + +static llama_sampler_ptr make_sampler_chain( + const sampler_setup_fn & add_samplers, + const sampler_setup_fn & accept_history) { + llama_sampler_ptr chain(llama_sampler_chain_init(llama_sampler_chain_default_params())); + add_samplers(chain.get()); + accept_history(chain.get()); + return chain; +} + +struct backend_sampler_output { + std::vector logits; + std::vector candidates; +}; + +static backend_sampler_output run_backend_sampler( + const test_params & params, + const std::string & prompt, + llama_sampler * sampler) { + const int seq_id = 0; + std::vector configs = {{ seq_id, sampler }}; + test_context ctx(params, configs); + + GGML_ASSERT(ctx.decode({{ seq_id, prompt }})); + llama_synchronize(ctx.ctx.get()); + + const int32_t idx = ctx.idx_for_seq(seq_id); + const uint32_t n_logits = llama_get_sampled_logits_count_ith(ctx.ctx.get(), idx); + const uint32_t n_candidates = llama_get_sampled_candidates_count_ith(ctx.ctx.get(), idx); + float * logits = llama_get_sampled_logits_ith(ctx.ctx.get(), idx); + llama_token * candidates = llama_get_sampled_candidates_ith(ctx.ctx.get(), idx); + GGML_ASSERT(logits != nullptr); + + backend_sampler_output result; + result.logits.assign(logits, logits + n_logits); + result.candidates.resize(n_logits); + + if (n_candidates == 0) { + for (uint32_t i = 0; i < n_logits; ++i) { + result.candidates[i] = (llama_token) i; + } + } else { + GGML_ASSERT(candidates != nullptr); + GGML_ASSERT(n_candidates == n_logits); + std::memcpy(result.candidates.data(), candidates, n_candidates * sizeof(llama_token)); + } + + return result; +} + +struct sampler_comparison_output { + std::vector expected; + backend_sampler_output actual; +}; + +static sampler_comparison_output run_sampler_comparison( + const test_params & params, + const std::string & prompt, + const std::vector & raw_logits, + const sampler_setup_fn & add_samplers, + const sampler_setup_fn & accept_history) { + llama_sampler_ptr cpu_chain = make_sampler_chain(add_samplers, accept_history); + llama_sampler_ptr backend_chain = make_sampler_chain(add_samplers, accept_history); + return { + apply_cpu_sampler(raw_logits, cpu_chain.get()), + run_backend_sampler(params, prompt, backend_chain.get()), + }; +} + +static std::unordered_map map_logits(const std::vector & data) { + std::unordered_map result; + result.reserve(data.size()); + for (const auto & item : data) { + result[item.id] = item.logit; + } + return result; +} + +struct sampler_comparison_stats { + int n_mismatch = 0; + int n_masked = 0; + float max_diff = 0.0f; +}; + +static sampler_comparison_stats compare_sampler_outputs( + const char * name, + const std::unordered_map & expected, + const backend_sampler_output & actual, + bool allow_extra_candidates = false) { + GGML_ASSERT(actual.logits.size() == actual.candidates.size()); + + sampler_comparison_stats result; + std::unordered_set seen; + seen.reserve(actual.candidates.size()); + + for (size_t i = 0; i < actual.logits.size(); ++i) { + const llama_token token = actual.candidates[i]; + const float logit = actual.logits[i]; + if (!seen.insert(token).second || std::isnan(logit)) { + if (result.n_mismatch < 5) { + printf("%s token %d has invalid backend output\n", name, token); + } + ++result.n_mismatch; + continue; + } + + const auto it = expected.find(token); + if (it == expected.end()) { + if (std::isinf(logit) && logit < 0.0f) { + ++result.n_masked; + } else if (!allow_extra_candidates) { + if (result.n_mismatch < 5) { + printf("%s token %d was not masked\n", name, token); + } + ++result.n_mismatch; + } + continue; + } + + const float diff = fabsf(it->second - logit); + result.max_diff = std::max(result.max_diff, diff); + if (!std::isfinite(logit) || diff > 1e-3f) { + if (result.n_mismatch < 5) { + printf("%s mismatch token %d: cpu=%.6f backend=%.6f diff=%.6f\n", + name, token, it->second, logit, diff); + } + ++result.n_mismatch; + } + } + + for (const auto & item : expected) { + if (seen.find(item.first) == seen.end()) { + if (result.n_mismatch < 5) { + printf("%s missing backend token %d\n", name, item.first); + } + ++result.n_mismatch; + } + } + + printf("%s logits: max_diff=%.6f n_masked=%d n_mismatch=%d\n", + name, result.max_diff, result.n_masked, result.n_mismatch); + return result; +} + +static float find_backend_logit(const backend_sampler_output & output, llama_token token) { + for (size_t i = 0; i < output.candidates.size(); ++i) { + if (output.candidates[i] == token) { + return output.logits[i]; + } + } + GGML_ABORT("backend token not found"); +} + +static sampler_comparison_output run_penalties_comparison( + const test_params & params, + int32_t penalty_last_n, + float penalty_repeat, + float penalty_freq, + float penalty_present, + const std::string & prompt, + const std::function & extra_accept = {}) { + const auto * vocab = llama_model_get_vocab(params.model.get()); + const std::vector raw_logits = decode_raw_logits(params, prompt); + const auto add_samplers = [&](llama_sampler * chain) { + llama_sampler_chain_add(chain, llama_sampler_init_penalties( + llama_vocab_n_tokens(vocab), penalty_last_n, penalty_repeat, penalty_freq, penalty_present)); + }; + const auto accept_history = [&](llama_sampler * chain) { + accept_prompt(chain, vocab, prompt); + if (extra_accept) { + extra_accept(chain); + } + }; + + return run_sampler_comparison( + params, prompt, raw_logits, add_samplers, accept_history); +} + +static void compare_penalties_logits( + const test_params & params, + int32_t penalty_last_n, + float penalty_repeat, + float penalty_freq, + float penalty_present, + const std::string & prompt, + const std::function & extra_accept = {}) { + const sampler_comparison_output output = run_penalties_comparison( + params, penalty_last_n, penalty_repeat, penalty_freq, penalty_present, prompt, extra_accept); + + GGML_ASSERT(output.expected.size() == output.actual.logits.size()); + + const sampler_comparison_stats stats = compare_sampler_outputs( + "penalties", map_logits(output.expected), output.actual); + GGML_ASSERT(stats.n_masked == 0); + GGML_ASSERT(stats.n_mismatch == 0); +} + +static void test_penalty_parameter_values(const test_params & params) { + struct penalty_test_case { + const char * name; + float repeat; + float frequency; + float presence; + }; + + const penalty_test_case cases[] = { + { "frequency -1", 1.0f, -1.0f, 0.0f }, + { "frequency 0", 1.0f, 0.0f, 0.0f }, + { "frequency 1", 1.0f, 1.0f, 0.0f }, + { "presence -1", 1.0f, 0.0f, -1.0f }, + { "presence 0", 1.0f, 0.0f, 0.0f }, + { "presence 1", 1.0f, 0.0f, 1.0f }, + { "repeat 1", 1.0f, 0.0f, 0.0f }, + }; + + int n_failed = 0; + for (const auto & test : cases) { + const sampler_comparison_output output = run_penalties_comparison( + params, 64, test.repeat, test.frequency, test.presence, "Hello Hello world"); + GGML_ASSERT(output.expected.size() == output.actual.logits.size()); + const sampler_comparison_stats stats = compare_sampler_outputs( + test.name, map_logits(output.expected), output.actual); + n_failed += stats.n_mismatch != 0; + } + + GGML_ASSERT(n_failed == 0); +} + +static void compare_top_k_penalties_logits( + const test_params & params, + int32_t k, + int32_t penalty_last_n, + float penalty_repeat, + float penalty_freq, + float penalty_present, + const std::string & prompt, + penalties_position position) { + const auto * vocab = llama_model_get_vocab(params.model.get()); + const std::vector raw_logits = decode_raw_logits(params, prompt); + const int n_vocab = (int) raw_logits.size(); + + GGML_ASSERT(n_vocab > k); + + const sampler_init_fn init_top_k = [k]() { + return llama_sampler_init_top_k(k); + }; + llama_sampler_ptr top_k(init_top_k()); + const std::vector top_k_data = apply_cpu_sampler(raw_logits, top_k.get()); + GGML_ASSERT(top_k_data.size() == (size_t) k); + const llama_token retained_history_token = top_k_data[0].id; + + llama_token excluded_history_token = LLAMA_TOKEN_NULL; + for (llama_token token = 0; token < n_vocab; ++token) { + const auto it = std::find_if(top_k_data.begin(), top_k_data.end(), [token](const llama_token_data & data) { + return data.id == token; + }); + if (it == top_k_data.end()) { + excluded_history_token = token; + break; + } + } + GGML_ASSERT(excluded_history_token != LLAMA_TOKEN_NULL); + + const auto add_samplers = [&](llama_sampler * chain) { + add_filter_and_penalties(chain, init_top_k, n_vocab, + penalty_last_n, penalty_repeat, penalty_freq, penalty_present, position); + }; + + auto accept_history = [&](llama_sampler * smpl) { + accept_prompt(smpl, vocab, prompt); + llama_sampler_accept(smpl, excluded_history_token); + llama_sampler_accept(smpl, excluded_history_token); + llama_sampler_accept(smpl, retained_history_token); + llama_sampler_accept(smpl, retained_history_token); + }; + + const sampler_comparison_output output = run_sampler_comparison( + params, prompt, raw_logits, add_samplers, accept_history); + + GGML_ASSERT(output.expected.size() == (size_t) k); + GGML_ASSERT(output.actual.logits.size() == (size_t) k); + + const std::unordered_map expected_logits = map_logits(output.expected); + + if (position == penalties_position::after_filter) { + GGML_ASSERT(expected_logits.find(retained_history_token) != expected_logits.end()); + GGML_ASSERT(fabsf(expected_logits.at(retained_history_token) - raw_logits[retained_history_token]) > 1e-6f); + GGML_ASSERT(expected_logits.find(excluded_history_token) == expected_logits.end()); + GGML_ASSERT(std::find(output.actual.candidates.begin(), output.actual.candidates.end(), + excluded_history_token) == output.actual.candidates.end()); + } else { + const std::unordered_map unpenalized_logits = map_logits(top_k_data); + bool changed = false; + for (const auto & item : expected_logits) { + const auto it = unpenalized_logits.find(item.first); + if (it == unpenalized_logits.end() || fabsf(it->second - item.second) > 1e-6f) { + changed = true; + break; + } + } + GGML_ASSERT(changed); + } + + const char * name = position == penalties_position::before_filter + ? "penalties top-k" + : "top-k penalties"; + const sampler_comparison_stats stats = compare_sampler_outputs( + name, expected_logits, output.actual); + GGML_ASSERT(stats.n_masked == 0); + GGML_ASSERT(stats.n_mismatch == 0); +} + +static void compare_masking_penalties_logits( + const test_params & params, + const char * filter_name, + const sampler_init_fn & init_filter, + int32_t penalty_last_n, + float penalty_repeat, + float penalty_freq, + float penalty_present, + const std::string & prompt, + penalties_position position, + bool allow_extra_candidates, + bool add_history = true) { + const auto * vocab = llama_model_get_vocab(params.model.get()); + const std::vector raw_logits = decode_raw_logits(params, prompt); + const int n_vocab = (int) raw_logits.size(); + llama_sampler_ptr filter(init_filter()); + const std::vector filtered_data = apply_cpu_sampler(raw_logits, filter.get()); + GGML_ASSERT(!filtered_data.empty()); + GGML_ASSERT(filtered_data.size() < (size_t) n_vocab); + + const llama_token penalized_token = filtered_data[0].id; + std::unordered_set retained_tokens; + retained_tokens.reserve(filtered_data.size()); + for (const auto & data : filtered_data) { + retained_tokens.insert(data.id); + } + + llama_token masked_token = LLAMA_TOKEN_NULL; + for (llama_token token = 0; token < n_vocab; ++token) { + if (retained_tokens.find(token) == retained_tokens.end()) { + masked_token = token; + break; + } + } + GGML_ASSERT(masked_token != LLAMA_TOKEN_NULL); + + const auto add_samplers = [&](llama_sampler * chain) { + add_filter_and_penalties(chain, init_filter, n_vocab, + penalty_last_n, penalty_repeat, penalty_freq, penalty_present, position); + }; + auto accept_history = [&](llama_sampler * smpl) { + if (!add_history) { + return; + } + accept_prompt(smpl, vocab, prompt); + llama_sampler_accept(smpl, penalized_token); + llama_sampler_accept(smpl, penalized_token); + llama_sampler_accept(smpl, masked_token); + llama_sampler_accept(smpl, masked_token); + }; + + const sampler_comparison_output output = run_sampler_comparison( + params, prompt, raw_logits, add_samplers, accept_history); + + GGML_ASSERT(output.actual.logits.size() == (size_t) n_vocab); + + const std::unordered_map expected_logits = map_logits(output.expected); + + GGML_ASSERT(expected_logits.find(masked_token) == expected_logits.end()); + if (add_history) { + if (position == penalties_position::after_filter) { + GGML_ASSERT(expected_logits.find(penalized_token) != expected_logits.end()); + GGML_ASSERT(fabsf(expected_logits.at(penalized_token) - raw_logits[penalized_token]) > 1e-6f); + } else { + llama_sampler_ptr penalties(llama_sampler_init_penalties( + n_vocab, penalty_last_n, penalty_repeat, penalty_freq, penalty_present)); + accept_history(penalties.get()); + const std::unordered_map penalized_logits = + map_logits(apply_cpu_sampler(raw_logits, penalties.get())); + GGML_ASSERT(fabsf(penalized_logits.at(penalized_token) - raw_logits[penalized_token]) > 1e-6f); + } + } + + const std::string name = position == penalties_position::before_filter + ? "penalties " + std::string(filter_name) + : std::string(filter_name) + " penalties"; + const sampler_comparison_stats stats = compare_sampler_outputs( + name.c_str(), expected_logits, output.actual, allow_extra_candidates); + const float masked_logit = find_backend_logit(output.actual, masked_token); + GGML_ASSERT(stats.n_masked > 0); + GGML_ASSERT(std::isinf(masked_logit) && masked_logit < 0.0f); + GGML_ASSERT(stats.n_mismatch == 0); +} + +static void test_backend_penalties_sampling(const test_params & params) { + printf("Testing backend penalties (repeat + freq + presence)\n"); + compare_penalties_logits(params, 64, 1.1f, 0.5f, 0.25f, "Hello Hello world"); + + printf("Testing backend penalties with penalty_last_n > 64\n"); + const auto * vocab = llama_model_get_vocab(params.model.get()); + std::vector tokens(8); + int32_t n_tok = llama_tokenize(vocab, "a", 1, tokens.data(), (int32_t) tokens.size(), false, false); + if (n_tok < 0) { + tokens.resize(-n_tok); + n_tok = llama_tokenize(vocab, "a", 1, tokens.data(), (int32_t) tokens.size(), false, false); + } + GGML_ASSERT(n_tok > 0); + const llama_token tok = tokens[0]; + + compare_penalties_logits(params, 80, 1.15f, 0.1f, 0.05f, "a", [tok](llama_sampler * smpl) { + // accept_prompt already accepted BOS + one 'a'; fill the ring to n=80 + for (int i = 0; i < 78; ++i) { + llama_sampler_accept(smpl, tok); + } + }); + + printf("Testing backend penalties without filler entries\n"); + compare_penalties_logits(params, 64, 1.1f, 0.5f, 0.25f, "Hello", [](llama_sampler * smpl) { + for (llama_token token = 0; token < 64; ++token) { + llama_sampler_accept(smpl, token); + } + }); + + printf("Testing backend top-k followed by penalties\n"); + compare_top_k_penalties_logits(params, 8, 64, 1.1f, 0.5f, 0.25f, "Hello", + penalties_position::after_filter); + + printf("Testing backend penalties followed by top-k\n"); + compare_top_k_penalties_logits(params, 8, 64, 1.1f, 0.5f, 0.25f, "Hello", + penalties_position::before_filter); + + printf("Testing backend top-p followed by penalties\n"); + compare_masking_penalties_logits(params, "top-p", []() { + return llama_sampler_init_top_p(0.9f, 0); + }, 64, 1.1f, 0.5f, 0.25f, "Hello", penalties_position::after_filter, true); + + printf("Testing backend top-p followed by penalties with a large history window\n"); + compare_masking_penalties_logits(params, "top-p large-window", []() { + return llama_sampler_init_top_p(0.9f, 0); + }, 4096, 1.1f, 0.5f, 0.25f, "Hello", penalties_position::after_filter, true); + + printf("Testing backend penalties followed by top-p\n"); + compare_masking_penalties_logits(params, "top-p", []() { + return llama_sampler_init_top_p(0.9f, 0); + }, 64, 1.1f, 0.5f, 0.25f, "Hello", penalties_position::before_filter, true); + + printf("Testing backend min-p followed by penalties\n"); + compare_masking_penalties_logits(params, "min-p", []() { + return llama_sampler_init_min_p(0.1f, 0); + }, 64, 1.1f, 0.5f, 0.25f, "Hello", penalties_position::after_filter, false); + + printf("Testing backend penalties followed by min-p\n"); + compare_masking_penalties_logits(params, "min-p", []() { + return llama_sampler_init_min_p(0.1f, 0); + }, 64, 1.1f, 0.5f, 0.25f, "Hello", penalties_position::before_filter, false); + + printf("Testing backend top-p followed by penalties with empty history\n"); + compare_masking_penalties_logits(params, "top-p empty", []() { + return llama_sampler_init_top_p(0.9f, 0); + }, 64, 1.1f, 0.5f, 0.25f, "Hello", penalties_position::after_filter, true, false); + + printf("Testing backend top-p followed by individual penalties\n"); + compare_masking_penalties_logits(params, "top-p repeat", []() { + return llama_sampler_init_top_p(0.9f, 0); + }, 64, 1.1f, 0.0f, 0.0f, "Hello", penalties_position::after_filter, true); + compare_masking_penalties_logits(params, "top-p frequency", []() { + return llama_sampler_init_top_p(0.9f, 0); + }, 64, 1.0f, 0.5f, 0.0f, "Hello", penalties_position::after_filter, true); + compare_masking_penalties_logits(params, "top-p presence", []() { + return llama_sampler_init_top_p(0.9f, 0); + }, 64, 1.0f, 0.0f, 0.25f, "Hello", penalties_position::after_filter, true); + + printf("Testing backend penalty parameter values\n"); + test_penalty_parameter_values(params); + + printf("backend penalties sampling test PASSED\n"); +} + // This test verifies that it is possible to have two different backend samplers, // one that uses the backend dist sampler, and another that uses CPU dist sampler. static void test_backend_mixed_sampling(const test_params & params) { @@ -1014,6 +1575,7 @@ struct backend_test_case { static const backend_test_case BACKEND_TESTS[] = { { "greedy", test_backend_greedy_sampling, true }, { "logit_bias", test_backend_logit_bias_sampling, true }, + { "penalties", test_backend_penalties_sampling, true }, { "temp", test_backend_temp_sampling, true }, { "temp_ext", test_backend_temp_ext_sampling, true }, { "top_k", test_backend_top_k_sampling, true }, diff --git a/tests/test-chat-peg-parser.cpp b/tests/test-chat-peg-parser.cpp index 908b13fd0ca7..3ab7a67b6a82 100644 --- a/tests/test-chat-peg-parser.cpp +++ b/tests/test-chat-peg-parser.cpp @@ -8,6 +8,7 @@ #include #include +#include #include #include "nlohmann/json.hpp" @@ -21,6 +22,7 @@ static void test_example_qwen3_non_coder(testing & t); static void test_command7_parser_compare(testing & t); static void test_prefix_tool_names(testing & t); static void test_tagged_peg_parser(testing & t); +static void test_permute(testing & t); int main(int argc, char * argv[]) { testing t(std::cout); @@ -39,6 +41,7 @@ int main(int argc, char * argv[]) { t.test("comparison", test_command7_parser_compare); t.test("prefix tool names", test_prefix_tool_names); t.test("tagged peg parser", test_tagged_peg_parser); + t.test("permute", test_permute); return t.summary(); } @@ -981,3 +984,103 @@ static void test_tagged_peg_parser(testing & t) { t.assert_equal("fun_post should be '>'", ">", result.tags["fun_post"]); }); } + +static void test_permute(testing & t) { + auto accepts = [](const common_peg_arena & parser, const std::string & input) { + common_peg_parse_context ctx(input); + return parser.parse(ctx).success(); + }; + + auto gbnf_of = [](const common_peg_arena & parser) { + return build_grammar([&](const common_grammar_builder & builder) { parser.build_grammar(builder); }); + }; + + auto assert_gbnf_equal = [](testing & t, const std::string & expected, const std::string & actual) { + static const std::regex leading_ws_re = std::regex(R"((^|\n)\s+)"); + t.assert_equal("gbnf are equal", std::regex_replace(expected, leading_ws_re, "$1"), actual); + }; + + auto count_rules = [](const std::string & gbnf, const std::string & prefix) { + size_t count = 0; + for (const auto & line : string_split(gbnf, '\n')) { + if (line.rfind(prefix, 0) == 0) { + count++; + } + } + return count; + }; + + t.test("accepts every ordering", [&](testing & t) { + auto parser = build_chat_peg_parser([](common_chat_peg_builder & p) { + return p.permute("abc", { p.literal("a"), p.literal("b"), p.literal("c") }) + p.end(); + }); + + for (const std::string input : { "abc", "acb", "bac", "bca", "cab", "cba" }) { + t.assert_true("accepts " + input, accepts(parser, input)); + } + }); + + t.test("single element", [&](testing & t) { + auto parser = build_chat_peg_parser([](common_chat_peg_builder & p) { + return p.permute("a", { p.literal("a") }) + p.end(); + }); + + t.assert_true("accepts a", accepts(parser, "a")); + t.assert_true("rejects aa", !accepts(parser, "aa")); + }); + + t.test("grammar left-factorizes shared tails", [&](testing & t) { + auto parser = build_chat_peg_parser([](common_chat_peg_builder & p) { + return p.permute("abc", { p.literal("a"), p.literal("b"), p.literal("c") }) + p.end(); + }); + + // Every rule is one remaining subset, keyed by bitmask: abc-3 is {a,b}, abc-7 is {a,b,c}. + // Each subset is emitted once and shared by every branch that leads into it. + assert_gbnf_equal(t, R"""( + abc-1 ::= "a" + abc-2 ::= "b" + abc-3 ::= "a" abc-2 | "b" abc-1 + abc-4 ::= "c" + abc-5 ::= "a" abc-4 | "c" abc-1 + abc-6 ::= "b" abc-4 | "c" abc-2 + abc-7 ::= "a" abc-6 | "b" abc-5 | "c" abc-3 + root ::= abc-7 + space ::= | " " | "\n"{1,2} [ \t]{0,20} + )""", gbnf_of(parser)); + }); + + t.test("grammar emits one rule per remaining subset", [&](testing & t) { + auto parser = build_chat_peg_parser([](common_chat_peg_builder & p) { + return p.permute("abcd", { p.literal("a"), p.literal("b"), p.literal("c"), p.literal("d") }) + p.end(); + }); + + // 2^4 - 1 non-empty subsets, one rule each - not the 4! = 24 orderings. + t.assert_equal("permute rule count", 15u, count_rules(gbnf_of(parser), "abcd-")); + }); + + t.test("grammar emits no rules for a single element", [&](testing & t) { + auto parser = build_chat_peg_parser([](common_chat_peg_builder & p) { + return p.permute("a", { p.literal("a") }) + p.end(); + }); + + assert_gbnf_equal(t, R"""( + root ::= "a" + space ::= | " " | "\n"{1,2} [ \t]{0,20} + )""", gbnf_of(parser)); + }); + + t.test("grammar falls back to the given order when too large", [&](testing & t) { + auto parser = build_chat_peg_parser([](common_chat_peg_builder & p) { + std::vector parsers; + for (size_t i = 0; i <= COMMON_CHAT_MAX_PERMUTE; i++) { + parsers.push_back(p.literal(std::string(1, (char) ('a' + i)))); + } + return p.permute("big", parsers) + p.end(); + }); + + assert_gbnf_equal(t, R"""( + root ::= "a" "b" "c" "d" "e" "f" "g" + space ::= | " " | "\n"{1,2} [ \t]{0,20} + )""", gbnf_of(parser)); + }); +} diff --git a/tests/test-chat.cpp b/tests/test-chat.cpp index 01b07953a627..f54a58f9b67c 100644 --- a/tests/test-chat.cpp +++ b/tests/test-chat.cpp @@ -2278,46 +2278,39 @@ static void test_template_output_peg_parsers(bool detailed_debug) { .expect_content(R"({"amount": 123.45, "date": "2025-12-03"})") .run(); - // tool call segment in reasoning + // a tool call ends the prefilled thinking block, with or without a closing tst.test( - "Let's call a tool: \n" - "\n" - "\n" - "def hello():\n" - " print(\"Not the real call!\")\n" - "\n" - "hello()\n" + "\n" + "\n" + "\n" + "pwd\n" "\n" "\n" - "\n\n\n" + "") + .enable_thinking(true) + .reasoning_format(COMMON_REASONING_FORMAT_AUTO) + .tools({ run_in_terminal_tool }) + .expect_tool_calls({ + { "run_in_terminal", R"({"command": "pwd"})", {} }, + }) + .run(); + + // ...including after the model has thought about it + tst.test( + "Need to inspect the current directory.\n" "\n" - "\n" - "\n" - "def hello():\n" - " print(\"Hello, world!\")\n" - "\n" - "hello()\n" + "\n" + "\n" + "pwd\n" "\n" "\n" "") .enable_thinking(true) .reasoning_format(COMMON_REASONING_FORMAT_AUTO) - .tools({ - python_tool - }) - .expect_reasoning( - "Let's call a tool: \n" - "\n" - "\n" - "def hello():\n" - " print(\"Not the real call!\")\n" - "\n" - "hello()\n" - "\n" - "\n" - "") + .tools({ run_in_terminal_tool }) + .expect_reasoning("Need to inspect the current directory.") .expect_tool_calls({ - { "python", "{\"code\": \"def hello():\\n print(\\\"Hello, world!\\\")\\n\\nhello()\"}", {} }, + { "run_in_terminal", R"({"command": "pwd"})", {} }, }) .run(); @@ -2461,17 +2454,6 @@ static void test_template_output_peg_parsers(bool detailed_debug) { }) .run(); - tst.test( - "I might call later, but I am still thinking.\n" - "\n\n" - "Final answer without tools.") - .reasoning_format(COMMON_REASONING_FORMAT_AUTO) - .enable_thinking(true) - .tools({ run_in_terminal_tool }) - .expect_reasoning("I might call later, but I am still thinking.") - .expect_content("Final answer without tools.") - .run(); - // Continuation tests tst.test("world!\nWhat's up?") .reasoning_format(COMMON_REASONING_FORMAT_AUTO) @@ -2776,49 +2758,6 @@ static void test_template_output_peg_parsers(bool detailed_debug) { .expect_content(R"({"amount": 123.45, "date": "2025-12-03"})") .run(); - // tool call segment in reasoning - tst.test( - "Let's call a tool: \n" - "\n" - "\n" - "def hello():\n" - " print(\"Not the real call!\")\n" - "\n" - "hello()\n" - "\n" - "\n" - "\n\n" - "\n" - "\n" - "\n" - "def hello():\n" - " print(\"Hello, world!\")\n" - "\n" - "hello()\n" - "\n" - "\n" - "\n" - ) - .enable_thinking(true) - .reasoning_format(COMMON_REASONING_FORMAT_AUTO) - .tools({ - python_tool - }) - .expect_reasoning("Let's call a tool: \n" - "\n" - "\n" - "def hello():\n" - " print(\"Not the real call!\")\n" - "\n" - "hello()\n" - "\n" - "\n" - "\n") - .expect_tool_calls({ - { "python", "{\"code\": \"def hello():\\n print(\\\"Hello, world!\\\")\\n\\nhello()\"}", {} }, - }) - .run(); - // Continuation tests tst.test("world!\nWhat's up?") .reasoning_format(COMMON_REASONING_FORMAT_AUTO) @@ -3572,6 +3511,61 @@ static void test_template_output_peg_parsers(bool detailed_debug) { .expect_reconstruction() .run(); + // Some models skip the opening and go straight to + tst.test( + "\n" + "\n" + "1\n" + "\n" + "\n" + "") + .tools({ special_function_tool }) + .expect(message_assist_call) + .run(); + + tst.test( + "Let me call it.\n" + "\n" + "\n" + "1\n" + "\n" + "\n" + "") + .tools({ special_function_tool }) + .expect_content("Let me call it.\n") + .expect_tool_calls({ + { "special_function", R"({"arg1": 1})", {} }, + }) + .run(); + + // Only the first call may omit it, the rest keep the \n separator + tst.test( + "\n" + "\n" + "1\n" + "\n" + "\n" + "\n" + "\n" + "\n" + "\n" + "1\n" + "\n" + "\n" + "2\n" + "\n" + "\n" + "") + .parallel_tool_calls(true) + .tools({ + special_function_tool, special_function_tool_with_optional_param + }) + .expect_tool_calls({ + { "special_function", R"({"arg1": 1})", {} }, + { "special_function_with_opt", R"({"arg1": 1, "arg2": 2})", {} }, + }) + .run(); + tst.test( "\n" "\n" @@ -3680,6 +3674,37 @@ static void test_template_output_peg_parsers(bool detailed_debug) { .expect_reconstruction() .run(); + // Test flexible required argument ordering (required args still come first, in any order) + tst.test( + "\n" + "\n" + "\n#include\n\n" + "\nfoo.c\n\n" + "\n#iclunde\n\n" + "\n" + "") + .tools({ edit_tool }) + .expect_tool_calls({ + { "edit", R"({"newString": "#include", "filename": "foo.c", "oldString": "#iclunde"})", {} }, + }) + .expect_reconstruction() + .run(); + + tst.test( + "\n" + "\n" + "\n42\n\n" + "\nhello\n\n" + "\n200\n\n" + "\n" + "") + .tools({ tool_2req_4opt }) + .expect_tool_calls({ + { "tool_2req_4opt", R"({"req2": 42, "req1": "hello", "opt2": 200})", {} }, + }) + .expect_reconstruction() + .run(); + // Test flexible optional argument ordering (2 required + 4 optional, reversed optional order) tst.test( "\n" @@ -3962,6 +3987,7 @@ static void test_template_output_peg_parsers(bool detailed_debug) { .expect_tool_calls({ { "special_function", R"({"arg1": 1})", {} }, }) + .expect_reconstruction() .run(); // Tool call with negative number @@ -4187,6 +4213,7 @@ static void test_template_output_peg_parsers(bool detailed_debug) { .expect_tool_calls({ { "special_function", R"({"arg1": 1})", {} }, }) + .expect_reconstruction() .run(); // Tool call with multiple params (mixed types) @@ -4227,6 +4254,38 @@ static void test_template_output_peg_parsers(bool detailed_debug) { .expect_reasoning("I'm thinking") .expect_content("Hello, world!\nWhat's up?") .run(); + + tst.test( + "Let me check the time\n\n" + "<｜DSML｜tool_calls>\n" + "<｜DSML｜invoke name=\"get_time\">\n" + "<｜DSML｜parameter name=\"city\" string=\"true\">Tokyo\n" + "\n" + "") // no after the TC close because the grammar will immediately constrain it to end + .enable_thinking(true) + .reasoning_format(COMMON_REASONING_FORMAT_DEEPSEEK) + .tools({ get_time_tool }) + .expect_reasoning("Let me check the time") + .expect_tool_calls({ { "get_time", R"({"city": "Tokyo"})", {} } }) + .run(); + } + + { + // The DSML separator belongs to the tool call block, not assistant content. + auto tst = peg_tester("models/templates/deepseek-ai-DeepSeek-V4-Flash-0731.jinja", detailed_debug); + tst.test( + "\n\n" + "<｜DSML｜tool_calls>\n" + "<｜DSML｜invoke name=\"special_function\">\n" + "<｜DSML｜parameter name=\"arg1\" string=\"false\">1\n" + "\n" + "") + .enable_thinking(false) + .reasoning_format(COMMON_REASONING_FORMAT_DEEPSEEK) + .tools({ special_function_tool }) + .expect(message_assist_call) + .expect_reconstruction() + .run(); } // GLM-4.6 tests - format: function_name\n...\n...\n @@ -6320,6 +6379,7 @@ static void test_template_generation_prompt() { std::vector messages; bool add_generation_prompt = true; common_chat_continuation continue_final_message = COMMON_CHAT_CONTINUATION_NONE; + bool enable_thinking = true; }; auto basic = [&]() { @@ -6351,6 +6411,7 @@ static void test_template_generation_prompt() { inputs.messages = opts.messages; inputs.add_generation_prompt = opts.add_generation_prompt; inputs.continue_final_message = opts.continue_final_message; + inputs.enable_thinking = opts.enable_thinking; auto params = common_chat_templates_apply(tmpls.get(), inputs); @@ -6449,6 +6510,156 @@ static void test_template_generation_prompt() { check(tmpls, continuation_reasoning(), "<｜Assistant｜>I'm"); } + const std::string deepseek_v4_reasoning_effort_max = "Reasoning Effort: Absolute maximum"; + const std::string deepseek_v4_flash_0731_reasoning_effort_max = "Reasoning Effort: Beyond maximum"; + + { + auto tmpls = read_templates("models/templates/deepseek-ai-DeepSeek-V4.jinja"); + check(tmpls, basic(), "<｜Assistant｜>"); + check(tmpls, continuation_content(), "<｜Assistant｜>I'm thinkingHello, "); + check(tmpls, continuation_reasoning(), "<｜Assistant｜>I'm"); + + auto continuation_content_no_thinking = continuation_content(); + continuation_content_no_thinking.messages = { system_msg, message_user, simple_assist_msg("Hello, ") }; + continuation_content_no_thinking.enable_thinking = false; + check(tmpls, continuation_content_no_thinking, "<｜Assistant｜>Hello, "); + + common_chat_templates_inputs max_inputs; + max_inputs.messages = { system_msg, message_user }; + max_inputs.chat_template_kwargs["reasoning_effort"] = R"("max")"; + auto max_params = common_chat_templates_apply(tmpls.get(), max_inputs); + assert_contains(max_params.prompt, deepseek_v4_reasoning_effort_max); + + auto high_inputs = max_inputs; + high_inputs.chat_template_kwargs["reasoning_effort"] = R"("high")"; + auto high_params = common_chat_templates_apply(tmpls.get(), high_inputs); + assert_not_contains(high_params.prompt, deepseek_v4_reasoning_effort_max); + + auto low_inputs = max_inputs; + low_inputs.chat_template_kwargs["reasoning_effort"] = R"("low")"; + auto low_params = common_chat_templates_apply(tmpls.get(), low_inputs); + assert_not_contains(low_params.prompt, deepseek_v4_reasoning_effort_max); + + common_chat_templates_inputs default_effort_inputs; + default_effort_inputs.messages = { system_msg, message_user }; + auto default_effort_params = common_chat_templates_apply(tmpls.get(), default_effort_inputs); + assert_not_contains(default_effort_params.prompt, deepseek_v4_reasoning_effort_max); + + auto non_thinking_max_inputs = max_inputs; + non_thinking_max_inputs.enable_thinking = false; + auto non_thinking_max_params = common_chat_templates_apply(tmpls.get(), non_thinking_max_inputs); + assert_not_contains(non_thinking_max_params.prompt, deepseek_v4_reasoning_effort_max); + + common_chat_templates_inputs response_format_inputs; + response_format_inputs.messages = { system_msg, message_user }; + response_format_inputs.tools = { get_time_tool }; + response_format_inputs.json_schema = + R"({"type":"object","properties":{"answer":{"type":"string"}}})"; + auto response_format_params = common_chat_templates_apply(tmpls.get(), response_format_inputs); + const auto tools_pos = response_format_params.prompt.find("## Tools"); + const auto response_format_pos = response_format_params.prompt.find( + "## Response Format:\n\nYou MUST strictly adhere to the following schema to reply:\n"); + if (tools_pos == std::string::npos || response_format_pos == std::string::npos || tools_pos > response_format_pos) { + LOG_ERR("Expected response format after tools\nActual: %s\n", response_format_params.prompt.c_str()); + common_log_flush(common_log_main()); + throw std::runtime_error("Test failed"); + } + assert_contains(response_format_params.prompt, R"("answer": {"type": "string"})"); + + response_format_inputs.json_schema = "{}"; + auto json_object_params = common_chat_templates_apply(tmpls.get(), response_format_inputs); + assert_contains(json_object_params.prompt, + "## Response Format:\n\nYou MUST strictly adhere to the following schema to reply:\n{}"); + + common_chat_msg assistant_history; + assistant_history.role = "assistant"; + assistant_history.content = "Previous answer"; + assistant_history.reasoning_content = "Previous reasoning"; + + common_chat_msg user_followup; + user_followup.role = "user"; + user_followup.content = "Follow up"; + + common_chat_templates_inputs default_history_inputs; + default_history_inputs.messages = { message_user, assistant_history, user_followup }; + auto default_history_params = common_chat_templates_apply(tmpls.get(), default_history_inputs); + assert_contains(default_history_params.prompt, "<｜Assistant｜>Previous answer"); + + auto drop_thinking_inputs = default_history_inputs; + drop_thinking_inputs.chat_template_kwargs["drop_thinking"] = "false"; + auto drop_thinking_params = common_chat_templates_apply(tmpls.get(), drop_thinking_inputs); + assert_contains(drop_thinking_params.prompt, "<｜Assistant｜>Previous reasoningPrevious answer"); + + auto preserve_reasoning_inputs = default_history_inputs; + preserve_reasoning_inputs.chat_template_kwargs["preserve_reasoning"] = "true"; + auto preserve_reasoning_params = common_chat_templates_apply(tmpls.get(), preserve_reasoning_inputs); + assert_contains(preserve_reasoning_params.prompt, "<｜Assistant｜>Previous reasoningPrevious answer"); + assert_equals(true, common_chat_templates_get_caps(tmpls.get()).at("supports_preserve_reasoning")); + + auto no_preserve_reasoning_inputs = default_history_inputs; + no_preserve_reasoning_inputs.chat_template_kwargs["preserve_reasoning"] = "false"; + auto no_preserve_reasoning_params = common_chat_templates_apply(tmpls.get(), no_preserve_reasoning_inputs); + assert_contains(no_preserve_reasoning_params.prompt, "<｜Assistant｜>Previous answer"); + + common_chat_msg empty_tool_call = simple_assist_msg("", "", "empty_args", "{}"); + common_chat_templates_inputs empty_tool_inputs; + empty_tool_inputs.messages = { message_user, empty_tool_call }; + empty_tool_inputs.tools = { empty_args_tool }; + auto empty_tool_params = common_chat_templates_apply(tmpls.get(), empty_tool_inputs); + assert_contains(empty_tool_params.prompt, + "<｜DSML｜invoke name=\"empty_args\">\n\n"); + } + + { + auto tmpls = read_templates("models/templates/deepseek-ai-DeepSeek-V4-Flash-0731.jinja"); + check(tmpls, basic(), "<｜Assistant｜>"); + check(tmpls, continuation_content(), "<｜Assistant｜>I'm thinkingHello, "); + check(tmpls, continuation_reasoning(), "<｜Assistant｜>I'm"); + + auto continuation_content_no_thinking = continuation_content(); + continuation_content_no_thinking.messages = { system_msg, message_user, simple_assist_msg("Hello, ") }; + continuation_content_no_thinking.enable_thinking = false; + check(tmpls, continuation_content_no_thinking, "<｜Assistant｜>Hello, "); + + common_chat_templates_inputs high_inputs; + high_inputs.messages = { system_msg, message_user }; + high_inputs.chat_template_kwargs["reasoning_effort"] = R"("high")"; + auto high_params = common_chat_templates_apply(tmpls.get(), high_inputs); + assert_contains(high_params.prompt, deepseek_v4_reasoning_effort_max); + + auto max_inputs = high_inputs; + max_inputs.chat_template_kwargs["reasoning_effort"] = R"("max")"; + auto max_params = common_chat_templates_apply(tmpls.get(), max_inputs); + assert_contains(max_params.prompt, deepseek_v4_flash_0731_reasoning_effort_max); + + auto low_inputs = high_inputs; + low_inputs.chat_template_kwargs["reasoning_effort"] = R"("low")"; + auto low_params = common_chat_templates_apply(tmpls.get(), low_inputs); + assert_not_contains(low_params.prompt, deepseek_v4_reasoning_effort_max); + assert_not_contains(low_params.prompt, deepseek_v4_flash_0731_reasoning_effort_max); + + common_chat_templates_inputs default_effort_inputs; + default_effort_inputs.messages = { system_msg, message_user }; + auto default_effort_params = common_chat_templates_apply(tmpls.get(), default_effort_inputs); + assert_not_contains(default_effort_params.prompt, deepseek_v4_reasoning_effort_max); + assert_not_contains(default_effort_params.prompt, deepseek_v4_flash_0731_reasoning_effort_max); + + auto non_thinking_max_inputs = max_inputs; + non_thinking_max_inputs.enable_thinking = false; + auto non_thinking_max_params = common_chat_templates_apply(tmpls.get(), non_thinking_max_inputs); + assert_not_contains(non_thinking_max_params.prompt, deepseek_v4_flash_0731_reasoning_effort_max); + + common_chat_templates_inputs response_format_inputs; + response_format_inputs.messages = { system_msg, message_user }; + response_format_inputs.tools = { get_time_tool }; + response_format_inputs.json_schema = + R"({"type":"object","properties":{"answer":{"type":"string"}}})"; + auto response_format_params = common_chat_templates_apply(tmpls.get(), response_format_inputs); + assert_contains(response_format_params.prompt, + "## Response Format:\n\nYou MUST strictly adhere to the following schema to reply:\n"); + assert_contains(response_format_params.prompt, R"("answer": {"type": "string"})"); + } + { auto tmpls = read_templates("models/templates/openbmb-MiniCPM5-1B.jinja"); check(tmpls, basic(), "<|im_start|>assistant\n\n"); diff --git a/tests/test-llama-archs.cpp b/tests/test-llama-archs.cpp index a1ed2a76f879..1654f122a731 100644 --- a/tests/test-llama-archs.cpp +++ b/tests/test-llama-archs.cpp @@ -113,6 +113,8 @@ static gguf_context_ptr get_gguf_ctx(const llm_arch arch, const bool moe) { n_layer = 3; } else if (arch == LLM_ARCH_CHAMELEON) { n_vocab = 10240; + } else if (arch == LLM_ARCH_QWEN3TTS) { + n_vocab = 4096; // must be >= the hard-coded codec head size (3072) } const uint32_t n_embd_head = n_embd / n_head; @@ -430,7 +432,7 @@ static bool arch_supported(const llm_arch arch) { // FIXME: these hit scheduler/view-backed-output issues with WebGPU on CI. #ifdef GGML_USE_WEBGPU - if (arch == LLM_ARCH_DEEPSEEK32 || arch == LLM_ARCH_GLM_DSA) { + if (arch == LLM_ARCH_DEEPSEEK32 || arch == LLM_ARCH_GLM_DSA || arch == LLM_ARCH_MINIMAX_M3) { return false; } #endif // GGML_USE_WEBGPU diff --git a/tests/test-model-resolution.cpp b/tests/test-model-resolution.cpp new file mode 100644 index 000000000000..a96e40bb2bf8 --- /dev/null +++ b/tests/test-model-resolution.cpp @@ -0,0 +1,506 @@ +// tests the HF model resolution and the model handler assembly end-to-end on +// synthetic repo listings: a local httplib server bound to the loopback +// serves hardcoded HF API responses, so the real client, hf_cache, resolution +// and CLI parsing run against them without external network access + +#include "arg.h" +#include "common.h" +#include "download.h" +#include "http.h" +#include "log.h" + +#include + +#include +#include +#include +#include +#include +#include +#include +#include + +// the case and reordering being checked, printed with every failure +static std::string g_context; + +// independent of NDEBUG, so the checks stay alive in Release builds +#define REQUIRE(x) do { \ + if (!(x)) { \ + fprintf(stderr, "%s:%d: [%s] REQUIRE(%s) failed\n", \ + __FILE__, __LINE__, g_context.c_str(), #x); \ + std::abort(); \ + } \ +} while (0) + +#define REQUIRE_EQ(actual, expected) do { \ + if (!((actual) == (expected))) { \ + fprintf(stderr, "%s:%d: [%s] REQUIRE_EQ(%s, %s) failed\n actual: '%s'\n expected: '%s'\n", \ + __FILE__, __LINE__, g_context.c_str(), #actual, #expected, \ + std::string(actual).c_str(), std::string(expected).c_str()); \ + std::abort(); \ + } \ +} while (0) + +// +// synthetic repos keyed by repo id, served over the loopback by a real +// httplib server, so the tested code runs its own client and transport +// + +static std::map> g_repos; + +static const char * COMMIT = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"; + +// the server lives in main, so its destructor runs before the static teardown +// tears down the winsock state httplib brings in +static void serve_repos(httplib::Server & server) { + server.Get(R"(/api/models/(.+)/refs)", [](const httplib::Request & req, httplib::Response & res) { + if (g_repos.count(req.matches[1])) { + res.set_content(nlohmann::json{{"branches", {{{"name", "main"}, {"targetCommit", COMMIT}}}}}.dump(), + "application/json"); + } else { + res.status = 404; + } + }); + server.Get(R"(/api/models/(.+)/tree/.+)", [](const httplib::Request & req, httplib::Response & res) { + if (!g_repos.count(req.matches[1])) { + res.status = 404; + return; + } + auto files = nlohmann::json::array(); + size_t i = 0; + for (const auto & p : g_repos[req.matches[1]]) { + char oid[41]; + snprintf(oid, sizeof(oid), "%040lx", (unsigned long) ++i); + files.push_back({{"type", "file"}, {"path", p}, {"size", 1}, {"oid", oid}}); + } + res.set_content(files.dump(), "application/json"); + }); +} + +static common_params_model model_ref(const std::string & hf_repo, const std::string & hf_file = "") { + common_params_model m; + m.hf_repo = hf_repo; + m.hf_file = hf_file; + return m; +} + +// the model cache is isolated under a temporary directory named after the +// loopback port, so concurrent runs on a shared machine keep their own, and +// the local path the handler wires for a file is snapshots// +static std::filesystem::path cache_dir; + +static std::string cached(std::string repo_id, const std::string & path) { + string_replace_all(repo_id, "/", "--"); + return (cache_dir / ("models--" + repo_id) / "snapshots" / COMMIT / path).string(); +} + +// +// fixtures mimicking real repo layouts +// + +// flat layout in the style of ggml-org/gemma-4-31B-it-GGUF +static const std::vector flat = { + "README.md", + "model-BF16.gguf", + "model-Q4_K_M.gguf", + "model-Q8_0.gguf", + "mmproj-model-BF16.gguf", + "mmproj-model-Q8_0.gguf", + "mtp-model-BF16.gguf", + "mtp-model-Q4_0.gguf", + "mtp-model-Q8_0.gguf", + "dflash-model-BF16.gguf", + "dflash-model-Q8_0.gguf", +}; + +// quants in subdirectories with sharded files and root sidecars, +// in the style of stepfun-ai/Step-3.7-Flash-GGUF +static const std::vector subdir = { + "mmproj-model-f16.gguf", + "model-mtp-BF16.gguf", + "model-mtp-Q8_0.gguf", + "Q3_K_M/model-Q3_K_M-00001-of-00003.gguf", + "Q3_K_M/model-Q3_K_M-00002-of-00003.gguf", + "Q3_K_M/model-Q3_K_M-00003-of-00003.gguf", + "Q8_0/model-Q8_0-00001-of-00002.gguf", + "Q8_0/model-Q8_0-00002-of-00002.gguf", +}; + +// sidecar quants exist where the full model quant does not, +// in the style of ggml-org/Qwen3.6-27B-GGUF +static const std::vector hole = { + "model-BF16.gguf", + "model-Q4_K_M.gguf", + "model-Q8_0.gguf", + "mtp-model-BF16.gguf", + "mtp-model-Q4_0.gguf", + "mtp-model-Q8_0.gguf", + "dflash-model-BF16.gguf", + "dflash-model-Q8_0.gguf", +}; + +// unsloth-style naming with UD quants and a suffix MTP file +static const std::vector unsloth = { + "model-UD-Q8_K_XL.gguf", + "mmproj-BF16.gguf", + "model-MTP-BF16.gguf", +}; + +// bartowski-style vendor prefix and mradermacher-style dot quant +static const std::vector vendors = { + "TheDrummer_Model-24B-v4.1-Q8_0.gguf", + "BlackSheep-24B.Q8_0.gguf", +}; + +// every speculative sidecar type at the same quant +static const std::vector quad = { + "model-Q8_0.gguf", + "mtp-model-Q8_0.gguf", + "dflash-model-Q8_0.gguf", + "eagle3-model-Q8_0.gguf", + "dspark-model-Q8_0.gguf", +}; + +static const std::vector dflash_only = { + "model-Q8_0.gguf", + "dflash-model-Q8_0.gguf", +}; + +static const std::vector eagle3_only = { + "model-Q8_0.gguf", + "eagle3-model-Q8_0.gguf", +}; + +// a single full quant with dspark sidecars at other quants, +// in the style of ggml-org/DeepSeek-V4-Flash-0731-GGUF +static const std::vector spark = { + "README.md", + "model-MXFP4.gguf", + "dspark-model-BF16.gguf", + "dspark-model-MXFP4.gguf", +}; + +// dspark outranks dflash in the type auto-selection +static const std::vector dspark_dflash = { + "model-Q8_0.gguf", + "dflash-model-Q8_0.gguf", + "dspark-model-Q8_0.gguf", +}; + +// +// table-driven plan resolution through the real entry point, +// each case replayed on multiple deterministic reorderings of the listing, +// except the cases whose pick legitimately depends on the listing order +// + +struct plan_case { + const char * name; + const std::vector & files; + const char * hf_repo; + const char * hf_file; + bool sidecars; // request mmproj + mtp + dflash + eagle3 + dspark + bool order_dependent; // the expected pick depends on the listing order + const char * primary; + std::vector model_files; + const char * mmproj; + const char * mtp; + const char * dflash; + const char * eagle3; + const char * dspark; +}; + +static const plan_case plan_cases[] = { + // exact tag picks the matching primary, sidecars follow the tag + {"flat exact tag", flat, "test/repo:Q8_0", "", true, false, + "model-Q8_0.gguf", {"model-Q8_0.gguf"}, + "mmproj-model-Q8_0.gguf", "mtp-model-Q8_0.gguf", "dflash-model-Q8_0.gguf", "", ""}, + + // no tag falls back to the default quant preference + {"flat default", flat, "test/repo", "", false, false, + "model-Q4_K_M.gguf", {"model-Q4_K_M.gguf"}, + "", "", "", "", ""}, + + // no tag and no default match falls back to the first model in the listing + {"unsloth fallback", unsloth, "test/repo", "", true, true, + "model-UD-Q8_K_XL.gguf", {"model-UD-Q8_K_XL.gguf"}, + "mmproj-BF16.gguf", "", "", "", ""}, + + // explicit hf_file picks that exact file + {"flat hf_file", flat, "test/repo", "model-BF16.gguf", false, false, + "model-BF16.gguf", {"model-BF16.gguf"}, + "", "", "", "", ""}, + + // missing hf_file resolves nothing + {"flat missing hf_file", flat, "test/repo", "nope.gguf", false, false, + "", {}, + "", "", "", "", ""}, + + // a sharded primary brings all its parts, a subdir primary finds the root sidecar + {"subdir shards", subdir, "test/repo:Q3_K_M", "", true, false, + "Q3_K_M/model-Q3_K_M-00001-of-00003.gguf", + {"Q3_K_M/model-Q3_K_M-00001-of-00003.gguf", + "Q3_K_M/model-Q3_K_M-00002-of-00003.gguf", + "Q3_K_M/model-Q3_K_M-00003-of-00003.gguf"}, + "mmproj-model-f16.gguf", "model-mtp-Q8_0.gguf", "", "", ""}, + + // a tag with no matching full model still resolves the requested sidecars + {"hole tag sidecar", hole, "test/repo:Q4_0", "", true, false, + "", {}, + "", "mtp-model-Q4_0.gguf", "dflash-model-Q8_0.gguf", "", ""}, + + // the same tag without a requested sidecar resolves nothing + {"hole tag alone", hole, "test/repo:Q4_0", "", false, false, + "", {}, + "", "", "", "", ""}, + + // no tag anchors the sidecars on the primary quant + {"hole default anchor", hole, "test/repo", "", true, false, + "model-Q4_K_M.gguf", {"model-Q4_K_M.gguf"}, + "", "mtp-model-Q4_0.gguf", "dflash-model-Q8_0.gguf", "", ""}, + + // the mtp- keyword is case sensitive, a suffix -MTP file is not discovered + {"unsloth suffix mtp", unsloth, "test/repo:Q8_K_XL", "", true, false, + "model-UD-Q8_K_XL.gguf", {"model-UD-Q8_K_XL.gguf"}, + "mmproj-BF16.gguf", "", "", "", ""}, + + // vendor prefixes and the dot quant convention both match the tag, + // first match wins between two files at the same quant + {"vendor prefix", vendors, "test/repo:Q8_0", "", false, true, + "TheDrummer_Model-24B-v4.1-Q8_0.gguf", {"TheDrummer_Model-24B-v4.1-Q8_0.gguf"}, + "", "", "", "", ""}, + + // every sidecar type resolves at the tag + {"quad exact tag", quad, "test/repo:Q8_0", "", true, false, + "model-Q8_0.gguf", {"model-Q8_0.gguf"}, + "", "mtp-model-Q8_0.gguf", "dflash-model-Q8_0.gguf", "eagle3-model-Q8_0.gguf", "dspark-model-Q8_0.gguf"}, + + // no tag anchors the dspark sidecar on the only full quant + {"spark default anchor", spark, "test/repo", "", true, false, + "model-MXFP4.gguf", {"model-MXFP4.gguf"}, + "", "", "", "", "dspark-model-MXFP4.gguf"}, + + // a tag with no matching full model still resolves the exact dspark sidecar + {"spark tag sidecar", spark, "test/repo:BF16", "", true, false, + "", {}, + "", "", "", "", "dspark-model-BF16.gguf"}, +}; + +static void check_plan(const plan_case & c) { + common_download_opts opts; + opts.download_mmproj = c.sidecars; + opts.download_mtp = c.sidecars; + opts.download_dflash = c.sidecars; + opts.download_eagle3 = c.sidecars; + opts.download_dspark = c.sidecars; + + auto plan = common_download_get_hf_plan(model_ref(c.hf_repo, c.hf_file), opts); + + REQUIRE_EQ(plan.primary.path, c.primary); + REQUIRE_EQ(plan.mmproj.path, c.mmproj); + REQUIRE_EQ(plan.mtp.path, c.mtp); + REQUIRE_EQ(plan.dflash.path, c.dflash); + REQUIRE_EQ(plan.eagle3.path, c.eagle3); + REQUIRE_EQ(plan.dspark.path, c.dspark); + + // exact shard set, order insensitive; the primary must be the first split + std::vector actual; + for (const auto & f : plan.model_files) { + actual.push_back(f.path); + } + std::sort(actual.begin(), actual.end()); + auto expected = c.model_files; + std::sort(expected.begin(), expected.end()); + REQUIRE(actual == expected); + if (!expected.empty()) { + REQUIRE(plan.primary.path == expected.front()); + } +} + +static void test_plan_resolution() { + printf("test-model-resolution: plan resolution on %zu cases\n", sizeof(plan_cases) / sizeof(plan_cases[0])); + + for (const auto & c : plan_cases) { + printf(" %s\n", c.name); + // invariant: the resolution is insensitive to the listing order + for (size_t rot = 0; rot < c.files.size(); ++rot) { + if (c.order_dependent && rot > 0) { + continue; + } + g_context = std::string(c.name) + ", reordering " + std::to_string(rot); + auto files = c.files; + std::rotate(files.begin(), files.begin() + rot, files.end()); + if (rot % 2 == 1) { + std::reverse(files.begin(), files.end()); + } + g_repos["test/repo"] = files; + check_plan(c); + } + } + g_repos.clear(); +} + +// +// end-to-end assembly: real CLI parsing, real handler init resolving over the +// loopback, downloads skipped by flipping offline before apply +// + +static void assemble(std::vector argv, common_params & params) { + std::vector cargv; + g_context.clear(); + for (auto & a : argv) { + g_context += g_context.empty() ? a : " " + a; + cargv.push_back(a.data()); + } + bool ok = common_params_parse((int) cargv.size(), cargv.data(), params, LLAMA_EXAMPLE_SERVER); + REQUIRE(ok); + + auto handler = common_models_handler_init(params, LLAMA_EXAMPLE_SERVER); + + // skip the network execution, on_done still wires the params + params.offline = true; + common_models_handler_apply(handler, params); +} + +static void test_task_assembly() { + printf("test-model-resolution: end-to-end assembly\n"); + + g_repos["test/main"] = flat; + g_repos["test/hole"] = hole; + g_repos["test/quad"] = quad; + g_repos["test/dflash"] = dflash_only; + g_repos["test/eagle3"] = eagle3_only; + g_repos["test/spark"] = spark; + g_repos["test/pair"] = dspark_dflash; + g_repos["test/small"] = {"draft-model-Q4_K_M.gguf"}; + g_repos["test/preset"] = {"preset.ini", "model-Q8_0.gguf"}; + + { + // plain -hf wires the model and its mmproj, nothing speculative + common_params params; + assemble({"server", "-hf", "test/main:Q8_0"}, params); + REQUIRE_EQ(params.model.path, cached("test/main", "model-Q8_0.gguf")); + REQUIRE_EQ(params.mmproj.path, cached("test/main", "mmproj-model-Q8_0.gguf")); + REQUIRE(params.speculative.draft.mparams.path.empty()); + } + { + // --no-mmproj disables the mmproj discovery + common_params params; + assemble({"server", "-hf", "test/main:Q8_0", "--no-mmproj"}, params); + REQUIRE(params.mmproj.path.empty()); + } + { + // an explicit --mmproj wins over the discovery + common_params params; + assemble({"server", "-hf", "test/main:Q8_0", "--mmproj", "/local/mmproj.gguf"}, params); + REQUIRE(params.mmproj.path == "/local/mmproj.gguf"); + } + { + // -hf with a spec type wires the sidecar of the main repo as fallback draft + common_params params; + assemble({"server", "-hf", "test/main:Q8_0", "--spec-type", "draft-mtp"}, params); + REQUIRE_EQ(params.speculative.draft.mparams.path, cached("test/main", "mtp-model-Q8_0.gguf")); + } + { + // -hfd with a spec type wires the draft repo sidecar at its tag, + // not its full model, and suppresses the main repo fallback + common_params params; + assemble({"server", "-hf", "test/hole:Q8_0", "-hfd", "test/hole:Q4_0", "--spec-type", "draft-mtp"}, params); + REQUIRE_EQ(params.speculative.draft.mparams.path, cached("test/hole", "mtp-model-Q4_0.gguf")); + } + { + // an explicit -md file wins over the sidecar resolution + common_params params; + assemble({"server", "-hf", "test/main:Q8_0", "-hfd", "test/main", "-md", "mtp-model-BF16.gguf", "--spec-type", "draft-mtp"}, params); + REQUIRE_EQ(params.speculative.draft.mparams.path, cached("test/main", "mtp-model-BF16.gguf")); + } + { + // -hfd without a spec type auto-selects the type, mtp first when all ship + common_params params; + assemble({"server", "-hf", "test/main:Q8_0", "-hfd", "test/quad:Q8_0"}, params); + REQUIRE(params.speculative.types == std::vector{COMMON_SPECULATIVE_TYPE_DRAFT_MTP}); + REQUIRE_EQ(params.speculative.draft.mparams.path, cached("test/quad", "mtp-model-Q8_0.gguf")); + } + { + // auto-selection with only a dflash sidecar + common_params params; + assemble({"server", "-hf", "test/main:Q8_0", "-hfd", "test/dflash:Q8_0"}, params); + REQUIRE(params.speculative.types == std::vector{COMMON_SPECULATIVE_TYPE_DRAFT_DFLASH}); + REQUIRE_EQ(params.speculative.draft.mparams.path, cached("test/dflash", "dflash-model-Q8_0.gguf")); + } + { + // auto-selection with only an eagle3 sidecar + common_params params; + assemble({"server", "-hf", "test/main:Q8_0", "-hfd", "test/eagle3:Q8_0"}, params); + REQUIRE(params.speculative.types == std::vector{COMMON_SPECULATIVE_TYPE_DRAFT_EAGLE3}); + REQUIRE_EQ(params.speculative.draft.mparams.path, cached("test/eagle3", "eagle3-model-Q8_0.gguf")); + } + { + // auto-selection prefers dspark over dflash when both ship + common_params params; + assemble({"server", "-hf", "test/main:Q8_0", "-hfd", "test/pair:Q8_0"}, params); + REQUIRE(params.speculative.types == std::vector{COMMON_SPECULATIVE_TYPE_DRAFT_DSPARK}); + REQUIRE_EQ(params.speculative.draft.mparams.path, cached("test/pair", "dspark-model-Q8_0.gguf")); + } + { + // -hf with the dspark spec type wires the sidecar of the main repo, + // anchored on the only full quant + common_params params; + assemble({"server", "-hf", "test/spark", "--spec-type", "draft-dspark"}, params); + REQUIRE_EQ(params.model.path, cached("test/spark", "model-MXFP4.gguf")); + REQUIRE_EQ(params.speculative.draft.mparams.path, cached("test/spark", "dspark-model-MXFP4.gguf")); + } + { + // -hfd on a repo without sidecars keeps resolving a full model as draft + common_params params; + assemble({"server", "-hf", "test/main:Q8_0", "-hfd", "test/small"}, params); + REQUIRE(params.speculative.types == std::vector{COMMON_SPECULATIVE_TYPE_NONE}); + REQUIRE_EQ(params.speculative.draft.mparams.path, cached("test/small", "draft-model-Q4_K_M.gguf")); + } + { + // a preset repo wires the preset and clears the model for router mode + common_params params; + assemble({"server", "-hf", "test/preset"}, params); + REQUIRE_EQ(params.models_preset, cached("test/preset", "preset.ini")); + REQUIRE(params.model.path.empty()); + REQUIRE(params.model.hf_repo.empty()); + } + + g_repos.clear(); +} + +int main(void) { + // unbuffered, so a crash cannot swallow the reports already printed + setvbuf(stdout, nullptr, _IONBF, 0); + setvbuf(stderr, nullptr, _IONBF, 0); + + // the negative cases legitimately log errors on every reordering, + // keep the output down to the reports + common_log_pause(common_log_main()); + + // the loopback endpoint also keeps the client init from rejecting + // https on the builds without TLS support + httplib::Server server; + serve_repos(server); + int port = server.bind_to_any_port("127.0.0.1"); + + // isolate the cache, its location is read once so it is set + // before anything else + cache_dir = std::filesystem::temp_directory_path() / + ("test-model-resolution-cache-" + std::to_string(port)); + std::filesystem::remove_all(cache_dir); + common_set_env("LLAMA_CACHE", cache_dir.string()); + + std::thread server_thread([&server] { server.listen_after_bind(); }); + server.wait_until_ready(); + common_set_env("MODEL_ENDPOINT", "http://127.0.0.1:" + std::to_string(port) + "/"); + + test_plan_resolution(); + test_task_assembly(); + + server.stop(); + server_thread.join(); + + std::filesystem::remove_all(cache_dir); + printf("test-model-resolution: all tests OK\n"); + return 0; +} diff --git a/tests/test-recurrent-state-rollback.cpp b/tests/test-recurrent-state-rollback.cpp index 8e2eace6a195..5d1f0140b623 100644 --- a/tests/test-recurrent-state-rollback.cpp +++ b/tests/test-recurrent-state-rollback.cpp @@ -83,27 +83,33 @@ int main(int argc, char ** argv) { if (llama_vocab_type(vocab) == LLAMA_VOCAB_TYPE_NONE) { tokens = { 1, 2, 3, 4, 5, 6, 7, 8, 9 }; } else { - tokens = common_tokenize(ctx_src, "The quick brown fox jumps", true); + tokens = common_tokenize(ctx_src, "The quick brown fox jumps over the lazy dog", true); } const uint32_t n_rs_seq = llama_n_rs_seq(ctx_src); - if (tokens.size() > n_rs_seq + 1) { - tokens.resize(n_rs_seq + 1); + constexpr uint32_t n_rollback = 3; + if (n_rs_seq < n_rollback) { + fprintf(stderr, "%s : skipping because n_rs_seq is too small\n", __func__); + llama_free(ctx_src); + llama_free(ctx_dst); + return 0; } - if (tokens.size() < 2) { + if (tokens.empty()) { fprintf(stderr, "%s : not enough prompt tokens\n", __func__); return 1; } - const uint32_t n_tokens = tokens.size(); - const llama_token last_tok = tokens.back(); - const llama_pos last_pos = (llama_pos) n_tokens - 2; + tokens.resize(n_rs_seq + 1, tokens.back()); - // Decode the full prompt on the source, then roll back the last position. + const uint32_t n_tokens = tokens.size(); + const llama_pos rollback_pos = (llama_pos) n_tokens - n_rollback; + + // Decode the full prompt on the source, then roll back three positions. + // Replaying them crosses DSV4's ratio-4 compressor boundary. // Rollback leaves the recurrent memory in a snapshot state (rs_idx != 0). if (!decode_tokens(ctx_src, tokens, n_tokens)) { fprintf(stderr, "%s : failed to decode prompt\n", __func__); return 1; } - if (!llama_memory_seq_rm(llama_get_memory(ctx_src), 0, last_pos, -1)) { + if (!llama_memory_seq_rm(llama_get_memory(ctx_src), 0, rollback_pos, -1)) { fprintf(stderr, "%s : rollback failed\n", __func__); return 1; } @@ -113,31 +119,56 @@ int main(int argc, char ** argv) { ckpt.update_tgt(ctx_src, 0, 0); ckpt.load_tgt(ctx_dst, 0, 0); - // Replay the rolled-back token on both contexts and compare logits. - if (!decode_one(ctx_src, last_tok, last_pos) || - !decode_one(ctx_dst, last_tok, last_pos)) { - fprintf(stderr, "%s : replay failed\n", __func__); + constexpr float eps = 1e-5f; + std::vector> logits_src_replay(n_rollback); + const auto replay_and_compare = [&](const char * mode) { + for (uint32_t i = 0; i < n_rollback; ++i) { + const llama_pos pos = rollback_pos + i; + if (!decode_one(ctx_src, tokens[pos], pos) || + !decode_one(ctx_dst, tokens[pos], pos)) { + fprintf(stderr, "%s : %s replay failed at position %d\n", __func__, mode, pos); + return false; + } + + const float * logits_src = llama_get_logits_ith(ctx_src, 0); + const float * logits_dst = llama_get_logits_ith(ctx_dst, 0); + if (logits_src == nullptr || logits_dst == nullptr) { + fprintf(stderr, "%s : missing %s logits at position %d\n", __func__, mode, pos); + return false; + } + + logits_src_replay[i].assign(logits_src, logits_src + n_vocab); + for (int token = 0; token < n_vocab; ++token) { + if (std::fabs(logits_src[token] - logits_dst[token]) > eps) { + fprintf(stderr, "%s : %s logits mismatch at position %d, token %d (%g != %g)\n", + __func__, mode, pos, token, (double) logits_src[token], (double) logits_dst[token]); + return false; + } + } + } + return true; + }; + if (!replay_and_compare("full")) { return 1; } - const float * logits_src = llama_get_logits_ith(ctx_src, 0); - const float * logits_dst = llama_get_logits_ith(ctx_dst, 0); - if (logits_src == nullptr || logits_dst == nullptr) { - fprintf(stderr, "%s : missing logits\n", __func__); + if (!llama_memory_seq_rm(llama_get_memory(ctx_src), 0, rollback_pos, -1) || + !llama_memory_seq_rm(llama_get_memory(ctx_dst), 0, rollback_pos, -1)) { + fprintf(stderr, "%s : partial rollback failed\n", __func__); return 1; } - constexpr float eps = 1e-5f; - for (int i = 0; i < n_vocab; ++i) { - if (std::fabs(logits_src[i] - logits_dst[i]) > eps) { - fprintf(stderr, "%s : logits mismatch at token %d (%g != %g)\n", - __func__, i, (double) logits_src[i], (double) logits_dst[i]); - return 1; - } + constexpr llama_state_seq_flags partial_flags = LLAMA_STATE_SEQ_FLAGS_PARTIAL_ONLY; + common_prompt_checkpoint ckpt_partial; + ckpt_partial.update_tgt(ctx_src, 0, partial_flags); + ckpt_partial.load_tgt(ctx_dst, 0, partial_flags); + + if (!replay_and_compare("partial")) { + return 1; } // Repeat the load into a context that already has its own rollback state: - // groups 1..n_rs_seq hold a *different* prompt's history, and rs_idx[0] is + // groups 1..n_rs_seq hold a different prompt's history, and rs_idx[0] is // non-zero at load time. The restore must wipe that state and still match. llama_context * ctx_dirty = make_ctx(params, model); if (ctx_dirty == nullptr) { @@ -156,30 +187,33 @@ int main(int argc, char ** argv) { fprintf(stderr, "%s : dirty prompt decode failed\n", __func__); return 1; } - if (!llama_memory_seq_rm(llama_get_memory(ctx_dirty), 0, last_pos, -1)) { + if (!llama_memory_seq_rm(llama_get_memory(ctx_dirty), 0, rollback_pos, -1)) { fprintf(stderr, "%s : dirty rollback failed\n", __func__); return 1; } ckpt.load_tgt(ctx_dirty, 0, 0); - if (!decode_one(ctx_dirty, last_tok, last_pos)) { - fprintf(stderr, "%s : dirty replay failed\n", __func__); - return 1; - } - - const float * logits_dirty = llama_get_logits_ith(ctx_dirty, 0); - if (logits_dirty == nullptr) { - fprintf(stderr, "%s : missing dirty logits\n", __func__); - return 1; - } + for (uint32_t i = 0; i < n_rollback; ++i) { + const llama_pos pos = rollback_pos + i; + if (!decode_one(ctx_dirty, tokens[pos], pos)) { + fprintf(stderr, "%s : dirty replay failed at position %d\n", __func__, pos); + return 1; + } - for (int i = 0; i < n_vocab; ++i) { - if (std::fabs(logits_src[i] - logits_dirty[i]) > eps) { - fprintf(stderr, "%s : dirty-ctx logits mismatch at token %d (%g != %g)\n", - __func__, i, (double) logits_src[i], (double) logits_dirty[i]); + const float * logits_dirty = llama_get_logits_ith(ctx_dirty, 0); + if (logits_dirty == nullptr) { + fprintf(stderr, "%s : missing dirty logits at position %d\n", __func__, pos); return 1; } + + for (int token = 0; token < n_vocab; ++token) { + if (std::fabs(logits_src_replay[i][token] - logits_dirty[token]) > eps) { + fprintf(stderr, "%s : dirty-ctx logits mismatch at position %d, token %d (%g != %g)\n", + __func__, pos, token, (double) logits_src_replay[i][token], (double) logits_dirty[token]); + return 1; + } + } } fprintf(stderr, "%s : recurrent rollback checkpoint restored successfully\n", __func__); diff --git a/tests/test-sampling.cpp b/tests/test-sampling.cpp index 2aecff90e7bb..df1eb1a20227 100644 --- a/tests/test-sampling.cpp +++ b/tests/test-sampling.cpp @@ -10,7 +10,7 @@ #include #include -extern struct llama_sampler * llama_sampler_init_dry_testing(int32_t context_size, float dry_multiplier, float dry_base, int32_t dry_allowed_length, int32_t dry_penalty_last_n, const std::vector>& seq_breakers); +extern struct llama_sampler * llama_sampler_init_dry_testing(float dry_multiplier, float dry_base, int32_t dry_allowed_length, int32_t dry_penalty_last_n, const std::vector>& seq_breakers); static void dump(const llama_token_data_array * cur_p) { for (size_t i = 0; i < cur_p->size; i++) { @@ -144,7 +144,7 @@ static void test_penalties( sampler_tester tester(probs, probs_expected); - auto * sampler = llama_sampler_init_penalties(last_tokens.size(), repeat_penalty, alpha_frequency, alpha_presence); + auto * sampler = llama_sampler_init_penalties((int32_t) probs.size(), (int32_t) last_tokens.size(), repeat_penalty, alpha_frequency, alpha_presence); for (size_t i = 0; i < last_tokens.size(); i++) { llama_sampler_accept(sampler, last_tokens[i]); @@ -168,7 +168,7 @@ static void test_dry( sampler_tester tester(probs, expected_probs); - auto * sampler = llama_sampler_init_dry_testing(1024, dry_multiplier, dry_base, dry_allowed_length, dry_penalty_last_n, seq_breakers); + auto * sampler = llama_sampler_init_dry_testing(dry_multiplier, dry_base, dry_allowed_length, dry_penalty_last_n, seq_breakers); for (size_t i = 0; i < last_tokens.size(); i++) { llama_sampler_accept(sampler, last_tokens[i]); diff --git a/tools/cli/README.md b/tools/cli/README.md index bcddd05702bb..4d86ce7c0136 100644 --- a/tools/cli/README.md +++ b/tools/cli/README.md @@ -116,14 +116,14 @@ | `--xtc-probability N` | xtc probability (default: 0.00, 0.0 = disabled) | | `--xtc-threshold N` | xtc threshold (default: 0.10, 1.0 = disabled) | | `--typical, --typical-p N` | locally typical sampling, parameter p (default: 1.00, 1.0 = disabled) | -| `--repeat-last-n N` | last n tokens to consider for penalize (default: 64, 0 = disabled, -1 = ctx_size) | +| `--repeat-last-n N` | last n tokens to consider for penalize (default: 64, 0 = disabled) | | `--repeat-penalty N` | penalize repeat sequence of tokens (default: 1.00, 1.0 = disabled) | | `--presence-penalty N` | repeat alpha presence penalty (default: 0.00, 0.0 = disabled) | | `--frequency-penalty N` | repeat alpha frequency penalty (default: 0.00, 0.0 = disabled) | | `--dry-multiplier N` | set DRY sampling multiplier (default: 0.00, 0.0 = disabled) | | `--dry-base N` | set DRY sampling base value (default: 1.75) | | `--dry-allowed-length N` | set allowed length for DRY sampling (default: 2) | -| `--dry-penalty-last-n N` | set DRY penalty for the last n tokens (default: -1, 0 = disable, -1 = context size) | +| `--dry-penalty-last-n N` | set DRY penalty for the last n tokens (default: 64, 0 = disable) | | `--dry-sequence-breaker STRING` | add sequence breaker for DRY sampling, clearing out default breakers ('\n', ':', '"', '*') in the process; use "none" to not use any sequence breakers | | `--adaptive-target N` | adaptive-p: select tokens near this probability (valid range 0.0 to 1.0; negative = disabled) (default: -1.00)
[(more info)](https://github.com/ggml-org/llama.cpp/pull/17927) | | `--adaptive-decay N` | adaptive-p: decay rate for target adaptation over time. lower values are more reactive, higher values are more stable.
(valid range 0.0 to 0.99) (default: 0.90) | diff --git a/tools/cli/cli-context.cpp b/tools/cli/cli-context.cpp index 0de8f69025ce..3d801b73d4c1 100644 --- a/tools/cli/cli-context.cpp +++ b/tools/cli/cli-context.cpp @@ -624,10 +624,14 @@ int cli_context::run() { generated_content content; generate_completion(content, timings); - impl->messages.push_back({ + json assistant_msg = { {"role", "assistant"}, {"content", content.content} - }); + }; + if (!content.reasoning.empty()) { + assistant_msg["reasoning_content"] = content.reasoning; + } + impl->messages.push_back(std::move(assistant_msg)); if (output_file) { std::string out_content = "Assistant:\n"; diff --git a/tools/completion/README.md b/tools/completion/README.md index bce71d68d949..2abe7aaa25bb 100644 --- a/tools/completion/README.md +++ b/tools/completion/README.md @@ -199,14 +199,14 @@ llama-completion.exe -m models\gemma-1.1-7b-it.Q4_K_M.gguf --ignore-eos -n -1 | `--xtc-probability N` | xtc probability (default: 0.00, 0.0 = disabled) | | `--xtc-threshold N` | xtc threshold (default: 0.10, 1.0 = disabled) | | `--typical, --typical-p N` | locally typical sampling, parameter p (default: 1.00, 1.0 = disabled) | -| `--repeat-last-n N` | last n tokens to consider for penalize (default: 64, 0 = disabled, -1 = ctx_size) | +| `--repeat-last-n N` | last n tokens to consider for penalize (default: 64, 0 = disabled) | | `--repeat-penalty N` | penalize repeat sequence of tokens (default: 1.00, 1.0 = disabled) | | `--presence-penalty N` | repeat alpha presence penalty (default: 0.00, 0.0 = disabled) | | `--frequency-penalty N` | repeat alpha frequency penalty (default: 0.00, 0.0 = disabled) | | `--dry-multiplier N` | set DRY sampling multiplier (default: 0.00, 0.0 = disabled) | | `--dry-base N` | set DRY sampling base value (default: 1.75) | | `--dry-allowed-length N` | set allowed length for DRY sampling (default: 2) | -| `--dry-penalty-last-n N` | set DRY penalty for the last n tokens (default: -1, 0 = disable, -1 = context size) | +| `--dry-penalty-last-n N` | set DRY penalty for the last n tokens (default: 64, 0 = disable) | | `--dry-sequence-breaker STRING` | add sequence breaker for DRY sampling, clearing out default breakers ('\n', ':', '"', '*') in the process; use "none" to not use any sequence breakers | | `--adaptive-target N` | adaptive-p: select tokens near this probability (valid range 0.0 to 1.0; negative = disabled) (default: -1.00)
[(more info)](https://github.com/ggml-org/llama.cpp/pull/17927) | | `--adaptive-decay N` | adaptive-p: decay rate for target adaptation over time. lower values are more reactive, higher values are more stable.
(valid range 0.0 to 0.99) (default: 0.90) | @@ -388,11 +388,11 @@ Example usage: `--temp 0` ### Repeat Penalty - `--repeat-penalty N`: Control the repetition of token sequences in the generated text default: 1.0, 1.0 = disabled). -- `--repeat-last-n N`: Last n tokens to consider for penalizing repetition (default: 64, 0 = disabled, -1 = ctx-size). +- `--repeat-last-n N`: Last n tokens to consider for penalizing repetition (default: 64, 0 = disabled). The `repeat-penalty` option helps prevent the model from generating repetitive or monotonous text. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. The default value is 1. -The `repeat-last-n` option controls the number of tokens in the history to consider for penalizing repetition. A larger value will look further back in the generated text to prevent repetitions, while a smaller value will only consider recent tokens. A value of 0 disables the penalty, and a value of -1 sets the number of tokens considered equal to the context size (`ctx-size`). +The `repeat-last-n` option controls the number of tokens in the history to consider for penalizing repetition. A larger value will look further back in the generated text to prevent repetitions, while a smaller value will only consider recent tokens. A value of 0 disables the penalty. ### DRY Repetition Penalty @@ -401,7 +401,7 @@ DRY (Don't Repeat Yourself) sampling is an effective technique for reducing repe - `--dry-multiplier N`: Set the DRY sampling multiplier (default: 0.0, 0.0 = disabled). - `--dry-base N`: Set the DRY sampling base value (default: 1.75). - `--dry-allowed-length N`: Set the allowed length for DRY sampling (default: 2). -- `--dry-penalty-last-n N`: Set DRY penalty for the last n tokens (default: -1, 0 = disable, -1 = context size). +- `--dry-penalty-last-n N`: Set DRY penalty for the last n tokens (default: 64, 0 = disable). - `--dry-sequence-breaker STRING`: Add a sequence breaker for DRY sampling. Can be used more than once to add multiple sequence breakers. Using this clears out the default breakers, which consist of: `['\n', ':', '"', '*']`. If the string `"none"` is supplied, no sequence breakers are used. The `dry-multiplier` option controls the strength of the DRY sampling effect. A value of 0.0 disables DRY sampling, while higher values increase its influence. A typical recommended value is 0.8. @@ -410,13 +410,13 @@ The `dry-base` option sets the base value for the exponential penalty calculatio The `dry-allowed-length` option sets the maximum length of repeated sequences that will not be penalized. Repetitions shorter than or equal to this length are not penalized, allowing for natural repetitions of short phrases or common words. -The `dry-penalty-last-n` option controls how many recent tokens to consider when applying the DRY penalty. A value of -1 considers the entire context. Use a positive value to limit the consideration to a specific number of recent tokens. +The `dry-penalty-last-n` option controls how many recent tokens to consider when applying the DRY penalty. A value of 0 disables the penalty. Use a positive value to limit the consideration to a specific number of recent tokens. The `dry-sequence-breaker` option adds a single sequence breaker and can be used more than once to specify multiple sequence breakers. Sequence breakers interrupt sequence matching and break the input into parts where matching can be applied. DRY sampling provides more nuanced control over text generation, particularly for reducing long-range repetitions and maintaining global coherence. -Example usage: `--dry-multiplier 0.8 --dry-base 1.75 --dry-allowed-length 2 --dry-penalty-last-n -1 --dry-sequence-breaker "—" --dry-sequence-breaker "##"` +Example usage: `--dry-multiplier 0.8 --dry-base 1.75 --dry-allowed-length 2 --dry-penalty-last-n 64 --dry-sequence-breaker "—" --dry-sequence-breaker "##"` ### Top-K Sampling diff --git a/tools/gguf-split/gguf-split.cpp b/tools/gguf-split/gguf-split.cpp index 8a6b5c198b21..5cafcc9aa96a 100644 --- a/tools/gguf-split/gguf-split.cpp +++ b/tools/gguf-split/gguf-split.cpp @@ -47,6 +47,7 @@ struct split_params { std::string output; bool no_tensor_first_split = false; bool dry_run = false; + bool delete_splits = false; }; static void split_print_usage(const char * executable) { @@ -65,6 +66,7 @@ static void split_print_usage(const char * executable) { printf(" --split-max-size N(M|G) max size per split\n"); printf(" --no-tensor-first-split do not add tensors to the first split (disabled by default)\n"); printf(" --dry-run only print out a split plan and exit, without writing any new files\n"); + printf(" --delete-splits delete the split files during merge to free up disk space WARNING: this option is unsafe and will leave you in an unrecoverable state if something fails during the merge\n"); printf("\n"); } @@ -147,6 +149,9 @@ static void split_params_parse_ex(int argc, const char ** argv, split_params & p } params.mode = MODE_SIZE; params.n_bytes_split = split_str_to_n_bytes(argv[arg_idx]); + } else if (arg == "--delete-splits") { + arg_found = true; + params.delete_splits = true; } if (!arg_found) { @@ -509,6 +514,7 @@ static void gguf_merge(const split_params & split_params) { } // Write tensors data + bool merge_error = false; for (int i_split = 0; i_split < n_split; i_split++) { llama_split_path(split_path, sizeof(split_path), split_prefix, i_split, n_split); std::ifstream f_input(split_path, std::ios::binary); @@ -554,6 +560,16 @@ static void gguf_merge(const split_params & split_params) { ggml_free(ctx_meta); f_input.close(); fprintf(stderr, "\033[3Ddone\n"); + + if (!split_params.dry_run && split_params.delete_splits) { + int delete_result = std::remove(split_path); + if (delete_result != 0) { + merge_error = true; + fprintf(stderr, "error: failed to delete %s\n", split_path); + } else { + fprintf(stderr, "%s: deleted file %s\n", __func__, split_path); + } + } } if (!split_params.dry_run) { @@ -568,6 +584,10 @@ static void gguf_merge(const split_params & split_params) { fprintf(stderr, "%s: %s merged from %d split with %d tensors.\n", __func__, split_params.output.c_str(), n_split, total_tensors); + + if (merge_error) { + exit(EXIT_FAILURE); + } } int main(int argc, const char ** argv) { diff --git a/tools/gguf-split/tests.sh b/tools/gguf-split/tests.sh index c8dd0b007953..dcd66681bb83 100755 --- a/tools/gguf-split/tests.sh +++ b/tools/gguf-split/tests.sh @@ -66,12 +66,12 @@ echo PASS echo # 5. Merge -#$SPLIT --merge $WORK_PATH/ggml-model-split-32-tensors-00001-of-00012.gguf $WORK_PATH/ggml-model-merge-2.gguf +#$SPLIT --merge $WORK_PATH/ggml-model-split-32-tensors-00001-of-00011.gguf $WORK_PATH/ggml-model-merge-2.gguf #echo PASS #echo # 5b. Test the merged model is loading properly -#$MAIN -no-cnv --model $WORK_PATH/ggml-model-merge-2.gguf --n-predict 32 +#$MAIN -no-cnv --model $WORK_PATH/ggml-model-merge-2.gguf -p "I believe the meaning of life is" --n-predict 32 #echo PASS #echo @@ -85,5 +85,25 @@ $MAIN -no-cnv --model $WORK_PATH/ggml-model-split-500M-00001-of-00002.gguf -p "I echo PASS echo +# 7. Merge with delete splits +#for i in $(seq -w 1 11); do +# cp "$WORK_PATH/ggml-model-split-32-tensors-000${i}-of-00011.gguf" "$WORK_PATH/ggml-model-split-32-tensors-copy-000${i}-of-00011.gguf" +#done +#$SPLIT --merge --delete-splits $WORK_PATH/ggml-model-split-32-tensors-copy-00001-of-00011.gguf $WORK_PATH/ggml-model-merge-3.gguf +#echo PASS +#echo + +# 7b. Test the merged model is loading properly +#$MAIN -no-cnv --model $WORK_PATH/ggml-model-merge-3.gguf -p "I believe the meaning of life is" --n-predict 32 +#echo PASS +#echo + +# 7c. Test the files were deleted +#for i in $(seq -w 1 11); do +# test ! -f "$WORK_PATH/ggml-model-split-32-tensors-copy-000${i}-of-00011.gguf" +#done +#echo PASS +#echo + # Clean up rm -f $WORK_PATH/ggml-model-split*.gguf $WORK_PATH/ggml-model-merge*.gguf diff --git a/tools/mtmd/CMakeLists.txt b/tools/mtmd/CMakeLists.txt index 15040e4af5f9..4675fb9a97b6 100644 --- a/tools/mtmd/CMakeLists.txt +++ b/tools/mtmd/CMakeLists.txt @@ -18,6 +18,8 @@ add_library(mtmd mtmd-image.cpp mtmd.h mtmd-helper.cpp + mtmd-helper-gen.cpp + mtmd-helper-common.h mtmd-helper.h clip.cpp clip.h @@ -52,6 +54,8 @@ add_library(mtmd models/mimovl.cpp models/qwen3a.cpp models/mimo-audio.cpp + models/qwen3tts-spkenc.cpp + models/qwen3tts-gen.cpp models/step3vl.cpp models/siglip.cpp models/whisper-enc.cpp diff --git a/tools/mtmd/README-dev.md b/tools/mtmd/README-dev.md index 3a08915876c1..3cddd085ec6c 100644 --- a/tools/mtmd/README-dev.md +++ b/tools/mtmd/README-dev.md @@ -33,3 +33,52 @@ A typical pipeline of the core libmtmd is as follows: We provide a set of helper functions via `mtmd_helper` to make using libmtmd easier. The helper provides: - Image, audio and video file decoding (for example, decode raw JPEG into RGB bitmap) - Manage `llama_batch` and calls to `llama_decode` + +## Audio generation support + +Audio generation is added to mtmd in PR [#26254](https://github.com/ggml-org/llama.cpp/pull/26254) + +Currently, we support the 3-stage pipeline below which should cover most TTS models: +- Stage 1: Backbone / Semantic Stage: Backbone model accepts text prompt and reference voice as input +- Stage 2: Acoustic Detail Generator: A model takes the hidden state from backbone and generate audio details (usually as audio codes or mel-spectrogram) +- Stage 3: Waveform Reconstruction: Convert the semantic and acoustic data from previous stages to the final waveform + +For example, Qwen3-TTS: +- Reference voice is encoded using ECAPA-TDNN speaker encoder (`speaker_encoder`) +- Text prompt and reference voice are processed via a backbone (`talker.model`) +- A model converts sampled semantic token and hidden state from stage 2 into a list of 15 acoustic codes (`talker.code_predictor`) +- 16 generated codes are converted into waveform (`code2wav`) + +### API design constraints + +Due to wide variety of audio generation pipelines, the `mtmd_gen_audio` system is designed to be flexible and reusable by new models. + +`mtmd_gen_audio` is split into 2 main API: +- Core API `mtmd.h`: handles main inference. Important: the API surface must be stateless; caller must handle state management and audio frame accumulation. +- Helper API `mtmd-helper.h`: provides a model-agnostic stateful API. Usage example can be found in the `tools/tts` directory. + +### Checklist for porting new audio generation models to mtmd + +1. Establish a list of reusable and missing components from the current mtmd implementation. +2. For GGUF conversion: + - Backbone model should be converted to a normal text model (loadable via `libllama`) + - If model used hard-coded embedding row ID, append them to token embeddings and assign token name for them (see `qwen3tts.py`) + - If model have a specific output logits head for audio codes (usually semantic code), keep the head as-is and pad the logits at inference time (see `src/models/qwen3vl.cpp`) + - Sidecar models (code2wav, bigvgan, etc) must live inside the mmproj GGUF (but can be in different `clip_context` if necessary) + - Note: it should use `ggml_build_forward_select` to select graphs if multiple graphs living in the same context + - Reuse existing GGUF metadata key name and tensor name whenever possible; think twice before adding extensive changes to GGUF writer. For example, Qwen3-TTS hard-code part of the hparams to `clip.cpp` as they won't likely to change. + - For tensor naming: + - Prefixed with `a.*` for tensors used by speaker encoder pipeline + - Prefixed with `a.gen.*` for generation stages (code / mel-spectrogram / PCM generation) +3. Make sure most of the changes happen inside `mtmd-helper-gen.cpp`. A good PR looks like this: + - 10-20% changes is to add new backbone (text) model and conversion + - 60% changes inside `mtmd-helper-gen.cpp` + - 10% changes inside `libmtmd` and `clip.cpp` systems + - The rest downstream code (CLI, server) should have no changes at all +4. Update usage documentation in `tools/tts/README.md` + +IMPORTANT: If your model needs changes that don't fit the existing infrastructure, **open an issue first for discussion**. + +No-go checklist (these will get the PR rejected and require discussion before proceeding): +- Violating the API design constraints stated above +- Adding a new model-specific binary: the API and binary surface must stay model-agnostic diff --git a/tools/mtmd/clip-graph.h b/tools/mtmd/clip-graph.h index 29352abb4c0b..e12140ba009d 100644 --- a/tools/mtmd/clip-graph.h +++ b/tools/mtmd/clip-graph.h @@ -54,6 +54,9 @@ struct clip_graph { clip_graph(clip_ctx * ctx, const clip_image_f32 & img); + // build sub-graph, reuse buf from parent + clip_graph(const clip_graph & parent); + virtual ~clip_graph() = default; virtual ggml_cgraph * build() = 0; diff --git a/tools/mtmd/clip-impl.h b/tools/mtmd/clip-impl.h index 589fc724ed08..e1567ee5bafb 100644 --- a/tools/mtmd/clip-impl.h +++ b/tools/mtmd/clip-impl.h @@ -32,6 +32,7 @@ #define KEY_PROJ_TYPE "clip.projector_type" #define KEY_HAS_AUDIO_ENC "clip.has_audio_encoder" #define KEY_HAS_VISION_ENC "clip.has_vision_encoder" +#define KEY_HAS_GEN_AUDIO_ENC "clip.has_gen_audio_encoder" #define KEY_USE_GELU "clip.use_gelu" #define KEY_USE_SILU "clip.use_silu" @@ -41,6 +42,7 @@ #define KEY_PROJ_DIM "clip.%s.projection_dim" #define KEY_N_HEAD "clip.%s.attention.head_count" #define KEY_N_HEAD_KV "clip.%s.attention.head_count_kv" +#define KEY_N_EMBD_HEAD "clip.%s.attention.head_dim" #define KEY_LAYER_NORM_EPS "clip.%s.attention.layer_norm_epsilon" #define KEY_FEATURE_LAYERS "clip.%s.feature_layer" @@ -88,6 +90,8 @@ #define KEY_A_ATTN_WINDOW_SIZE "clip.audio.window_size" // mimo-audio-tokenizer: sliding-window radius #define KEY_A_LOCAL_BLOCK_COUNT "clip.audio.local_block_count" // mimo-v2.5: input_local_transformer layer count #define KEY_A_LOCAL_GROUP_SIZE "clip.audio.local_group_size" // mimo-v2.5: input_local_transformer grouping size +// audio generation (gen-audio)-specific +#define KEY_GEN_AUDIO_PROJ_TYPE "clip.gen.audio.projector_type" // for models with mixed modalities #define KEY_AUDIO_SUBSAMPLING_FACTOR "clip.audio.subsampling_factor" // @@ -200,6 +204,48 @@ #define TN_MM_A_LOCAL_LN2 "mm.a.local_blk.%d.ln2.%s" #define TN_MM_A_LOCAL_NORM "mm.a.local_norm.%s" +// qwen3tts speaker encoder (ECAPA-TDNN) +#define TN_A_SE_CONV1 "a.blk.%d.se_conv1.%s" +#define TN_A_SE_CONV2 "a.blk.%d.se_conv2.%s" +#define TN_A_CONV_RES2 "a.blk.%d.res2.%d.%s" +#define TN_A_ASP_ATTN "a.asp_attn.%s" +#define TN_A_ASP_TDNN "a.asp_tdnn.%s" + +// qwen3tts code_predictor +#define TN_A_GEN_CODE_PROJ_IN "a.gen.code.proj_in.%s" +#define TN_A_GEN_CODE_EMBD "a.gen.code.embd.%s" +#define TN_A_GEN_CODE_HEAD "a.gen.code.head.%s" +#define TN_A_GEN_CODE_OUT_EMBD "a.gen.code.out_embd.%s" +#define TN_A_GEN_CODE_NORM "a.gen.code.output_norm.%s" + +// qwen3tts code2wav (RVQ codes -> raw PCM) +// pre_transformer layers use the generic TN_ATTN_*/TN_FFN_*/TN_LN_*/TN_LS_* macros, prefix "a.gen.wav.tfm" +#define TN_A_GEN_WAV_QUANT_FIRST_IN "a.gen.wav.quant.first.in_proj.%s" +#define TN_A_GEN_WAV_QUANT_FIRST_OUT "a.gen.wav.quant.first.out_proj.%s" +#define TN_A_GEN_WAV_QUANT_FIRST_CB "a.gen.wav.quant.first.codebook.%s" +#define TN_A_GEN_WAV_QUANT_REST_IN "a.gen.wav.quant.rest.in_proj.%s" +#define TN_A_GEN_WAV_QUANT_REST_OUT "a.gen.wav.quant.rest.out_proj.%s" +#define TN_A_GEN_WAV_QUANT_REST_CB "a.gen.wav.quant.rest.codebook.%s" +#define TN_A_GEN_WAV_PRE_CONV "a.gen.wav.pre_conv.%s" +#define TN_A_GEN_WAV_TFM_IN_PROJ "a.gen.wav.tfm.in_proj.%s" +#define TN_A_GEN_WAV_TFM_OUT_PROJ "a.gen.wav.tfm.out_proj.%s" +#define TN_A_GEN_WAV_TFM_OUT_NORM "a.gen.wav.tfm.output_norm.%s" +#define TN_A_GEN_WAV_UP_CONV "a.gen.wav.up.blk.%d.conv.%s" +#define TN_A_GEN_WAV_UP_DWCONV "a.gen.wav.up.blk.%d.dwconv.%s" +#define TN_A_GEN_WAV_UP_NORM "a.gen.wav.up.blk.%d.norm.%s" +#define TN_A_GEN_WAV_UP_PW1 "a.gen.wav.up.blk.%d.pw1.%s" +#define TN_A_GEN_WAV_UP_PW2 "a.gen.wav.up.blk.%d.pw2.%s" +#define TN_A_GEN_WAV_UP_GAMMA "a.gen.wav.up.blk.%d.gamma" +#define TN_A_GEN_WAV_DAC_ENTRY "a.gen.wav.dac.entry.%s" +#define TN_A_GEN_WAV_DAC_SNAKE "a.gen.wav.dac.blk.%d.snake.%s" +#define TN_A_GEN_WAV_DAC_CONV "a.gen.wav.dac.blk.%d.conv.%s" +#define TN_A_GEN_WAV_DAC_RES_ACT1 "a.gen.wav.dac.blk.%d.res.%d.act1.%s" +#define TN_A_GEN_WAV_DAC_RES_CONV1 "a.gen.wav.dac.blk.%d.res.%d.conv1.%s" +#define TN_A_GEN_WAV_DAC_RES_ACT2 "a.gen.wav.dac.blk.%d.res.%d.act2.%s" +#define TN_A_GEN_WAV_DAC_RES_CONV2 "a.gen.wav.dac.blk.%d.res.%d.conv2.%s" +#define TN_A_GEN_WAV_DAC_POST_SNAKE "a.gen.wav.dac.post_snake.%s" +#define TN_A_GEN_WAV_DAC_POST_CONV "a.gen.wav.dac.post_conv.%s" + // cogvlm #define TN_MM_POST_FC_NORM "mm.post_fc_norm.%s" #define TN_MM_H_TO_4H "mm.up.%s" @@ -407,6 +453,8 @@ enum projector_type { PROJECTOR_TYPE_MINIMAX_M3, PROJECTOR_TYPE_GRANITE4_VISION, PROJECTOR_TYPE_MIMO_AUDIO, + PROJECTOR_TYPE_QWEN3TTS_SPKENC, + PROJECTOR_TYPE_QWEN3TTS_GEN, PROJECTOR_TYPE_UNKNOWN, }; @@ -464,6 +512,8 @@ static std::map PROJECTOR_TYPE_NAMES = { { PROJECTOR_TYPE_GRANITE4_VISION, "granite4_vision"}, { PROJECTOR_TYPE_MIMO_AUDIO, "mimo_audio"}, { PROJECTOR_TYPE_PARAKEET, "parakeet"}, + { PROJECTOR_TYPE_QWEN3TTS_SPKENC, "qwen3tts_spkenc"}, + { PROJECTOR_TYPE_QWEN3TTS_GEN, "qwen3tts_gen"}, }; static projector_type clip_projector_type_from_string(const std::string & str) { diff --git a/tools/mtmd/clip-model.h b/tools/mtmd/clip-model.h index fec2b01802f8..101f49cd1849 100644 --- a/tools/mtmd/clip-model.h +++ b/tools/mtmd/clip-model.h @@ -54,6 +54,8 @@ struct clip_hparams { int32_t projection_dim = 0; int32_t n_head = 0; int32_t n_head_kv = 0; + // 0 = derive from n_embd; set when qkv width != n_embd + int32_t n_embd_head = 0; int32_t n_layer = 0; int32_t n_merge = 1; // number of patch merges **per-side** @@ -134,6 +136,19 @@ struct clip_hparams { int32_t rvq_num_quantizers = 0; std::vector rvq_codebook_size; // per-quantizer bin count (ragged, e.g. 1024/1024/256/128x17) + // qwen3tts code2wav + int32_t wav_tfm_n_layer = 0; + int32_t wav_tfm_n_embd = 0; + int32_t wav_tfm_n_ff = 0; + int32_t wav_tfm_n_head = 0; + int32_t wav_tfm_n_head_kv = 0; + float wav_tfm_eps = 1e-5f; + float wav_tfm_rope_theta = 10000.0f; + int32_t wav_upsample_n_block = 0; + int32_t wav_dac_n_block = 0; + int32_t wav_dac_n_res = 0; + int32_t wav_tfm_swa = 0; // pre_transformer's KV cache size, in frames + // mimo-v2.5: LLM-side connector (input_local_transformer) int32_t audio_local_n_layer = 0; int32_t audio_local_group_size = 0; @@ -284,6 +299,14 @@ struct clip_layer { ggml_tensor * cross_attn_norm_w = nullptr; ggml_tensor * cross_attn_norm_b = nullptr; + // qwen3tts speaker encoder: SE-Res2Net block, tdnn1/tdnn2 reuse conv_pw1_w/b and conv_pw2_w/b above + ggml_tensor * se_conv1_w = nullptr; + ggml_tensor * se_conv1_b = nullptr; + ggml_tensor * se_conv2_w = nullptr; + ggml_tensor * se_conv2_b = nullptr; + std::vector res2_conv_w; // Res2Net hierarchical branches + std::vector res2_conv_b; + bool has_deepstack() const { return deepstack_fc1_w != nullptr; } @@ -363,6 +386,73 @@ struct qf_block { std::vector qf_proj_layers; }; +// qwen3tts code2wav: RVQ codes -> raw PCM +struct clip_code2wav { + // "upsample" stage: one ConvNeXt block plus the causal ConvTranspose1d before it + struct upsample_block { + ggml_tensor * conv_w = nullptr; // causal ConvTranspose1d, 2x + ggml_tensor * conv_b = nullptr; + ggml_tensor * dwconv_w = nullptr; // depthwise causal conv, k=7 + ggml_tensor * dwconv_b = nullptr; + ggml_tensor * norm_w = nullptr; // LayerNorm + ggml_tensor * norm_b = nullptr; + ggml_tensor * pw1_w = nullptr; // pointwise expand + ggml_tensor * pw1_b = nullptr; + ggml_tensor * pw2_w = nullptr; // pointwise project + ggml_tensor * pw2_b = nullptr; + ggml_tensor * gamma = nullptr; // layer scale + }; + + // one DAC residual unit: SnakeBeta -> dilated causal conv -> SnakeBeta -> pointwise causal conv + struct dac_res { + ggml_tensor * act1_alpha = nullptr; + ggml_tensor * act1_beta = nullptr; + ggml_tensor * conv1_w = nullptr; + ggml_tensor * conv1_b = nullptr; + ggml_tensor * act2_alpha = nullptr; + ggml_tensor * act2_beta = nullptr; + ggml_tensor * conv2_w = nullptr; + ggml_tensor * conv2_b = nullptr; + }; + + // one DAC upsample block (SnakeBeta -> causal ConvTranspose1d -> 3 residual units) + struct dac_block { + ggml_tensor * snake_alpha = nullptr; + ggml_tensor * snake_beta = nullptr; + ggml_tensor * conv_w = nullptr; // causal ConvTranspose1d + ggml_tensor * conv_b = nullptr; + std::vector res; + }; + + // quantizer: RVQ codebook decode + ggml_tensor * quant_first_in_w = nullptr; // semantic RVQ, in_proj (1x1 conv, loaded as 2D) + ggml_tensor * quant_first_out_w = nullptr; + ggml_tensor * quant_first_cb_w = nullptr; // codebook (1 layer) + ggml_tensor * quant_rest_in_w = nullptr; // acoustic RVQ + ggml_tensor * quant_rest_out_w = nullptr; + ggml_tensor * quant_rest_cb_w = nullptr; // codebooks, merged 3D [15, vocab, dim] + + ggml_tensor * pre_conv_w = nullptr; + ggml_tensor * pre_conv_b = nullptr; + + ggml_tensor * tfm_in_proj_w = nullptr; + ggml_tensor * tfm_in_proj_b = nullptr; + ggml_tensor * tfm_out_proj_w = nullptr; + ggml_tensor * tfm_out_proj_b = nullptr; + ggml_tensor * tfm_output_norm_w = nullptr; + std::vector tfm_layers; // reuses the generic block fields (ln_1/attn/ln_2/ffn/ls_1/ls_2) + + std::vector upsample; + + ggml_tensor * dac_entry_w = nullptr; + ggml_tensor * dac_entry_b = nullptr; + std::vector dac; + ggml_tensor * dac_post_snake_alpha = nullptr; + ggml_tensor * dac_post_snake_beta = nullptr; + ggml_tensor * dac_post_conv_w = nullptr; + ggml_tensor * dac_post_conv_b = nullptr; +}; + struct clip_model { clip_modality modality = CLIP_MODALITY_VISION; projector_type proj_type = PROJECTOR_TYPE_MLP; @@ -575,6 +665,24 @@ struct clip_model { ggml_tensor * conv2d_3_w = nullptr; ggml_tensor * conv2d_3_b = nullptr; + // qwen3tts speaker encoder (ECAPA-TDNN) + // reused tensors: stem conv is conv1d_1_w/b, feature aggregation is conv_out_w/b, output proj is mm_fc_w/b + ggml_tensor * spk_asp_attn_w = nullptr; + ggml_tensor * spk_asp_attn_b = nullptr; + ggml_tensor * spk_asp_tdnn_w = nullptr; + ggml_tensor * spk_asp_tdnn_b = nullptr; + + // qwen3tts code_predictor + ggml_tensor * gen_code_proj_in_w = nullptr; // small_to_mtp_projection + ggml_tensor * gen_code_proj_in_b = nullptr; + ggml_tensor * gen_code_embd_w = nullptr; // per-codebook embedding, merged 3D + ggml_tensor * gen_code_head_w = nullptr; // per-codebook output head, merged 3D + ggml_tensor * gen_code_out_embd_w = nullptr; // codebook-0 embedding, fed back into the talker + ggml_tensor * gen_code_norm_w = nullptr; // final norm + + // qwen3tts code2wav: RVQ codes -> raw PCM + clip_code2wav c2w; + // cogvlm ggml_tensor * mm_post_fc_norm_w = nullptr; ggml_tensor * mm_post_fc_norm_b = nullptr; diff --git a/tools/mtmd/clip.cpp b/tools/mtmd/clip.cpp index 11f9820edeb8..d6670030ff79 100644 --- a/tools/mtmd/clip.cpp +++ b/tools/mtmd/clip.cpp @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -253,7 +254,7 @@ clip_graph::clip_graph(clip_ctx * ctx, const clip_image_f32 & img) : n_embd(hparams.n_embd), n_head(hparams.n_head), n_head_kv(hparams.n_head_kv), - d_head(n_head > 0 ? n_embd / n_head : 0), + d_head(hparams.n_embd_head > 0 ? hparams.n_embd_head : (n_head > 0 ? n_embd / n_head : 0)), n_layer(hparams.n_layer), n_mmproj_embd(clip_n_mmproj_embd(ctx)), eps(hparams.eps), @@ -269,6 +270,29 @@ clip_graph::clip_graph(clip_ctx * ctx, const clip_image_f32 & img) : gf = ggml_new_graph_custom(ctx0, ctx->max_nodes, false); } +clip_graph::clip_graph(const clip_graph & parent) : + model(parent.model), + hparams(parent.hparams), + proj_type(parent.proj_type), + img(parent.img), + patch_size(parent.patch_size), + n_patches_x(parent.n_patches_x), + n_patches_y(parent.n_patches_y), + n_patches(parent.n_patches), + n_embd(parent.n_embd), + n_head(parent.n_head), + n_head_kv(parent.n_head_kv), + d_head(parent.d_head), + n_layer(parent.n_layer), + n_mmproj_embd(parent.n_mmproj_embd), + eps(parent.eps), + kq_scale(parent.kq_scale), + flash_attn_type(parent.flash_attn_type) { + // reuse from parent + ctx0 = parent.ctx0; + gf = parent.gf; +} + ggml_tensor * clip_graph::build_mm(ggml_tensor * w, ggml_tensor * x) const { return ggml_mul_mat(ctx0, w, x); } @@ -372,13 +396,13 @@ ggml_tensor * clip_graph::build_vit( /* nb1 */ ggml_row_size(cur->type, d_head), /* nb2 */ cur->nb[1], /* nb3 */ cur->nb[1] * n_pos, - /* offset */ ggml_row_size(cur->type, n_embd)); + /* offset */ ggml_row_size(cur->type, n_head * d_head)); Vcur = ggml_view_4d(ctx0, cur, d_head, n_head, n_pos, B, /* nb1 */ ggml_row_size(cur->type, d_head), /* nb2 */ cur->nb[1], /* nb3 */ cur->nb[1] * n_pos, - /* offset */ ggml_row_size(cur->type, 2 * n_embd)); + /* offset */ ggml_row_size(cur->type, 2 * n_head * d_head)); if (layer.q_norm) { GGML_ASSERT(layer.q_norm->ne[0] == Qcur->ne[0]); @@ -873,7 +897,8 @@ ggml_tensor * clip_graph::build_patch_merge_permute(ggml_tensor * cur, int scale return cur; } -static std::unique_ptr clip_get_graph_builder(clip_ctx * ctx, const clip_image_f32_batch & imgs) { +static std::unique_ptr clip_get_graph_builder(clip_ctx * ctx, const clip_image_f32_batch & imgs, + const clip_encode_params * params = nullptr) { const clip_image_f32 & img = imgs.entries[0]; std::unique_ptr builder; @@ -1025,6 +1050,17 @@ static std::unique_ptr clip_get_graph_builder(clip_ctx * ctx, const { builder = std::make_unique(ctx, img); } break; + case PROJECTOR_TYPE_QWEN3TTS_SPKENC: + { + builder = std::make_unique(ctx, img); + } break; + case PROJECTOR_TYPE_QWEN3TTS_GEN: + { + const auto gen_process = params ? params->gen_process : CLIP_GEN_PROCESS_GEN_CODE; + const int top_k = params ? params->top_k : 50; + const float top_p = params ? params->top_p : 1.0f; + builder = std::make_unique(ctx, img, gen_process, top_k, top_p); + } break; case PROJECTOR_TYPE_YOUTUVL: { builder = std::make_unique(ctx, img); @@ -1065,8 +1101,9 @@ struct clip_model_loader { size_t model_size = 0; // in bytes - bool has_vision = false; - bool has_audio = false; + bool has_vision = false; + bool has_audio = false; + bool has_gen_audio = false; mtmd_progress_callback progress_callback = nullptr; void * progress_callback_user_data = nullptr; @@ -1112,8 +1149,9 @@ struct clip_model_loader { // modalities { - get_bool(KEY_HAS_VISION_ENC, has_vision, false); - get_bool(KEY_HAS_AUDIO_ENC, has_audio, false); + get_bool(KEY_HAS_VISION_ENC, has_vision, false); + get_bool(KEY_HAS_AUDIO_ENC, has_audio, false); + get_bool(KEY_HAS_GEN_AUDIO_ENC, has_gen_audio, false); if (has_vision) { LOG_INF("%s: has vision encoder\n", __func__); @@ -1121,6 +1159,9 @@ struct clip_model_loader { if (has_audio) { LOG_INF("%s: has audio encoder\n", __func__); } + if (has_gen_audio) { + LOG_INF("%s: has audio generation (gen) encoder\n", __func__); + } } // tensors @@ -1147,6 +1188,8 @@ struct clip_model_loader { GGML_ASSERT(has_vision); } else if (modality == CLIP_MODALITY_AUDIO) { GGML_ASSERT(has_audio); + } else if (modality == CLIP_MODALITY_GEN_AUDIO) { + GGML_ASSERT(has_gen_audio); } model.modality = modality; @@ -1163,6 +1206,8 @@ struct clip_model_loader { get_string(KEY_VISION_PROJ_TYPE, proj_type, false); } else if (modality == CLIP_MODALITY_AUDIO) { get_string(KEY_AUDIO_PROJ_TYPE, proj_type, false); + } else if (modality == CLIP_MODALITY_GEN_AUDIO) { + get_string(KEY_GEN_AUDIO_PROJ_TYPE, proj_type, false); } else { GGML_ABORT("unknown modality"); } @@ -1182,14 +1227,16 @@ struct clip_model_loader { } } - const bool is_vision = model.modality == CLIP_MODALITY_VISION; - const bool is_audio = model.modality == CLIP_MODALITY_AUDIO; + const bool is_vision = model.modality == CLIP_MODALITY_VISION; + const bool is_audio = model.modality == CLIP_MODALITY_AUDIO; + const bool is_gen_audio = model.modality == CLIP_MODALITY_GEN_AUDIO; // other hparams { - const char * prefix = is_vision ? "vision" : "audio"; + const char * prefix = is_vision ? "vision" : (is_audio ? "audio" : "gen.audio"); get_u32(string_format(KEY_N_EMBD, prefix), hparams.n_embd); get_u32(string_format(KEY_N_HEAD, prefix), hparams.n_head); + get_u32(string_format(KEY_N_EMBD_HEAD, prefix), hparams.n_embd_head, false); get_u32(string_format(KEY_N_FF, prefix), hparams.n_ff); get_u32(string_format(KEY_N_BLOCK, prefix), hparams.n_layer); get_u32(string_format(KEY_PROJ_DIM, prefix), hparams.projection_dim); @@ -1197,6 +1244,7 @@ struct clip_model_loader { // n_head_kv is optional (for GQA), default to n_head hparams.n_head_kv = hparams.n_head; + get_u32(string_format(KEY_N_HEAD_KV, prefix), hparams.n_head_kv, false); if (is_vision) { get_u32(KEY_IMAGE_SIZE, hparams.image_size); @@ -1225,6 +1273,11 @@ struct clip_model_loader { hparams.image_size = 0; hparams.patch_size = 1; + } else if (is_gen_audio) { + // these are unused, but still need to be set to avoid issues + hparams.image_size = 0; + hparams.patch_size = 1; + } else { GGML_ASSERT(false && "unknown modality"); } @@ -1336,6 +1389,7 @@ struct clip_model_loader { // ViT merger 2x2 + final merger 2x2 = 4x spatial merge per dimension hparams.n_merge = 4; get_u32(KEY_PROJ_SCALE_FACTOR, hparams.n_merge, false); + GGML_ASSERT(hparams.n_merge == 2 || hparams.n_merge == 4); // borrow wa_layer_indexes for vit_merger insertion point std::vector wa_layer_indexes_vec; @@ -1645,6 +1699,33 @@ struct clip_model_loader { "%s: mimo_audio: %s must be > 0\n", __func__, KEY_A_LOCAL_GROUP_SIZE)); } } break; + case PROJECTOR_TYPE_QWEN3TTS_SPKENC: + { + // ECAPA-TDNN speaker encoder, mel front-end uses the Slaney default (fmin=0, fmax=sr/2) + hparams.audio_sample_rate = 24000; + hparams.audio_n_fft = 1024; + hparams.audio_window_len = 1024; + hparams.audio_hop_len = 256; + } break; + case PROJECTOR_TYPE_QWEN3TTS_GEN: + { + // TODO: hardcoded for now, read from code_predictor_config instead + hparams.rope_theta = 1000000.0f; + + // code2wav params + hparams.wav_tfm_n_layer = 8; + hparams.wav_tfm_n_embd = 512; + hparams.wav_tfm_n_ff = 1024; + hparams.wav_tfm_n_head = 16; + hparams.wav_tfm_n_head_kv = 16; + hparams.wav_tfm_eps = 1e-5f; + hparams.wav_tfm_rope_theta = 10000.0f; + hparams.wav_upsample_n_block = 2; + hparams.wav_dac_n_block = 4; + hparams.wav_dac_n_res = 3; + // matches the reference decoder's sliding_window (speech_tokenizer/config.json) + hparams.wav_tfm_swa = 72; + } break; case PROJECTOR_TYPE_PADDLEOCR: { hparams.n_merge = 2; @@ -1869,7 +1950,9 @@ struct clip_model_loader { } // TODO @ngxson : support both audio and video in the future - const char * prefix = model.modality == CLIP_MODALITY_AUDIO ? "a" : "v"; + const char * prefix = model.modality == CLIP_MODALITY_AUDIO ? "a" + : model.modality == CLIP_MODALITY_GEN_AUDIO ? "a.gen.code" + : "v"; // get offsets for (int64_t i = 0; i < gguf_get_n_tensors(ctx_gguf.get()); ++i) { @@ -1971,7 +2054,8 @@ struct clip_model_loader { model.position_embeddings = get_tensor(string_format(TN_POS_EMBD, prefix), false); const bool has_standard_layers = ( - model.proj_type != PROJECTOR_TYPE_GEMMA3NV); + model.proj_type != PROJECTOR_TYPE_GEMMA3NV && + model.proj_type != PROJECTOR_TYPE_QWEN3TTS_SPKENC); // layers const int n_layers_to_load = has_standard_layers ? hparams.n_layer : 0; @@ -2142,24 +2226,29 @@ struct clip_model_loader { } break; case PROJECTOR_TYPE_MINICPMV4_6: { + const bool merger_required = hparams.n_merge == 4; + auto get_merger_tensor = [&](const std::string & name, bool required = true) { + return get_tensor(name, merger_required && required); + }; + // ViT merger: window self-attention - model.vit_merger_ln1_w = get_tensor(string_format(TN_VIT_MERGER_LN1, "weight")); - model.vit_merger_ln1_b = get_tensor(string_format(TN_VIT_MERGER_LN1, "bias")); - model.vit_merger_attn_q_w = get_tensor(string_format(TN_VIT_MERGER_ATTN_Q, "weight")); - model.vit_merger_attn_q_b = get_tensor(string_format(TN_VIT_MERGER_ATTN_Q, "bias"), false); - model.vit_merger_attn_k_w = get_tensor(string_format(TN_VIT_MERGER_ATTN_K, "weight")); - model.vit_merger_attn_k_b = get_tensor(string_format(TN_VIT_MERGER_ATTN_K, "bias"), false); - model.vit_merger_attn_v_w = get_tensor(string_format(TN_VIT_MERGER_ATTN_V, "weight")); - model.vit_merger_attn_v_b = get_tensor(string_format(TN_VIT_MERGER_ATTN_V, "bias"), false); - model.vit_merger_attn_o_w = get_tensor(string_format(TN_VIT_MERGER_ATTN_O, "weight")); - model.vit_merger_attn_o_b = get_tensor(string_format(TN_VIT_MERGER_ATTN_O, "bias"), false); + model.vit_merger_ln1_w = get_merger_tensor(string_format(TN_VIT_MERGER_LN1, "weight")); + model.vit_merger_ln1_b = get_merger_tensor(string_format(TN_VIT_MERGER_LN1, "bias")); + model.vit_merger_attn_q_w = get_merger_tensor(string_format(TN_VIT_MERGER_ATTN_Q, "weight")); + model.vit_merger_attn_q_b = get_merger_tensor(string_format(TN_VIT_MERGER_ATTN_Q, "bias"), false); + model.vit_merger_attn_k_w = get_merger_tensor(string_format(TN_VIT_MERGER_ATTN_K, "weight")); + model.vit_merger_attn_k_b = get_merger_tensor(string_format(TN_VIT_MERGER_ATTN_K, "bias"), false); + model.vit_merger_attn_v_w = get_merger_tensor(string_format(TN_VIT_MERGER_ATTN_V, "weight")); + model.vit_merger_attn_v_b = get_merger_tensor(string_format(TN_VIT_MERGER_ATTN_V, "bias"), false); + model.vit_merger_attn_o_w = get_merger_tensor(string_format(TN_VIT_MERGER_ATTN_O, "weight")); + model.vit_merger_attn_o_b = get_merger_tensor(string_format(TN_VIT_MERGER_ATTN_O, "bias"), false); // ViT merger: MLP downsample - model.vit_merger_ds_ln_w = get_tensor(string_format(TN_VIT_MERGER_DS_LN, "weight")); - model.vit_merger_ds_ln_b = get_tensor(string_format(TN_VIT_MERGER_DS_LN, "bias")); - model.vit_merger_ds_up_w = get_tensor(string_format(TN_VIT_MERGER_DS_UP, "weight")); - model.vit_merger_ds_up_b = get_tensor(string_format(TN_VIT_MERGER_DS_UP, "bias"), false); - model.vit_merger_ds_down_w = get_tensor(string_format(TN_VIT_MERGER_DS_DOWN, "weight")); - model.vit_merger_ds_down_b = get_tensor(string_format(TN_VIT_MERGER_DS_DOWN, "bias"), false); + model.vit_merger_ds_ln_w = get_merger_tensor(string_format(TN_VIT_MERGER_DS_LN, "weight")); + model.vit_merger_ds_ln_b = get_merger_tensor(string_format(TN_VIT_MERGER_DS_LN, "bias")); + model.vit_merger_ds_up_w = get_merger_tensor(string_format(TN_VIT_MERGER_DS_UP, "weight")); + model.vit_merger_ds_up_b = get_merger_tensor(string_format(TN_VIT_MERGER_DS_UP, "bias"), false); + model.vit_merger_ds_down_w = get_merger_tensor(string_format(TN_VIT_MERGER_DS_DOWN, "weight")); + model.vit_merger_ds_down_b = get_merger_tensor(string_format(TN_VIT_MERGER_DS_DOWN, "bias"), false); // Final Merger (DownsampleMLP) model.mm_input_norm_w = get_tensor(TN_MM_INP_NORM); model.mm_input_norm_b = get_tensor(TN_MM_INP_NORM_B, false); @@ -2592,6 +2681,144 @@ struct clip_model_loader { model.mm_1_w = get_tensor(string_format(TN_MM_AUDIO_MLP, 1, "weight")); model.mm_2_w = get_tensor(string_format(TN_MM_AUDIO_MLP, 2, "weight")); } break; + case PROJECTOR_TYPE_QWEN3TTS_SPKENC: + { + // stem TDNN (block 0) + model.conv1d_1_w = get_tensor(string_format(TN_CONV1D, 0, "weight")); + model.conv1d_1_b = get_tensor(string_format(TN_CONV1D, 0, "bias")); + + // SE-Res2Net blocks (GGUF bid 1..3, one per hparams.n_layer) + model.layers.resize(hparams.n_layer); + for (int il = 0; il < hparams.n_layer; il++) { + auto & layer = model.layers[il]; + int bid = il + 1; + layer.conv_pw1_w = get_tensor(string_format(TN_CONV_PW1, prefix, bid, "weight")); + layer.conv_pw1_b = get_tensor(string_format(TN_CONV_PW1, prefix, bid, "bias")); + layer.conv_pw2_w = get_tensor(string_format(TN_CONV_PW2, prefix, bid, "weight")); + layer.conv_pw2_b = get_tensor(string_format(TN_CONV_PW2, prefix, bid, "bias")); + layer.se_conv1_w = get_tensor(string_format(TN_A_SE_CONV1, bid, "weight")); + layer.se_conv1_b = get_tensor(string_format(TN_A_SE_CONV1, bid, "bias")); + layer.se_conv2_w = get_tensor(string_format(TN_A_SE_CONV2, bid, "weight")); + layer.se_conv2_b = get_tensor(string_format(TN_A_SE_CONV2, bid, "bias")); + layer.res2_conv_w.resize(7); + layer.res2_conv_b.resize(7); + for (int xid = 0; xid < 7; xid++) { + layer.res2_conv_w[xid] = get_tensor(string_format(TN_A_CONV_RES2, bid, xid, "weight")); + layer.res2_conv_b[xid] = get_tensor(string_format(TN_A_CONV_RES2, bid, xid, "bias")); + } + } + + // multi-layer feature aggregation + model.conv_out_w = get_tensor(string_format(TN_CONV_OUT, "weight")); + model.conv_out_b = get_tensor(string_format(TN_CONV_OUT, "bias")); + + // attentive statistics pooling + model.spk_asp_attn_w = get_tensor(string_format(TN_A_ASP_ATTN, "weight")); + model.spk_asp_attn_b = get_tensor(string_format(TN_A_ASP_ATTN, "bias")); + model.spk_asp_tdnn_w = get_tensor(string_format(TN_A_ASP_TDNN, "weight")); + model.spk_asp_tdnn_b = get_tensor(string_format(TN_A_ASP_TDNN, "bias")); + + // final speaker embedding projection + model.mm_fc_w = get_tensor(string_format(TN_MM_AUDIO_FC, "weight")); + model.mm_fc_b = get_tensor(string_format(TN_MM_AUDIO_FC, "bias")); + } break; + case PROJECTOR_TYPE_QWEN3TTS_GEN: + { + // code_predictor + model.gen_code_proj_in_w = get_tensor(string_format(TN_A_GEN_CODE_PROJ_IN, "weight")); + model.gen_code_proj_in_b = get_tensor(string_format(TN_A_GEN_CODE_PROJ_IN, "bias")); + model.gen_code_embd_w = get_tensor(string_format(TN_A_GEN_CODE_EMBD, "weight")); + model.gen_code_head_w = get_tensor(string_format(TN_A_GEN_CODE_HEAD, "weight")); + model.gen_code_out_embd_w = get_tensor(string_format(TN_A_GEN_CODE_OUT_EMBD, "weight")); + model.gen_code_norm_w = get_tensor(string_format(TN_A_GEN_CODE_NORM, "weight")); + + // code2wav: RVQ codes -> raw PCM, lives in the same ctx as code_predictor + { + auto & c2w = model.c2w; + + c2w.quant_first_in_w = get_tensor(string_format(TN_A_GEN_WAV_QUANT_FIRST_IN, "weight")); + c2w.quant_first_out_w = get_tensor(string_format(TN_A_GEN_WAV_QUANT_FIRST_OUT, "weight")); + c2w.quant_first_cb_w = get_tensor(string_format(TN_A_GEN_WAV_QUANT_FIRST_CB, "weight")); + c2w.quant_rest_in_w = get_tensor(string_format(TN_A_GEN_WAV_QUANT_REST_IN, "weight")); + c2w.quant_rest_out_w = get_tensor(string_format(TN_A_GEN_WAV_QUANT_REST_OUT, "weight")); + c2w.quant_rest_cb_w = get_tensor(string_format(TN_A_GEN_WAV_QUANT_REST_CB, "weight")); + + c2w.pre_conv_w = get_tensor(string_format(TN_A_GEN_WAV_PRE_CONV, "weight")); + c2w.pre_conv_b = get_tensor(string_format(TN_A_GEN_WAV_PRE_CONV, "bias")); + + c2w.tfm_in_proj_w = get_tensor(string_format(TN_A_GEN_WAV_TFM_IN_PROJ, "weight")); + c2w.tfm_in_proj_b = get_tensor(string_format(TN_A_GEN_WAV_TFM_IN_PROJ, "bias")); + c2w.tfm_out_proj_w = get_tensor(string_format(TN_A_GEN_WAV_TFM_OUT_PROJ, "weight")); + c2w.tfm_out_proj_b = get_tensor(string_format(TN_A_GEN_WAV_TFM_OUT_PROJ, "bias")); + c2w.tfm_output_norm_w = get_tensor(string_format(TN_A_GEN_WAV_TFM_OUT_NORM, "weight")); + + // loaded manually, the generic model.layers loop is taken by code_predictor + c2w.tfm_layers.resize(hparams.wav_tfm_n_layer); + for (int il = 0; il < hparams.wav_tfm_n_layer; il++) { + auto & layer = c2w.tfm_layers[il]; + const char * p = "a.gen.wav.tfm"; + layer.q_w = get_tensor(string_format(TN_ATTN_Q, p, il, "weight")); + layer.k_w = get_tensor(string_format(TN_ATTN_K, p, il, "weight")); + layer.v_w = get_tensor(string_format(TN_ATTN_V, p, il, "weight")); + layer.o_w = get_tensor(string_format(TN_ATTN_OUTPUT, p, il, "weight")); + layer.ln_1_w = get_tensor(string_format(TN_LN_1, p, il, "weight")); + layer.ln_2_w = get_tensor(string_format(TN_LN_2, p, il, "weight")); + layer.ls_1_w = get_tensor(string_format(TN_LS_1, p, il, "weight")); + layer.ls_2_w = get_tensor(string_format(TN_LS_2, p, il, "weight")); + layer.ff_gate_w = get_tensor(string_format(TN_FFN_GATE, p, il, "weight")); + layer.ff_up_w = get_tensor(string_format(TN_FFN_UP, p, il, "weight")); + layer.ff_down_w = get_tensor(string_format(TN_FFN_DOWN, p, il, "weight")); + } + + // upsample: 2x (causal ConvTranspose1d + ConvNeXt block) + c2w.upsample.resize(hparams.wav_upsample_n_block); + for (int il = 0; il < hparams.wav_upsample_n_block; il++) { + auto & up = c2w.upsample[il]; + up.conv_w = get_tensor(string_format(TN_A_GEN_WAV_UP_CONV, il, "weight")); + up.conv_b = get_tensor(string_format(TN_A_GEN_WAV_UP_CONV, il, "bias")); + up.dwconv_w = get_tensor(string_format(TN_A_GEN_WAV_UP_DWCONV, il, "weight")); + up.dwconv_b = get_tensor(string_format(TN_A_GEN_WAV_UP_DWCONV, il, "bias")); + up.norm_w = get_tensor(string_format(TN_A_GEN_WAV_UP_NORM, il, "weight")); + up.norm_b = get_tensor(string_format(TN_A_GEN_WAV_UP_NORM, il, "bias")); + up.pw1_w = get_tensor(string_format(TN_A_GEN_WAV_UP_PW1, il, "weight")); + up.pw1_b = get_tensor(string_format(TN_A_GEN_WAV_UP_PW1, il, "bias")); + up.pw2_w = get_tensor(string_format(TN_A_GEN_WAV_UP_PW2, il, "weight")); + up.pw2_b = get_tensor(string_format(TN_A_GEN_WAV_UP_PW2, il, "bias")); + up.gamma = get_tensor(string_format(TN_A_GEN_WAV_UP_GAMMA, il)); + } + + // DAC decoder: conv_pre + n upsample blocks (each with n_res residual units) + conv_post + c2w.dac_entry_w = get_tensor(string_format(TN_A_GEN_WAV_DAC_ENTRY, "weight")); + c2w.dac_entry_b = get_tensor(string_format(TN_A_GEN_WAV_DAC_ENTRY, "bias")); + + c2w.dac.resize(hparams.wav_dac_n_block); + for (int il = 0; il < hparams.wav_dac_n_block; il++) { + auto & blk = c2w.dac[il]; + blk.snake_alpha = get_tensor(string_format(TN_A_GEN_WAV_DAC_SNAKE, il, "alpha")); + blk.snake_beta = get_tensor(string_format(TN_A_GEN_WAV_DAC_SNAKE, il, "beta")); + blk.conv_w = get_tensor(string_format(TN_A_GEN_WAV_DAC_CONV, il, "weight")); + blk.conv_b = get_tensor(string_format(TN_A_GEN_WAV_DAC_CONV, il, "bias")); + + blk.res.resize(hparams.wav_dac_n_res); + for (int ir = 0; ir < hparams.wav_dac_n_res; ir++) { + auto & res = blk.res[ir]; + res.act1_alpha = get_tensor(string_format(TN_A_GEN_WAV_DAC_RES_ACT1, il, ir, "alpha")); + res.act1_beta = get_tensor(string_format(TN_A_GEN_WAV_DAC_RES_ACT1, il, ir, "beta")); + res.conv1_w = get_tensor(string_format(TN_A_GEN_WAV_DAC_RES_CONV1, il, ir, "weight")); + res.conv1_b = get_tensor(string_format(TN_A_GEN_WAV_DAC_RES_CONV1, il, ir, "bias")); + res.act2_alpha = get_tensor(string_format(TN_A_GEN_WAV_DAC_RES_ACT2, il, ir, "alpha")); + res.act2_beta = get_tensor(string_format(TN_A_GEN_WAV_DAC_RES_ACT2, il, ir, "beta")); + res.conv2_w = get_tensor(string_format(TN_A_GEN_WAV_DAC_RES_CONV2, il, ir, "weight")); + res.conv2_b = get_tensor(string_format(TN_A_GEN_WAV_DAC_RES_CONV2, il, ir, "bias")); + } + } + + c2w.dac_post_snake_alpha = get_tensor(string_format(TN_A_GEN_WAV_DAC_POST_SNAKE, "alpha")); + c2w.dac_post_snake_beta = get_tensor(string_format(TN_A_GEN_WAV_DAC_POST_SNAKE, "beta")); + c2w.dac_post_conv_w = get_tensor(string_format(TN_A_GEN_WAV_DAC_POST_CONV, "weight")); + c2w.dac_post_conv_b = get_tensor(string_format(TN_A_GEN_WAV_DAC_POST_CONV, "bias")); + } + } break; case PROJECTOR_TYPE_VOXTRAL: { model.conv1d_1_w = get_tensor(string_format(TN_CONV1D, 1, "weight")); @@ -3420,6 +3647,7 @@ struct clip_model_loader { struct clip_init_result clip_init(const char * fname, struct clip_context_params ctx_params) { clip_ctx * ctx_vision = nullptr; clip_ctx * ctx_audio = nullptr; + clip_ctx * ctx_gen_audio = nullptr; try { clip_model_loader loader(fname, @@ -3452,16 +3680,25 @@ struct clip_init_result clip_init(const char * fname, struct clip_context_params } } + if (loader.has_gen_audio) { + ctx_gen_audio = new clip_ctx(ctx_params); + loader.load_hparams(ctx_gen_audio->model, CLIP_MODALITY_GEN_AUDIO); + loader.load_tensors(*ctx_gen_audio); + // TODO: fix warmup + ctx_gen_audio->buf_compute_meta.resize(ctx_gen_audio->max_nodes * ggml_tensor_overhead() + ggml_graph_overhead()); + } + } catch (const std::exception & e) { LOG_ERR("%s: failed to load model '%s': %s\n", __func__, fname, e.what()); delete ctx_vision; delete ctx_audio; + delete ctx_gen_audio; - return {nullptr, nullptr}; + return {nullptr, nullptr, nullptr}; } - return {ctx_vision, ctx_audio}; + return {ctx_vision, ctx_audio, ctx_gen_audio}; } struct clip_cap clip_get_cap(const char * fname) { @@ -3590,8 +3827,7 @@ int clip_n_output_tokens(const clip_ctx * ctx, const clip_image_f32 * img) { } break; case PROJECTOR_TYPE_MINICPMV4_6: { - // ViT merger 4x + final merger 4x = 16x total spatial downsample - n_patches = n_patches / 16; + n_patches /= params.n_merge * params.n_merge; } break; case PROJECTOR_TYPE_QWEN2VL: case PROJECTOR_TYPE_QWEN25VL: @@ -3778,6 +4014,16 @@ int clip_n_output_tokens(const clip_ctx * ctx, const clip_image_f32 * img) { const int ds = ctx->model.hparams.audio_proj_downsample_rate; n_patches = ((img->nx() + ws - 1) / ws) * (ws / ds); } break; + case PROJECTOR_TYPE_QWEN3TTS_SPKENC: + { + // pooling gives one speaker embedding, whatever the clip length is + n_patches = 1; + } break; + case PROJECTOR_TYPE_QWEN3TTS_GEN: + { + // one hidden-state vector fed back to the talker per call + n_patches = 1; + } break; case PROJECTOR_TYPE_GRANITE4_VISION: { // Per-tile output token count: each projector block outputs @@ -3811,7 +4057,16 @@ bool clip_image_encode(struct clip_ctx * ctx, int n_threads, const clip_image_f3 } bool clip_image_batch_encode(clip_ctx * ctx, int n_threads, const clip_image_f32_batch * imgs_c_ptr, std::vector & out_batch_embd) { - const clip_image_f32_batch & imgs = *imgs_c_ptr; + clip_encode_params params; + params.imgs = imgs_c_ptr; + params.n_threads = n_threads; + params.out_embd = &out_batch_embd; + + return clip_encode(ctx, ¶ms); +} + +bool clip_encode(struct clip_ctx * ctx, struct clip_encode_params * params) { + const clip_image_f32_batch & imgs = *params->imgs; int n_batch_cur = imgs.entries.size(); // [QWEN_VIDEO] for video models, the batch dimension is used as temporal dimension for merged frames @@ -3822,12 +4077,12 @@ bool clip_image_batch_encode(clip_ctx * ctx, int n_threads, const clip_image_f32 // if buffers are not allocated, we need to do a warmup run to allocate them if (!ctx->is_allocated) { - clip_model_loader::warmup(*ctx, *imgs_c_ptr); + clip_model_loader::warmup(*ctx, *params->imgs); } // build the inference graph ggml_backend_sched_reset(ctx->sched.get()); - ggml_cgraph * gf = clip_get_graph_builder(ctx, imgs)->build(); + ggml_cgraph * gf = clip_get_graph_builder(ctx, imgs, params)->build(); ggml_backend_sched_alloc_graph(ctx->sched.get(), gf); // set inputs @@ -3912,8 +4167,8 @@ bool clip_image_batch_encode(clip_ctx * ctx, int n_threads, const clip_image_f32 } set_input_f32("inp_raw", inp_raw); - } else { - // audio input + } else if (!(ctx->proj_type() == PROJECTOR_TYPE_QWEN3TTS_GEN && params->gen_process == CLIP_GEN_PROCESS_GEN_WAV)) { + // audio input, code2wav is not here: its only input is "inp_codes", set in the switch below GGML_ASSERT(imgs.entries.size() == 1); const auto & mel_inp = imgs.entries[0]; @@ -3973,6 +4228,8 @@ bool clip_image_batch_encode(clip_ctx * ctx, int n_threads, const clip_image_f32 } break; case PROJECTOR_TYPE_MINICPMV4_6: { + const bool is_4x = hparams.n_merge == 2; + // SigLIP position buckets (same as resampler path) std::vector positions(pos_h * pos_w); int bucket_coords_h[1024]; @@ -3993,40 +4250,6 @@ bool clip_image_batch_encode(clip_ctx * ctx, int n_threads, const clip_image_f32 const int half_h = pos_h / 2; const int half_w = pos_w / 2; - // window reorder indices for 2x2 windows - std::vector window_idx(n_pos); - std::vector inv_window_idx(n_pos); - { - int k = 0; - for (int wi = 0; wi < half_h; wi++) { - for (int wj = 0; wj < half_w; wj++) { - window_idx[k++] = (2*wi ) * pos_w + (2*wj ); - window_idx[k++] = (2*wi ) * pos_w + (2*wj + 1); - window_idx[k++] = (2*wi + 1) * pos_w + (2*wj ); - window_idx[k++] = (2*wi + 1) * pos_w + (2*wj + 1); - } - } - for (int i = 0; i < n_pos; i++) { - inv_window_idx[window_idx[i]] = i; - } - } - set_input_i32("vit_merger_window_idx", window_idx); - set_input_i32("vit_merger_inv_window_idx", inv_window_idx); - - // block-diagonal attention mask: tokens in the same 4-token - // window attend to each other (mask = 0), all other positions - // are masked out (-inf). matches the window-major reorder above. - std::vector window_mask_data(n_pos * n_pos, std::numeric_limits::lowest()); - for (int wi = 0; wi < n_pos / 4; wi++) { - for (int i = 0; i < 4; i++) { - for (int j = 0; j < 4; j++) { - window_mask_data[(wi*4 + i) * n_pos + (wi*4 + j)] = 0.0f; - } - } - } - set_input_f32("vit_merger_window_mask", window_mask_data); - - // ViT merger 2x2 downsample indices auto make_ds_idx = [](int off_r, int off_c, int ds_h, int ds_w, int stride_w) { std::vector idx(ds_h * ds_w); for (int i = 0; i < ds_h; i++) { @@ -4036,22 +4259,58 @@ bool clip_image_batch_encode(clip_ctx * ctx, int n_threads, const clip_image_f32 } return idx; }; - auto vit_merger_ds_0 = make_ds_idx(0, 0, half_h, half_w, pos_w); - auto vit_merger_ds_1 = make_ds_idx(0, 1, half_h, half_w, pos_w); - auto vit_merger_ds_2 = make_ds_idx(1, 0, half_h, half_w, pos_w); - auto vit_merger_ds_3 = make_ds_idx(1, 1, half_h, half_w, pos_w); - set_input_i32("vit_merger_ds_idx_0", vit_merger_ds_0); - set_input_i32("vit_merger_ds_idx_1", vit_merger_ds_1); - set_input_i32("vit_merger_ds_idx_2", vit_merger_ds_2); - set_input_i32("vit_merger_ds_idx_3", vit_merger_ds_3); - - // final merger 2x2 downsample indices (operates on half_h x half_w grid) - const int qh = half_h / 2; - const int qw = half_w / 2; - auto m_ds_0 = make_ds_idx(0, 0, qh, qw, half_w); - auto m_ds_1 = make_ds_idx(0, 1, qh, qw, half_w); - auto m_ds_2 = make_ds_idx(1, 0, qh, qw, half_w); - auto m_ds_3 = make_ds_idx(1, 1, qh, qw, half_w); + + if (!is_4x) { + // window reorder indices for 2x2 windows + std::vector window_idx(n_pos); + std::vector inv_window_idx(n_pos); + { + int k = 0; + for (int wi = 0; wi < half_h; wi++) { + for (int wj = 0; wj < half_w; wj++) { + window_idx[k++] = (2*wi ) * pos_w + (2*wj ); + window_idx[k++] = (2*wi ) * pos_w + (2*wj + 1); + window_idx[k++] = (2*wi + 1) * pos_w + (2*wj ); + window_idx[k++] = (2*wi + 1) * pos_w + (2*wj + 1); + } + } + for (int i = 0; i < n_pos; i++) { + inv_window_idx[window_idx[i]] = i; + } + } + set_input_i32("vit_merger_window_idx", window_idx); + set_input_i32("vit_merger_inv_window_idx", inv_window_idx); + + // block-diagonal attention mask: tokens in the same 4-token + // window attend to each other (mask = 0), all other positions + // are masked out (-inf). matches the window-major reorder above. + std::vector window_mask_data(n_pos * n_pos, std::numeric_limits::lowest()); + for (int wi = 0; wi < n_pos / 4; wi++) { + for (int i = 0; i < 4; i++) { + for (int j = 0; j < 4; j++) { + window_mask_data[(wi*4 + i) * n_pos + (wi*4 + j)] = 0.0f; + } + } + } + set_input_f32("vit_merger_window_mask", window_mask_data); + + // ViT merger 2x2 downsample indices + auto vit_merger_ds_0 = make_ds_idx(0, 0, half_h, half_w, pos_w); + auto vit_merger_ds_1 = make_ds_idx(0, 1, half_h, half_w, pos_w); + auto vit_merger_ds_2 = make_ds_idx(1, 0, half_h, half_w, pos_w); + auto vit_merger_ds_3 = make_ds_idx(1, 1, half_h, half_w, pos_w); + set_input_i32("vit_merger_ds_idx_0", vit_merger_ds_0); + set_input_i32("vit_merger_ds_idx_1", vit_merger_ds_1); + set_input_i32("vit_merger_ds_idx_2", vit_merger_ds_2); + set_input_i32("vit_merger_ds_idx_3", vit_merger_ds_3); + } + + const int merger_h = is_4x ? pos_h : half_h; + const int merger_w = is_4x ? pos_w : half_w; + auto m_ds_0 = make_ds_idx(0, 0, merger_h / 2, merger_w / 2, merger_w); + auto m_ds_1 = make_ds_idx(0, 1, merger_h / 2, merger_w / 2, merger_w); + auto m_ds_2 = make_ds_idx(1, 0, merger_h / 2, merger_w / 2, merger_w); + auto m_ds_3 = make_ds_idx(1, 1, merger_h / 2, merger_w / 2, merger_w); set_input_i32("merger_ds_idx_0", m_ds_0); set_input_i32("merger_ds_idx_1", m_ds_1); set_input_i32("merger_ds_idx_2", m_ds_2); @@ -4465,9 +4724,77 @@ bool clip_image_batch_encode(clip_ctx * ctx, int n_threads, const clip_image_f32 case PROJECTOR_TYPE_COGVLM: case PROJECTOR_TYPE_YASA2: case PROJECTOR_TYPE_GEMMA4UA: + case PROJECTOR_TYPE_QWEN3TTS_SPKENC: { // do nothing } break; + case PROJECTOR_TYPE_QWEN3TTS_GEN: + { + if (params->gen_process == CLIP_GEN_PROCESS_GEN_WAV) { + GGML_ASSERT(params->codes != nullptr); + + // frame-major input to group-major, rear-padded with code 0 up to one window + const int64_t n_codes = model.gen_code_head_w->ne[2] + 1; + const int64_t n_frames_w = hparams.wav_tfm_swa; + const int64_t n_frames = (int64_t) params->codes->size() / n_codes; + GGML_ASSERT(n_frames > 0 && n_frames <= n_frames_w); + + // codes are used as ggml_get_rows indices, so check them against the codebook vocab + const int64_t vocab_first = model.c2w.quant_first_cb_w->ne[1]; + const int64_t vocab_rest = model.c2w.quant_rest_cb_w->ne[1]; + for (int64_t f = 0; f < n_frames; f++) { + for (int64_t g = 0; g < n_codes; g++) { + const int32_t c = (*params->codes)[f * n_codes + g]; + const int64_t vocab = (g == 0) ? vocab_first : vocab_rest; + if (c < 0 || (int64_t) c >= vocab) { + LOG_ERR("%s: code out of range (frame %lld, group %lld, code %d, vocab %lld)\n", + __func__, (long long) f, (long long) g, c, (long long) vocab); + return false; + } + } + } + + std::vector codes(n_frames_w * n_codes, 0); + for (int64_t f = 0; f < n_frames; f++) { + for (int64_t g = 0; g < n_codes; g++) { + codes[g * n_frames_w + f] = (*params->codes)[f * n_codes + g]; + } + } + set_input_i32("inp_codes", codes); + + // upload the state from the previous call, or zero-fill on a cold start + size_t offset = 0; + for (const auto & slot : list_c2w_state_slots(hparams, model)) { + ggml_tensor * t = get_inp_tensor(("state_in_" + slot.name).c_str()); + const size_t nb = ggml_nbytes(t); + if (params->state_in && params->state_in->size() >= offset + nb) { + ggml_backend_tensor_set(t, params->state_in->data() + offset, 0, nb); + } else { + std::vector zeros(nb, 0); + ggml_backend_tensor_set(t, zeros.data(), 0, nb); + } + offset += nb; + } + } else { + // code0 indexes gen_code_out_embd_w via ggml_get_rows; bound it + const int64_t vocab0 = model.gen_code_out_embd_w->ne[1]; + if (params->code0 < 0 || (int64_t) params->code0 >= vocab0) { + LOG_ERR("%s: code0 out of range (%d, vocab %lld)\n", __func__, params->code0, (long long) vocab0); + return false; + } + std::vector code0 = { params->code0 }; + set_input_i32("inp_code0", code0); + + // one uniform(0,1) draw per codebook, used by do_sampling() + static std::mt19937 rng{ std::random_device{}() }; + std::uniform_real_distribution dist(0.0f, 1.0f); + const int64_t n_acoustic = model.gen_code_head_w->ne[2]; + for (int64_t g = 0; g < n_acoustic; g++) { + std::vector r = { dist(rng) }; + set_input_f32(("inp_rand_" + std::to_string(g)).c_str(), r); + } + } + } break; case PROJECTOR_TYPE_HUNYUANVL: { // Compute the HunyuanVL 2D position embedding on CPU (with the @@ -4873,7 +5200,7 @@ bool clip_image_batch_encode(clip_ctx * ctx, int n_threads, const clip_image_f32 if (reg) { auto ggml_backend_set_n_threads_fn = (ggml_backend_set_n_threads_t) ggml_backend_reg_get_proc_address(reg, "ggml_backend_set_n_threads"); if (ggml_backend_set_n_threads_fn) { - ggml_backend_set_n_threads_fn(ctx->backend_cpu, n_threads); + ggml_backend_set_n_threads_fn(ctx->backend_cpu, params->n_threads); } } @@ -4883,34 +5210,90 @@ bool clip_image_batch_encode(clip_ctx * ctx, int n_threads, const clip_image_f32 return false; } - // the last node is the embedding tensor - ggml_tensor * embeddings = ggml_graph_node(gf, -1); + // the last node is the embedding tensor, code2wav has no out_embd + ggml_tensor * embeddings = params->out_embd ? ggml_graph_node(gf, -1) : nullptr; + + if (embeddings != nullptr) { + // sanity check (assuming that all images in batch have the same number of tokens, so we only check the first one) + const int n_tokens_out = embeddings->ne[1]; + const int expected_n_tokens_out = clip_n_output_tokens(ctx, &imgs.entries[0]); + if (n_tokens_out != expected_n_tokens_out) { + LOG_ERR("%s: expected output %d tokens, got %d\n", __func__, expected_n_tokens_out, n_tokens_out); + GGML_ABORT("Invalid number of output tokens"); + } + + LOG_DBG("%s: output embedding shape [%d, %d, %d]\n", __func__, + (int)embeddings->ne[0], (int)embeddings->ne[1], (int)embeddings->ne[2]); - // sanity check (assuming that all images in batch have the same number of tokens, so we only check the first one) - const int n_tokens_out = embeddings->ne[1]; - const int expected_n_tokens_out = clip_n_output_tokens(ctx, &imgs.entries[0]); - if (n_tokens_out != expected_n_tokens_out) { - LOG_ERR("%s: expected output %d tokens, got %d\n", __func__, expected_n_tokens_out, n_tokens_out); - GGML_ABORT("Invalid number of output tokens"); + // copy output to user buffer if provided + // if output is empty, skip the copy + auto & out_batch_embd = *params->out_embd; + if (!out_batch_embd.empty()) { + if (out_batch_embd.size() != (size_t)ggml_nelements(embeddings)) { + LOG_ERR("%s: output buffer has %zu elements but expected %zu\n", __func__, out_batch_embd.size(), (size_t)ggml_nelements(embeddings)); + GGML_ABORT("Output buffer size mismatch"); + } + ggml_backend_tensor_get(embeddings, out_batch_embd.data(), 0, ggml_nbytes(embeddings)); + } else { + LOG_WRN("%s: output buffer is empty, skipping copy\n", __func__); + } } - LOG_DBG("%s: output embedding shape [%d, %d, %d]\n", __func__, - (int)embeddings->ne[0], (int)embeddings->ne[1], (int)embeddings->ne[2]); + // + // for audio gen models + // - // copy output to user buffer if provided - // if output is empty, skip the copy - if (!out_batch_embd.empty()) { - if (out_batch_embd.size() != (size_t)ggml_nelements(embeddings)) { - LOG_ERR("%s: output buffer has %zu elements but expected %zu\n", __func__, out_batch_embd.size(), (size_t)ggml_nelements(embeddings)); - GGML_ABORT("Output buffer size mismatch"); + if (params->out_codes != nullptr) { + ggml_tensor * codes = ggml_graph_get_tensor(gf, "out_codes"); + if (codes == nullptr) { + GGML_ABORT("out_codes requested but graph has no \"out_codes\" tensor"); + } + auto & out_codes = *params->out_codes; + out_codes.resize(ggml_nelements(codes)); + ggml_backend_tensor_get(codes, out_codes.data(), 0, ggml_nbytes(codes)); + } + if (params->out_audio != nullptr) { + ggml_tensor * audio = ggml_graph_get_tensor(gf, "out_audio"); + if (audio == nullptr) { + GGML_ABORT("out_audio requested but graph has no \"out_audio\" tensor"); + } + auto & out_audio = *params->out_audio; + out_audio.resize(ggml_nelements(audio)); + ggml_backend_tensor_get(audio, out_audio.data(), 0, ggml_nbytes(audio)); + + // drop the tail audio that comes from the code-0 rear padding + const int64_t n_codes = model.gen_code_head_w->ne[2] + 1; + const int64_t n_frames_w = hparams.wav_tfm_swa; + const int64_t n_frames = (int64_t) params->codes->size() / n_codes; + if (n_frames < n_frames_w) { + const size_t hop = out_audio.size() / n_frames_w; + out_audio.resize((size_t) n_frames * hop); + } + } + if (params->state_out != nullptr) { + auto & state_out = *params->state_out; + size_t total = 0; + for (const auto & slot : list_c2w_state_slots(hparams, model)) { + total += (size_t) (slot.ne0 * slot.ne1) * sizeof(float); + } + state_out.resize(total); + size_t offset = 0; + for (const auto & slot : list_c2w_state_slots(hparams, model)) { + ggml_tensor * t = ggml_graph_get_tensor(gf, ("state_out_" + slot.name).c_str()); + if (t == nullptr) { + GGML_ABORT("state_out requested but graph has no \"state_out_%s\" tensor", slot.name.c_str()); + } + const size_t nb = ggml_nbytes(t); + ggml_backend_tensor_get(t, state_out.data() + offset, 0, nb); + offset += nb; } - ggml_backend_tensor_get(embeddings, out_batch_embd.data(), 0, ggml_nbytes(embeddings)); - } else { - LOG_WRN("%s: output buffer is empty, skipping copy\n", __func__); } + // // Debug: dump final embeddings if MTMD_DEBUG_EMBEDDINGS is set - if (ctx->debug_output_embeddings) { + // + + if (ctx->debug_output_embeddings && embeddings != nullptr) { const int64_t n_embd = embeddings->ne[0]; const int64_t n_tokens = embeddings->ne[1]; std::vector emb_data(ggml_nelements(embeddings)); @@ -5037,6 +5420,10 @@ int clip_n_mmproj_embd(const struct clip_ctx * ctx) { return ctx->model.mm_ffn_down_w->ne[1]; case PROJECTOR_TYPE_MIMO_AUDIO: return ctx->model.mm_2_w->ne[1]; + case PROJECTOR_TYPE_QWEN3TTS_SPKENC: + return ctx->model.mm_fc_w->ne[2]; + case PROJECTOR_TYPE_QWEN3TTS_GEN: + return ctx->model.gen_code_out_embd_w->ne[0]; case PROJECTOR_TYPE_PARAKEET: return ctx->model.mm_1_w->ne[1]; default: diff --git a/tools/mtmd/clip.h b/tools/mtmd/clip.h index 967093a812d6..7f706d976eb3 100644 --- a/tools/mtmd/clip.h +++ b/tools/mtmd/clip.h @@ -37,6 +37,7 @@ struct clip_image_f32_batch; enum clip_modality { CLIP_MODALITY_VISION, CLIP_MODALITY_AUDIO, + CLIP_MODALITY_GEN_AUDIO, }; enum clip_flash_attn_type { @@ -61,6 +62,7 @@ struct clip_context_params { struct clip_init_result { struct clip_ctx * ctx_v; // vision context struct clip_ctx * ctx_a; // audio context + struct clip_ctx * ctx_gen_a; // audio generation context }; struct clip_init_result clip_init(const char * fname, struct clip_context_params ctx_params); @@ -84,6 +86,33 @@ int clip_n_mmproj_embd(const struct clip_ctx * ctx); bool clip_image_encode (struct clip_ctx * ctx, int n_threads, const clip_image_f32 * img, std::vector & out_vec); bool clip_image_batch_encode(struct clip_ctx * ctx, int n_threads, const struct clip_image_f32_batch * imgs, std::vector & out_batch_embd); +enum clip_gen_process_type { + CLIP_GEN_PROCESS_GEN_UNKNOWN, + CLIP_GEN_PROCESS_GEN_CODE, // h_state to codes + CLIP_GEN_PROCESS_GEN_WAV, // codes to raw PCM audio +}; +struct clip_encode_params { + int n_threads = 1; + const clip_image_f32_batch * imgs = nullptr; + std::vector * out_embd = nullptr; + + // for audio gen, imgs has exactly one entry: hidden state from backbone (GEN_CODE) or unused (GEN_WAV) + clip_gen_process_type gen_process = CLIP_GEN_PROCESS_GEN_UNKNOWN; + + // GEN_CODE: out_embd receives the embd to feed back to the backbone + int32_t code0 = 0; // semantic code sampled by the backbone + int32_t top_k = 50; + float top_p = 1.0f; + std::vector * out_codes = nullptr; // this frame's 16 sampled codes + + // GEN_WAV + const std::vector * codes = nullptr; // this frame's 16 RVQ codes + std::vector * out_audio = nullptr; // decoded PCM samples, F32 + const std::vector * state_in = nullptr; // state from previous call, null or wrong size means cold start + std::vector * state_out = nullptr; // state for the next call +}; +bool clip_encode(struct clip_ctx * ctx, struct clip_encode_params * params); + bool clip_is_llava(const struct clip_ctx * ctx); // note for contributor: this clip_is_(model) pattern is deprecated // do NOT add new functions like this diff --git a/tools/mtmd/models/minicpmv.cpp b/tools/mtmd/models/minicpmv.cpp index bac087ffdfce..3e9c4c2a1114 100644 --- a/tools/mtmd/models/minicpmv.cpp +++ b/tools/mtmd/models/minicpmv.cpp @@ -114,14 +114,12 @@ ggml_cgraph * clip_graph_minicpmv::build() { } ggml_cgraph * clip_graph_minicpmv4_6::build() { - const int insert_lid = hparams.insert_layer_id; - const int n_pos = n_patches; - const int half_h = n_patches_y / 2; - const int half_w = n_patches_x / 2; - const int n_ds = half_h * half_w; // after ViT merger 2x2 downsample - const int qh = half_h / 2; - const int qw = half_w / 2; - const int n_ds2 = qh * qw; // after final merger 2x2 downsample + const bool is_4x = hparams.n_merge == 2; + const int n_pos = n_patches; + const int half_h = n_patches_y / 2; + const int half_w = n_patches_x / 2; + const int n_ds = half_h * half_w; + const int n_out = is_4x ? n_ds : (half_h / 2) * (half_w / 2); auto add_i32_input = [&](const char * name, int n) { ggml_tensor * t = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n); @@ -134,29 +132,39 @@ ggml_cgraph * clip_graph_minicpmv4_6::build() { ggml_tensor * positions = add_i32_input("positions", n_pos); ggml_tensor * learned_pos_embd = ggml_get_rows(ctx0, model.position_embeddings, positions); - // ViT merger window reorder indices + block-diagonal mask - // (mask layout follows qwen2vl: -inf except for 4x4 blocks on the diagonal, - // so each window-major group of 4 tokens only attends to itself) - ggml_tensor * vit_merger_window_idx = add_i32_input("vit_merger_window_idx", n_pos); - ggml_tensor * vit_merger_inv_window_idx = add_i32_input("vit_merger_inv_window_idx", n_pos); - ggml_tensor * vit_merger_window_mask = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_pos, n_pos); - ggml_set_name(vit_merger_window_mask, "vit_merger_window_mask"); - ggml_set_input(vit_merger_window_mask); - if (flash_attn_type == CLIP_FLASH_ATTN_TYPE_ENABLED) { - vit_merger_window_mask = ggml_cast(ctx0, vit_merger_window_mask, GGML_TYPE_F16); - } + ggml_tensor * vit_merger_window_idx = nullptr; + ggml_tensor * vit_merger_inv_window_idx = nullptr; + ggml_tensor * vit_merger_window_mask = nullptr; + ggml_tensor * vit_merger_ds_idx_0 = nullptr; + ggml_tensor * vit_merger_ds_idx_1 = nullptr; + ggml_tensor * vit_merger_ds_idx_2 = nullptr; + ggml_tensor * vit_merger_ds_idx_3 = nullptr; + + if (!is_4x) { + // ViT merger window reorder indices + block-diagonal mask + // (mask layout follows qwen2vl: -inf except for 4x4 blocks on the diagonal, + // so each window-major group of 4 tokens only attends to itself) + vit_merger_window_idx = add_i32_input("vit_merger_window_idx", n_pos); + vit_merger_inv_window_idx = add_i32_input("vit_merger_inv_window_idx", n_pos); + vit_merger_window_mask = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_pos, n_pos); + ggml_set_name(vit_merger_window_mask, "vit_merger_window_mask"); + ggml_set_input(vit_merger_window_mask); + if (flash_attn_type == CLIP_FLASH_ATTN_TYPE_ENABLED) { + vit_merger_window_mask = ggml_cast(ctx0, vit_merger_window_mask, GGML_TYPE_F16); + } - // ViT merger 2x2 downsample gather indices - ggml_tensor * vit_merger_ds_idx_0 = add_i32_input("vit_merger_ds_idx_0", n_ds); - ggml_tensor * vit_merger_ds_idx_1 = add_i32_input("vit_merger_ds_idx_1", n_ds); - ggml_tensor * vit_merger_ds_idx_2 = add_i32_input("vit_merger_ds_idx_2", n_ds); - ggml_tensor * vit_merger_ds_idx_3 = add_i32_input("vit_merger_ds_idx_3", n_ds); + // ViT merger 2x2 downsample gather indices + vit_merger_ds_idx_0 = add_i32_input("vit_merger_ds_idx_0", n_ds); + vit_merger_ds_idx_1 = add_i32_input("vit_merger_ds_idx_1", n_ds); + vit_merger_ds_idx_2 = add_i32_input("vit_merger_ds_idx_2", n_ds); + vit_merger_ds_idx_3 = add_i32_input("vit_merger_ds_idx_3", n_ds); + } // final merger 2x2 downsample gather indices - ggml_tensor * merger_ds_idx_0 = add_i32_input("merger_ds_idx_0", n_ds2); - ggml_tensor * merger_ds_idx_1 = add_i32_input("merger_ds_idx_1", n_ds2); - ggml_tensor * merger_ds_idx_2 = add_i32_input("merger_ds_idx_2", n_ds2); - ggml_tensor * merger_ds_idx_3 = add_i32_input("merger_ds_idx_3", n_ds2); + ggml_tensor * merger_ds_idx_0 = add_i32_input("merger_ds_idx_0", n_out); + ggml_tensor * merger_ds_idx_1 = add_i32_input("merger_ds_idx_1", n_out); + ggml_tensor * merger_ds_idx_2 = add_i32_input("merger_ds_idx_2", n_out); + ggml_tensor * merger_ds_idx_3 = add_i32_input("merger_ds_idx_3", n_out); // patch embedding + positional embedding ggml_tensor * inp = build_inp(); @@ -169,150 +177,10 @@ ggml_cgraph * clip_graph_minicpmv4_6::build() { cb(inpL, "pre_ln", -1); } - // ViT layers 0..insert_layer_id (inclusive) - // Mirrors the separate-qkv path of clip_graph::build_vit so the two manually - // unrolled segments around the ViT merger read like build_vit() expansions. - for (int il = 0; il <= insert_lid; il++) { - auto & layer = model.layers[il]; - ggml_tensor * cur = inpL; - - cur = build_norm(cur, layer.ln_1_w, layer.ln_1_b, NORM_TYPE_NORMAL, eps, il); - cb(cur, "layer_inp_normed", il); - - { - ggml_tensor * Qcur = build_mm(layer.q_w, cur); - if (layer.q_b) { - Qcur = ggml_add(ctx0, Qcur, layer.q_b); - } - ggml_tensor * Kcur = build_mm(layer.k_w, cur); - if (layer.k_b) { - Kcur = ggml_add(ctx0, Kcur, layer.k_b); - } - ggml_tensor * Vcur = build_mm(layer.v_w, cur); - if (layer.v_b) { - Vcur = ggml_add(ctx0, Vcur, layer.v_b); - } - - Qcur = ggml_reshape_3d(ctx0, Qcur, d_head, n_head, n_pos); - Kcur = ggml_reshape_3d(ctx0, Kcur, d_head, n_head, n_pos); - Vcur = ggml_reshape_3d(ctx0, Vcur, d_head, n_head, n_pos); - cb(Qcur, "Qcur", il); - cb(Kcur, "Kcur", il); - cb(Vcur, "Vcur", il); - - cur = build_attn(layer.o_w, layer.o_b, Qcur, Kcur, Vcur, nullptr, kq_scale, il); - cb(cur, "attn_out", il); - } - - if (layer.ls_1_w) { - cur = ggml_mul(ctx0, cur, layer.ls_1_w); - cb(cur, "attn_out_scaled", il); - } - cur = ggml_add(ctx0, cur, inpL); - inpL = cur; - cb(cur, "ffn_inp", il); - - cur = build_norm(cur, layer.ln_2_w, layer.ln_2_b, NORM_TYPE_NORMAL, eps, il); - cb(cur, "ffn_inp_normed", il); - - cur = build_ffn(cur, layer.ff_up_w, layer.ff_up_b, layer.ff_gate_w, layer.ff_gate_b, - layer.ff_down_w, layer.ff_down_b, hparams.ffn_op, il); - cb(cur, "ffn_out", il); - - if (layer.ls_2_w) { - cur = ggml_mul(ctx0, cur, layer.ls_2_w); - cb(cur, "ffn_out_scaled", il); - } - cur = ggml_add(ctx0, inpL, cur); - cb(cur, "layer_out", il); - - inpL = cur; - } - - // ViT merger: window self-attention - // Tokens are reordered to window-major (4 tokens per window are contiguous), - // and a block-diagonal mask restricts attention to within each window. This - // mirrors the qwen2vl windowed-attention pattern so build_attn() can pick the - // flash-attention path when available. - { - ggml_tensor * residual = inpL; - ggml_tensor * cur = build_norm(inpL, - model.vit_merger_ln1_w, model.vit_merger_ln1_b, - NORM_TYPE_NORMAL, eps, -1); - cb(cur, "vit_merger_attn_inp_normed", -1); - - cur = ggml_get_rows(ctx0, cur, vit_merger_window_idx); - cb(cur, "vit_merger_window_reorder", -1); - - ggml_tensor * Qcur = build_mm(model.vit_merger_attn_q_w, cur); - if (model.vit_merger_attn_q_b) { - Qcur = ggml_add(ctx0, Qcur, model.vit_merger_attn_q_b); - } - ggml_tensor * Kcur = build_mm(model.vit_merger_attn_k_w, cur); - if (model.vit_merger_attn_k_b) { - Kcur = ggml_add(ctx0, Kcur, model.vit_merger_attn_k_b); - } - ggml_tensor * Vcur = build_mm(model.vit_merger_attn_v_w, cur); - if (model.vit_merger_attn_v_b) { - Vcur = ggml_add(ctx0, Vcur, model.vit_merger_attn_v_b); - } - - Qcur = ggml_reshape_3d(ctx0, Qcur, d_head, n_head, n_pos); - Kcur = ggml_reshape_3d(ctx0, Kcur, d_head, n_head, n_pos); - Vcur = ggml_reshape_3d(ctx0, Vcur, d_head, n_head, n_pos); - cb(Qcur, "vit_merger_Qcur", -1); - cb(Kcur, "vit_merger_Kcur", -1); - cb(Vcur, "vit_merger_Vcur", -1); - - cur = build_attn(model.vit_merger_attn_o_w, model.vit_merger_attn_o_b, - Qcur, Kcur, Vcur, vit_merger_window_mask, kq_scale, -1); - cb(cur, "vit_merger_attn_out", -1); - - cur = ggml_get_rows(ctx0, cur, vit_merger_inv_window_idx); - inpL = ggml_add(ctx0, cur, residual); - cb(inpL, "vit_merger_attn_residual", -1); - } - - // ViT merger: 2x2 spatial downsample + MLP (4 tokens -> 1) - { - ggml_tensor * p0 = ggml_get_rows(ctx0, inpL, vit_merger_ds_idx_0); - ggml_tensor * p1 = ggml_get_rows(ctx0, inpL, vit_merger_ds_idx_1); - ggml_tensor * p2 = ggml_get_rows(ctx0, inpL, vit_merger_ds_idx_2); - ggml_tensor * p3 = ggml_get_rows(ctx0, inpL, vit_merger_ds_idx_3); - - ggml_tensor * mean_res = ggml_add(ctx0, p0, p1); - mean_res = ggml_add(ctx0, mean_res, p2); - mean_res = ggml_add(ctx0, mean_res, p3); - mean_res = ggml_scale(ctx0, mean_res, 0.25f); - cb(mean_res, "vit_merger_ds_mean_res", -1); - - ggml_tensor * cat = ggml_concat(ctx0, p0, p1, 0); - cat = ggml_concat(ctx0, cat, p2, 0); - cat = ggml_concat(ctx0, cat, p3, 0); - - ggml_tensor * cur = build_norm(cat, - model.vit_merger_ds_ln_w, model.vit_merger_ds_ln_b, - NORM_TYPE_NORMAL, eps, -1); - cb(cur, "vit_merger_ds_normed", -1); - - // ViTWindowAttentionMerger downsample MLP uses gelu_pytorch_tanh (FFN_GELU) - cur = build_ffn(cur, - model.vit_merger_ds_up_w, model.vit_merger_ds_up_b, - nullptr, nullptr, - model.vit_merger_ds_down_w, model.vit_merger_ds_down_b, - FFN_GELU, -1); - cb(cur, "vit_merger_ds_mlp_out", -1); - - inpL = ggml_add(ctx0, cur, mean_res); - cb(inpL, "vit_merger_ds_out", -1); - } - - // ViT layers (insert_layer_id+1)..n_layer-1, operating on the downsampled tokens - { - const int64_t n_pos_ds = n_ds; - for (int il = insert_lid + 1; il < n_layer; il++) { + auto build_vit_layers = [&](ggml_tensor * input, int il_begin, int il_end, int64_t n_pos_layer) { + for (int il = il_begin; il < il_end; il++) { auto & layer = model.layers[il]; - ggml_tensor * cur = inpL; + ggml_tensor * cur = input; cur = build_norm(cur, layer.ln_1_w, layer.ln_1_b, NORM_TYPE_NORMAL, eps, il); cb(cur, "layer_inp_normed", il); @@ -331,9 +199,9 @@ ggml_cgraph * clip_graph_minicpmv4_6::build() { Vcur = ggml_add(ctx0, Vcur, layer.v_b); } - Qcur = ggml_reshape_3d(ctx0, Qcur, d_head, n_head, n_pos_ds); - Kcur = ggml_reshape_3d(ctx0, Kcur, d_head, n_head, n_pos_ds); - Vcur = ggml_reshape_3d(ctx0, Vcur, d_head, n_head, n_pos_ds); + Qcur = ggml_reshape_3d(ctx0, Qcur, d_head, n_head, n_pos_layer); + Kcur = ggml_reshape_3d(ctx0, Kcur, d_head, n_head, n_pos_layer); + Vcur = ggml_reshape_3d(ctx0, Vcur, d_head, n_head, n_pos_layer); cb(Qcur, "Qcur", il); cb(Kcur, "Kcur", il); cb(Vcur, "Vcur", il); @@ -346,8 +214,8 @@ ggml_cgraph * clip_graph_minicpmv4_6::build() { cur = ggml_mul(ctx0, cur, layer.ls_1_w); cb(cur, "attn_out_scaled", il); } - cur = ggml_add(ctx0, cur, inpL); - inpL = cur; + cur = ggml_add(ctx0, cur, input); + input = cur; cb(cur, "ffn_inp", il); cur = build_norm(cur, layer.ln_2_w, layer.ln_2_b, NORM_TYPE_NORMAL, eps, il); @@ -361,11 +229,98 @@ ggml_cgraph * clip_graph_minicpmv4_6::build() { cur = ggml_mul(ctx0, cur, layer.ls_2_w); cb(cur, "ffn_out_scaled", il); } - cur = ggml_add(ctx0, inpL, cur); - cb(cur, "layer_out", il); + input = ggml_add(ctx0, input, cur); + cb(input, "layer_out", il); + } + return input; + }; + + if (!is_4x) { + const int insert_lid = hparams.insert_layer_id; + + inpL = build_vit_layers(inpL, 0, insert_lid + 1, n_pos); + + // ViT merger: window self-attention + // Tokens are reordered to window-major (4 tokens per window are contiguous), + // and a block-diagonal mask restricts attention to within each window. This + // mirrors the qwen2vl windowed-attention pattern so build_attn() can pick the + // flash-attention path when available. + { + ggml_tensor * residual = inpL; + ggml_tensor * cur = build_norm(inpL, + model.vit_merger_ln1_w, model.vit_merger_ln1_b, + NORM_TYPE_NORMAL, eps, -1); + cb(cur, "vit_merger_attn_inp_normed", -1); + + cur = ggml_get_rows(ctx0, cur, vit_merger_window_idx); + cb(cur, "vit_merger_window_reorder", -1); + + ggml_tensor * Qcur = build_mm(model.vit_merger_attn_q_w, cur); + if (model.vit_merger_attn_q_b) { + Qcur = ggml_add(ctx0, Qcur, model.vit_merger_attn_q_b); + } + ggml_tensor * Kcur = build_mm(model.vit_merger_attn_k_w, cur); + if (model.vit_merger_attn_k_b) { + Kcur = ggml_add(ctx0, Kcur, model.vit_merger_attn_k_b); + } + ggml_tensor * Vcur = build_mm(model.vit_merger_attn_v_w, cur); + if (model.vit_merger_attn_v_b) { + Vcur = ggml_add(ctx0, Vcur, model.vit_merger_attn_v_b); + } - inpL = cur; + Qcur = ggml_reshape_3d(ctx0, Qcur, d_head, n_head, n_pos); + Kcur = ggml_reshape_3d(ctx0, Kcur, d_head, n_head, n_pos); + Vcur = ggml_reshape_3d(ctx0, Vcur, d_head, n_head, n_pos); + cb(Qcur, "vit_merger_Qcur", -1); + cb(Kcur, "vit_merger_Kcur", -1); + cb(Vcur, "vit_merger_Vcur", -1); + + cur = build_attn(model.vit_merger_attn_o_w, model.vit_merger_attn_o_b, + Qcur, Kcur, Vcur, vit_merger_window_mask, kq_scale, -1); + cb(cur, "vit_merger_attn_out", -1); + + cur = ggml_get_rows(ctx0, cur, vit_merger_inv_window_idx); + inpL = ggml_add(ctx0, cur, residual); + cb(inpL, "vit_merger_attn_residual", -1); } + + // ViT merger: 2x2 spatial downsample + MLP (4 tokens -> 1) + { + ggml_tensor * p0 = ggml_get_rows(ctx0, inpL, vit_merger_ds_idx_0); + ggml_tensor * p1 = ggml_get_rows(ctx0, inpL, vit_merger_ds_idx_1); + ggml_tensor * p2 = ggml_get_rows(ctx0, inpL, vit_merger_ds_idx_2); + ggml_tensor * p3 = ggml_get_rows(ctx0, inpL, vit_merger_ds_idx_3); + + ggml_tensor * mean_res = ggml_add(ctx0, p0, p1); + mean_res = ggml_add(ctx0, mean_res, p2); + mean_res = ggml_add(ctx0, mean_res, p3); + mean_res = ggml_scale(ctx0, mean_res, 0.25f); + cb(mean_res, "vit_merger_ds_mean_res", -1); + + ggml_tensor * cat = ggml_concat(ctx0, p0, p1, 0); + cat = ggml_concat(ctx0, cat, p2, 0); + cat = ggml_concat(ctx0, cat, p3, 0); + + ggml_tensor * cur = build_norm(cat, + model.vit_merger_ds_ln_w, model.vit_merger_ds_ln_b, + NORM_TYPE_NORMAL, eps, -1); + cb(cur, "vit_merger_ds_normed", -1); + + // ViTWindowAttentionMerger downsample MLP uses gelu_pytorch_tanh (FFN_GELU) + cur = build_ffn(cur, + model.vit_merger_ds_up_w, model.vit_merger_ds_up_b, + nullptr, nullptr, + model.vit_merger_ds_down_w, model.vit_merger_ds_down_b, + FFN_GELU, -1); + cb(cur, "vit_merger_ds_mlp_out", -1); + + inpL = ggml_add(ctx0, cur, mean_res); + cb(inpL, "vit_merger_ds_out", -1); + } + + inpL = build_vit_layers(inpL, insert_lid + 1, n_layer, n_ds); + } else { + inpL = build_vit_layers(inpL, 0, n_layer, n_pos); } if (model.post_ln_w) { diff --git a/tools/mtmd/models/models.h b/tools/mtmd/models/models.h index e54366a086f4..eb924972bf5c 100644 --- a/tools/mtmd/models/models.h +++ b/tools/mtmd/models/models.h @@ -2,6 +2,11 @@ #include "../clip-graph.h" +#include +#include +#include +#include + /* * IMPORTANT: The mtmd module does NOT accept pull requests that are fully or predominantly AI-generated. * We encourage human contributors to ensure the quality and reliability of the codebase. @@ -215,6 +220,111 @@ struct clip_graph_mimo_audio : clip_graph { ggml_cgraph * build() override; }; +struct clip_graph_qwen3tts_spkenc : clip_graph { + clip_graph_qwen3tts_spkenc(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {} + ggml_cgraph * build() override; + + ggml_tensor * conv1d_same(ggml_tensor * x, ggml_tensor * w, ggml_tensor * b, int dilation) const; + ggml_tensor * res2net(ggml_tensor * x, const clip_layer & layer, int dilation, int scale) const; + ggml_tensor * se_block(ggml_tensor * x, const clip_layer & layer) const; + ggml_tensor * se_res2net_block(ggml_tensor * x, const clip_layer & layer, int dilation, int scale) const; + ggml_tensor * attentive_stats_pool(ggml_tensor * x) const; +}; + +struct clip_graph_qwen3tts_gen : clip_graph { + clip_graph_qwen3tts_gen(clip_ctx * ctx, const clip_image_f32 & img, clip_gen_process_type gen_process, int top_k, float top_p) + : clip_graph(ctx, img), gen_process(gen_process), top_k(top_k), top_p(top_p) {} + ggml_cgraph * build() override; + + // which sub-graph build() constructs, fixed at graph-build time + clip_gen_process_type gen_process; + + // sampling params, fixed at graph-build time (GEN_CODE only) + int top_k; + float top_p; + + // + // code_gen: backbone hidden state + sampled code0 -> 16 RVQ codes + // MTP-style code predictor, one token per codebook + // + struct code_gen : clip_graph { + code_gen(const clip_graph & parent, int top_k, float top_p) + : clip_graph(parent), top_k(top_k), top_p(top_p) {} + ggml_cgraph * build() override { GGML_ABORT("call prefill()/step() instead"); } + + int top_k; + float top_p; + + ggml_tensor * cache_set(ggml_tensor * cache, int row_idx, ggml_tensor * value) const; + ggml_tensor * do_sampling(ggml_tensor * logits, ggml_tensor * inp_rand) const; + + ggml_tensor * const_i32(ggml_tensor * anchor, float value) const; + ggml_tensor * causal_mask_row(int64_t n_kv_pad, int pos) const; + ggml_tensor * project_in(ggml_tensor * cur) const; + + ggml_tensor * layer_forward( + ggml_tensor * cur, + const clip_layer & layer, + ggml_tensor * inp_pos, + ggml_tensor * kq_mask, + ggml_tensor *& k_cache_layer, + ggml_tensor *& v_cache_layer, + int64_t n_kv_pad, + int pos, + int il) const; + + void prefill( + std::vector & k_cache, + std::vector & v_cache, + ggml_tensor *& out_code_cache, + ggml_tensor * h_state, + ggml_tensor * code0_embd, + ggml_tensor * inp_rand) const; + + ggml_tensor * step( + std::vector & k_cache, + std::vector & v_cache, + ggml_tensor * out_code_cache, + ggml_tensor * inp_rand, + int step_idx) const; + }; + + // + // code2wav: RVQ codes -> raw PCM (quantizer + pre_conv + pre_transformer + upsample + DAC). + // + struct code2wav : clip_graph { + code2wav(const clip_graph & parent) : clip_graph(parent) {} + ggml_cgraph * build() override { GGML_ABORT("call decode() instead"); } + + // state_in: previous call's persisted state, by slot name (see list_c2w_state_slots()) + std::map state_in; + // state_out: this call's state to persist, added to the graph outputs by build() + mutable std::vector> state_out; + + // stateful conv ops: read/update their state via state_in/state_out[state_name] + ggml_tensor * causal_conv1d(ggml_tensor * x, ggml_tensor * w, ggml_tensor * b, int dilation, const std::string & state_name) const; + ggml_tensor * causal_conv1d_dw(ggml_tensor * x, ggml_tensor * w, ggml_tensor * b, const std::string & state_name) const; + ggml_tensor * causal_conv_transpose1d(ggml_tensor * x, ggml_tensor * w, ggml_tensor * b, int stride, const std::string & state_name) const; + ggml_tensor * snake(ggml_tensor * x, ggml_tensor * alpha, ggml_tensor * beta) const; + + ggml_tensor * quant_decode(ggml_tensor * inp_codes) const; + ggml_tensor * tfm_layer_forward(ggml_tensor * cur, const clip_layer & layer, int il) const; + ggml_tensor * convnext_block(ggml_tensor * x, const clip_code2wav::upsample_block & blk, const std::string & state_prefix) const; + ggml_tensor * dac_res_unit(ggml_tensor * x, const clip_code2wav::dac_res & res, int dilation, const std::string & state_name) const; + + // inp_codes [1, n_codes] I32 -> this frame's audio samples [n_samples] F32, clamped to [-1, 1] + ggml_tensor * decode(ggml_tensor * inp_codes) const; + }; +}; + +// one persisted state buffer used by code2wav, see qwen3tts-gen.cpp +struct c2w_state_slot { + std::string name; + int64_t ne0; + int64_t ne1; +}; +std::vector list_c2w_state_slots(const clip_hparams & hparams, const clip_model & model); + struct clip_graph_kimik25 : clip_graph { clip_graph_kimik25(clip_ctx * ctx, const clip_image_f32 & img) : clip_graph(ctx, img) {} ggml_cgraph * build() override; diff --git a/tools/mtmd/models/qwen3tts-gen.cpp b/tools/mtmd/models/qwen3tts-gen.cpp new file mode 100644 index 000000000000..b6c95efa941e --- /dev/null +++ b/tools/mtmd/models/qwen3tts-gen.cpp @@ -0,0 +1,766 @@ +#include "models.h" + +#include + +// on-device sampling: top-k, top-p, then a random draw +ggml_tensor * clip_graph_qwen3tts_gen::code_gen::do_sampling(ggml_tensor * logits, ggml_tensor * inp_rand) const { + logits = ggml_reshape_1d(ctx0, logits, ggml_nelements(logits)); + const int64_t n_vocab = logits->ne[0]; + + // sort a's rows by idx + auto sort_by = [this](ggml_tensor * a, ggml_tensor * idx) { + ggml_tensor * a2d = ggml_reshape_2d(ctx0, a, 1, a->ne[0]); + return ggml_reshape_1d(ctx0, ggml_get_rows(ctx0, a2d, idx), idx->ne[0]); + }; + + ggml_tensor * cur = logits; + ggml_tensor * candidates = nullptr; // maps row index back to vocab id + + if (top_k > 0 && top_k < n_vocab) { + ggml_tensor * idx = ggml_top_k(ctx0, cur, top_k); + candidates = idx; + cur = sort_by(cur, idx); + cb(cur, "sample_top_k_logits", -1); + } + + if (top_p < 1.0f) { + ggml_tensor * sorted_idx = ggml_argsort(ctx0, cur, GGML_SORT_ORDER_DESC); + ggml_tensor * sorted_logits = sort_by(cur, sorted_idx); + candidates = candidates ? sort_by(candidates, sorted_idx) : sorted_idx; + + ggml_tensor * probs = ggml_soft_max(ctx0, sorted_logits); + ggml_tensor * cdf = ggml_cumsum(ctx0, probs); + + // keep_mask[i] = 1 once cdf[i] crosses top_p + ggml_tensor * cdf_scaled = ggml_scale_bias(ctx0, cdf, -1.0f, top_p); + ggml_tensor * keep_mask = ggml_step(ctx0, cdf_scaled); + ggml_tensor * idxf = ggml_sum(ctx0, keep_mask); + idxf = ggml_clamp(ctx0, idxf, 0.0f, (float) keep_mask->ne[0] - 1); + ggml_tensor * ones = ggml_scale_bias(ctx0, idxf, 0.0f, 1.0f); + + // top-p must include the crossing element, so force it to 1 + ggml_tensor * keep_mask_2d = ggml_reshape_2d(ctx0, keep_mask, 1, keep_mask->ne[0]); + keep_mask_2d = ggml_set_rows(ctx0, keep_mask_2d, ones, ggml_cast(ctx0, idxf, GGML_TYPE_I32)); + keep_mask = ggml_reshape_1d(ctx0, keep_mask_2d, keep_mask->ne[0]); + + // log(1) = 0 (keep), log(0) = -inf (drop) + ggml_tensor * bias = ggml_log(ctx0, keep_mask); + cur = ggml_add(ctx0, sorted_logits, bias); + cb(cur, "sample_top_p_logits", -1); + } + + // draw one token: find where the cdf crosses inp_rand + ggml_tensor * probs = ggml_soft_max(ctx0, cur); + ggml_tensor * cumsum = ggml_cumsum(ctx0, probs); + + ggml_tensor * diff = ggml_sub(ctx0, cumsum, inp_rand); + ggml_tensor * cross_mask = ggml_step(ctx0, diff); + ggml_tensor * idxf = ggml_sum(ctx0, cross_mask); + ggml_tensor * idx = ggml_cast(ctx0, ggml_scale_bias(ctx0, idxf, -1.0f, (float) cross_mask->ne[0]), GGML_TYPE_I32); + + if (candidates) { + ggml_tensor * cand_2d = ggml_reshape_2d(ctx0, candidates, 1, candidates->ne[0]); + idx = ggml_get_rows(ctx0, cand_2d, idx); + } + cb(idx, "sample_token_id", -1); + + return idx; +} + +// returns a new cache with row row_idx set to value +ggml_tensor * clip_graph_qwen3tts_gen::code_gen::cache_set(ggml_tensor * cache, int row_idx, ggml_tensor * value) const { + const int64_t n_embd = cache->ne[0]; + const int64_t n_cache = cache->ne[1]; + GGML_ASSERT(row_idx >= 0 && row_idx < n_cache); + + // append value as the last row, then gather it back into place + ggml_tensor * value_2d = ggml_reshape_2d(ctx0, value, n_embd, 1); + ggml_tensor * cache_ext = ggml_concat(ctx0, cache, value_2d, 1); // [n_embd, n_cache + 1] + + // gather indices [0..row_idx-1, n_cache, row_idx+1..n_cache-1] + // built via concat, since ggml_set_rows needs F32/F16 values, not an I32 index array + ggml_tensor * idx = const_i32(cache, (float) n_cache); + if (row_idx > 0) { + ggml_tensor * prefix = ggml_cast(ctx0, ggml_arange(ctx0, 0.0f, (float) row_idx, 1.0f), GGML_TYPE_I32); + idx = ggml_concat(ctx0, prefix, idx, 0); + } + if (row_idx < n_cache - 1) { + ggml_tensor * suffix = ggml_cast(ctx0, ggml_arange(ctx0, (float) (row_idx + 1), (float) n_cache, 1.0f), GGML_TYPE_I32); + idx = ggml_concat(ctx0, idx, suffix, 0); + } + + ggml_tensor * result = ggml_get_rows(ctx0, cache_ext, idx); + cb(result, "cache_set_out", -1); + return result; +} + +// builds a const i32 with no host upload: view a tensor, zero it via scale, add value, cast to i32 +ggml_tensor * clip_graph_qwen3tts_gen::code_gen::const_i32(ggml_tensor * anchor, float value) const { + ggml_tensor * v = ggml_view_1d(ctx0, anchor, 1, 0); + if (v->type != GGML_TYPE_F32) { + v = ggml_cast(ctx0, v, GGML_TYPE_F32); + } + return ggml_cast(ctx0, ggml_scale_bias(ctx0, v, 0.0f, value), GGML_TYPE_I32); +} + +// causal keep-mask row for a query at position pos, window size n_kv_pad +ggml_tensor * clip_graph_qwen3tts_gen::code_gen::causal_mask_row(int64_t n_kv_pad, int pos) const { + ggml_tensor * ones = ggml_fill(ctx0, ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_kv_pad, n_kv_pad), 1.0f); + ggml_tensor * keep = ggml_tri(ctx0, ones, GGML_TRI_TYPE_LOWER_DIAG); + ggml_tensor * row = ggml_view_1d(ctx0, keep, n_kv_pad, (size_t) pos * keep->nb[1]); + ggml_tensor * mask = ggml_log(ctx0, row); // 0 = keep, -inf = masked + return ggml_reshape_4d(ctx0, mask, n_kv_pad, 1, 1, 1); +} + +// talker hidden size -> predictor hidden size (small_to_mtp_projection) +ggml_tensor * clip_graph_qwen3tts_gen::code_gen::project_in(ggml_tensor * cur) const { + if (!model.gen_code_proj_in_w) { + return cur; + } + cur = ggml_mul_mat(ctx0, model.gen_code_proj_in_w, cur); + if (model.gen_code_proj_in_b) { + cur = ggml_add(ctx0, cur, model.gen_code_proj_in_b); + } + return cur; +} + +// one transformer layer at position pos; writes k/v into k_cache_layer/v_cache_layer at row pos +ggml_tensor * clip_graph_qwen3tts_gen::code_gen::layer_forward( + ggml_tensor * cur, + const clip_layer & layer, + ggml_tensor * inp_pos, + ggml_tensor * kq_mask, + ggml_tensor *& k_cache_layer, + ggml_tensor *& v_cache_layer, + int64_t n_kv_pad, + int pos, + int il) const { + const int n_head = hparams.n_head; + const int n_head_kv = hparams.n_head_kv; + const int64_t d_head = layer.q_w->ne[1] / n_head; // real head_dim, not n_embd / n_head + const float kq_scale = 1.0f / sqrtf((float) d_head); + + ggml_tensor * residual = cur; + + ggml_tensor * h = ggml_rms_norm(ctx0, cur, hparams.eps); + h = ggml_mul(ctx0, h, layer.ln_1_w); + + ggml_tensor * q = ggml_mul_mat(ctx0, layer.q_w, h); + ggml_tensor * k = ggml_mul_mat(ctx0, layer.k_w, h); + ggml_tensor * v = ggml_mul_mat(ctx0, layer.v_w, h); + + q = ggml_reshape_3d(ctx0, q, d_head, n_head, 1); + k = ggml_reshape_3d(ctx0, k, d_head, n_head_kv, 1); + + q = ggml_rms_norm(ctx0, q, hparams.eps); + q = ggml_mul(ctx0, q, layer.q_norm); + k = ggml_rms_norm(ctx0, k, hparams.eps); + k = ggml_mul(ctx0, k, layer.k_norm); + + q = ggml_rope_ext(ctx0, q, inp_pos, nullptr, (int) d_head, GGML_ROPE_TYPE_NEOX, 0, + hparams.rope_theta, 1.0f, 0.0f, 1.0f, 0.0f, 0.0f); + k = ggml_rope_ext(ctx0, k, inp_pos, nullptr, (int) d_head, GGML_ROPE_TYPE_NEOX, 0, + hparams.rope_theta, 1.0f, 0.0f, 1.0f, 0.0f, 0.0f); + + // write k/v into the cache at row pos, flat layout + ggml_tensor * k_flat = ggml_reshape_1d(ctx0, k, d_head * n_head_kv); + k_cache_layer = cache_set(k_cache_layer, pos, k_flat); + v_cache_layer = cache_set(v_cache_layer, pos, v); + + ggml_tensor * q_cur = ggml_reshape_4d(ctx0, q, d_head, n_head, 1, 1); + ggml_tensor * k_cur = ggml_reshape_4d(ctx0, k_cache_layer, d_head, n_head_kv, n_kv_pad, 1); + ggml_tensor * v_cur = ggml_reshape_4d(ctx0, v_cache_layer, d_head, n_head_kv, n_kv_pad, 1); + + ggml_tensor * attn_out = build_attn(layer.o_w, layer.o_b, q_cur, k_cur, v_cur, kq_mask, kq_scale, il); + + cur = ggml_add(ctx0, residual, attn_out); + + ggml_tensor * h2 = ggml_rms_norm(ctx0, cur, hparams.eps); + h2 = ggml_mul(ctx0, h2, layer.ln_2_w); + + ggml_tensor * gate = ggml_mul_mat(ctx0, layer.ff_gate_w, h2); + ggml_tensor * up = ggml_mul_mat(ctx0, layer.ff_up_w, h2); + ggml_tensor * gu = ggml_swiglu_split(ctx0, gate, up); + ggml_tensor * down = ggml_mul_mat(ctx0, layer.ff_down_w, gu); + + return ggml_add(ctx0, cur, down); +} + +// position 0: hidden bridge, seeds the k/v cache, no sampling +// position 1: embed(code0), sample with lm_head[0], write out_code_cache[1] +void clip_graph_qwen3tts_gen::code_gen::prefill( + std::vector & k_cache, + std::vector & v_cache, + ggml_tensor *& out_code_cache, + ggml_tensor * h_state, + ggml_tensor * code0_embd, + ggml_tensor * inp_rand) const { + const int64_t n_kv_pad = k_cache[0]->ne[1]; + + { + ggml_tensor * cur = project_in(h_state); + ggml_tensor * kq_mask = causal_mask_row(n_kv_pad, 0); + ggml_tensor * inp_pos = const_i32(k_cache[0], 0.0f); + for (size_t il = 0; il < model.layers.size(); il++) { + cur = layer_forward(cur, model.layers[il], inp_pos, kq_mask, k_cache[il], v_cache[il], n_kv_pad, 0, (int) il); + } + // position 0's output is unused, it only seeded the cache + } + + { + ggml_tensor * cur = project_in(code0_embd); + ggml_tensor * kq_mask = causal_mask_row(n_kv_pad, 1); + ggml_tensor * inp_pos = const_i32(k_cache[0], 1.0f); + for (size_t il = 0; il < model.layers.size(); il++) { + cur = layer_forward(cur, model.layers[il], inp_pos, kq_mask, k_cache[il], v_cache[il], n_kv_pad, 1, (int) il); + } + + cur = ggml_rms_norm(ctx0, cur, hparams.eps); + cur = ggml_mul(ctx0, cur, model.gen_code_norm_w); + + ggml_tensor * head_w = model.gen_code_head_w; + ggml_tensor * head_g = ggml_view_2d(ctx0, head_w, head_w->ne[0], head_w->ne[1], head_w->nb[1], 0); // lm_head[0] + ggml_tensor * logits = ggml_mul_mat(ctx0, head_g, cur); + + ggml_tensor * sampled = do_sampling(logits, inp_rand); + out_code_cache = cache_set(out_code_cache, 1, sampled); + } +} + +// one decode step of code_predictor +// at step_idx g: +// - read code from out_code_cache[g], then embed it with codebook table g-1 +// - write new kv at cache row g+1, sample with lm_head[g] +// - write result to out_code_cache[g+1] +// step_idx must be in [1, n_acoustic - 1] +ggml_tensor * clip_graph_qwen3tts_gen::code_gen::step( + std::vector & k_cache, + std::vector & v_cache, + ggml_tensor * out_code_cache, + ggml_tensor * inp_rand, + int step_idx) const { + const int64_t n_acoustic = model.gen_code_head_w->ne[2]; + GGML_ASSERT(step_idx >= 1 && step_idx < n_acoustic); + GGML_ASSERT(k_cache.size() == model.layers.size()); + GGML_ASSERT(v_cache.size() == model.layers.size()); + + const int64_t n_kv_pad = k_cache[0]->ne[1]; + const int pos = step_idx + 1; // new cache row and RoPE position + + // embed the previous code via this step's codebook table (rows are already scalars) + ggml_tensor * code_in = ggml_view_1d(ctx0, out_code_cache, 1, (size_t) step_idx * out_code_cache->nb[1]); + + ggml_tensor * embd_w = model.gen_code_embd_w; // [n_embd_talker, vocab, n_acoustic] + ggml_tensor * embd_g = ggml_view_2d(ctx0, embd_w, embd_w->ne[0], embd_w->ne[1], embd_w->nb[1], + (size_t) (step_idx - 1) * embd_w->nb[2]); + ggml_tensor * cur = ggml_get_rows(ctx0, embd_g, code_in); + cur = ggml_reshape_1d(ctx0, cur, cur->ne[0]); + cb(cur, "step_embd_in", step_idx); + + cur = project_in(cur); + cb(cur, "step_proj_in", step_idx); + + ggml_tensor * kq_mask = causal_mask_row(n_kv_pad, pos); + ggml_tensor * inp_pos = const_i32(k_cache[0], (float) pos); + + for (size_t il = 0; il < model.layers.size(); il++) { + cur = layer_forward(cur, model.layers[il], inp_pos, kq_mask, k_cache[il], v_cache[il], n_kv_pad, pos, (int) il); + cb(cur, "step_layer_out", (int) il); + } + + // final norm, this step's lm_head, sample, write the result + cur = ggml_rms_norm(ctx0, cur, hparams.eps); + cur = ggml_mul(ctx0, cur, model.gen_code_norm_w); + + ggml_tensor * head_w = model.gen_code_head_w; // [n_embd_pred, vocab, n_acoustic] + ggml_tensor * head_g = ggml_view_2d(ctx0, head_w, head_w->ne[0], head_w->ne[1], head_w->nb[1], + (size_t) step_idx * head_w->nb[2]); + ggml_tensor * logits = ggml_mul_mat(ctx0, head_g, cur); + cb(logits, "step_logits", step_idx); + + ggml_tensor * sampled = do_sampling(logits, inp_rand); + cb(sampled, "step_sampled", step_idx); + + return cache_set(out_code_cache, pos, sampled); +} + +// causal conv1d, stride 1: prepend persisted left-context instead of zero-padding, then a plain conv +// x: [T, IC] (T-first). w: [K, IC, OC]. state_name empty means K == 1 (no left-context). returns [T, OC] +ggml_tensor * clip_graph_qwen3tts_gen::code2wav::causal_conv1d(ggml_tensor * x, ggml_tensor * w, ggml_tensor * b, int dilation, const std::string & state_name) const { + const int K = (int) w->ne[0]; + const int pad = (K - 1) * dilation; + + ggml_tensor * x_full = x; + if (pad > 0) { + ggml_tensor * left = state_in.at(state_name); // [pad, IC] + x_full = ggml_concat(ctx0, left, x, 0); + } + ggml_tensor * y = ggml_conv_1d(ctx0, w, x_full, 1, 0, dilation); // [T, OC, 1] + y = ggml_reshape_2d(ctx0, y, y->ne[0], y->ne[1]); + if (b) { + y = ggml_add(ctx0, y, ggml_reshape_2d(ctx0, b, 1, b->ne[0])); + } + if (pad > 0) { + ggml_tensor * new_left = ggml_cont(ctx0, ggml_view_2d(ctx0, x_full, pad, x_full->ne[1], x_full->nb[1], + (size_t) (x_full->ne[0] - pad) * x_full->nb[0])); + state_out.push_back({state_name, new_left}); + } + return y; +} + +// causal depthwise conv1d, stride 1, dilation 1, kernel from w's shape. +// x: [T, C]. w: [K, 1, C]. returns [T, C]. see causal_conv1d for the state contract. +ggml_tensor * clip_graph_qwen3tts_gen::code2wav::causal_conv1d_dw(ggml_tensor * x, ggml_tensor * w, ggml_tensor * b, const std::string & state_name) const { + const int K = (int) w->ne[0]; + const int pad = K - 1; + + ggml_tensor * x_full = x; + if (pad > 0) { + ggml_tensor * left = state_in.at(state_name); // [pad, C] + x_full = ggml_concat(ctx0, left, x, 0); + } + ggml_tensor * y = ggml_conv_1d_dw(ctx0, w, x_full, 1, 0, 1); // [T, C, 1] + y = ggml_reshape_2d(ctx0, y, y->ne[0], y->ne[1]); + if (b) { + y = ggml_add(ctx0, y, ggml_reshape_2d(ctx0, b, 1, b->ne[0])); + } + if (pad > 0) { + ggml_tensor * new_left = ggml_cont(ctx0, ggml_view_2d(ctx0, x_full, pad, x_full->ne[1], x_full->nb[1], + (size_t) (x_full->ne[0] - pad) * x_full->nb[0])); + state_out.push_back({state_name, new_left}); + } + return y; +} + +// causal ConvTranspose1d, the (kernel - stride) overlap tail is kept as state for the next call +// x: [T, IC], w: [K, OC, IC]. state_name empty means K == stride (no overlap). returns [T * stride, OC] +ggml_tensor * clip_graph_qwen3tts_gen::code2wav::causal_conv_transpose1d(ggml_tensor * x, ggml_tensor * w, ggml_tensor * b, int stride, const std::string & state_name) const { + const int K = (int) w->ne[0]; + const int OC = (int) w->ne[1]; + const int trim = K - stride; + const int64_t emit_len = x->ne[0] * stride; + + // transposed conv as GEMM + col2im scatter-add, y: [emit_len + trim, OC] + ggml_tensor * w2 = ggml_reshape_2d(ctx0, w, (int64_t) K * OC, w->ne[2]); + w2 = ggml_cont(ctx0, ggml_transpose(ctx0, w2)); + ggml_tensor * xt = ggml_cont(ctx0, ggml_transpose(ctx0, x)); + ggml_tensor * col = ggml_mul_mat(ctx0, w2, xt); + ggml_tensor * y = ggml_col2im_1d(ctx0, col, stride, OC, 0); + + ggml_tensor * out = y; + if (trim > 0) { + ggml_tensor * tail = state_in.at(state_name); // [trim, OC] + ggml_tensor * head = ggml_add(ctx0, ggml_view_2d(ctx0, y, trim, y->ne[1], y->nb[1], 0), tail); + if (emit_len > trim) { + ggml_tensor * middle = ggml_view_2d(ctx0, y, emit_len - trim, y->ne[1], y->nb[1], (size_t) trim * y->nb[0]); + out = ggml_concat(ctx0, head, middle, 0); + } else { + out = head; + } + ggml_tensor * new_tail = ggml_cont(ctx0, ggml_view_2d(ctx0, y, trim, y->ne[1], y->nb[1], (size_t) emit_len * y->nb[0])); + state_out.push_back({state_name, new_tail}); + } + if (b) { + out = ggml_add(ctx0, out, ggml_reshape_2d(ctx0, b, 1, b->ne[0])); + } + return out; +} + +// SnakeBeta activation: y = x + sin(alpha*x)^2 * inv_beta (alpha/inv_beta folded via exp/reciprocal at conversion time) +// x: [T, C]. alpha/beta: [C], broadcasts over T +ggml_tensor * clip_graph_qwen3tts_gen::code2wav::snake(ggml_tensor * x, ggml_tensor * alpha, ggml_tensor * beta) const { + ggml_tensor * a = ggml_reshape_2d(ctx0, alpha, 1, alpha->ne[0]); + ggml_tensor * b = ggml_reshape_2d(ctx0, beta, 1, beta->ne[0]); + + // expand reshapes first so mul/sin/sqr/mul/add lands as consecutive nodes, letting backends fuse them + ggml_build_forward_expand(gf, a); + ggml_build_forward_expand(gf, b); + + ggml_tensor * s = ggml_sin(ctx0, ggml_mul(ctx0, x, a)); + s = ggml_sqr(ctx0, s); + s = ggml_mul(ctx0, s, b); + return ggml_add(ctx0, x, s); +} + +// RVQ codebook decode: T frames of 16 codes -> 512-dim hidden (C-first, [512, T]) +// codebook 0 (semantic) and 1..15 (acoustic) sum within their group, project separately, then add +ggml_tensor * clip_graph_qwen3tts_gen::code2wav::quant_decode(ggml_tensor * inp_codes) const { + const auto & c2w = model.c2w; + const int64_t T = inp_codes->ne[0]; + + // ids for codebook group g over all T frames, [T] I32 + auto group_ids = [&](int g) { + return ggml_view_1d(ctx0, inp_codes, T, (size_t) g * inp_codes->nb[1]); + }; + + ggml_tensor * sem = ggml_get_rows(ctx0, c2w.quant_first_cb_w, group_ids(0)); // [256, T] + ggml_tensor * sem_out = ggml_mul_mat(ctx0, c2w.quant_first_out_w, sem); // [512, T] + + ggml_tensor * acc = nullptr; + const int64_t n_acoustic = c2w.quant_rest_cb_w->ne[2]; + for (int g = 1; g <= n_acoustic; g++) { + ggml_tensor * cb_g = ggml_view_2d(ctx0, c2w.quant_rest_cb_w, c2w.quant_rest_cb_w->ne[0], c2w.quant_rest_cb_w->ne[1], + c2w.quant_rest_cb_w->nb[1], (size_t) (g - 1) * c2w.quant_rest_cb_w->nb[2]); + ggml_tensor * embd = ggml_get_rows(ctx0, cb_g, group_ids(g)); // [256, T] + acc = acc ? ggml_add(ctx0, acc, embd) : embd; + } + ggml_tensor * ac_out = ggml_mul_mat(ctx0, c2w.quant_rest_out_w, acc); // [512, T] + + ggml_tensor * hidden = ggml_add(ctx0, sem_out, ac_out); + cb(hidden, "wav_quant_hidden", -1); + return hidden; +} + +// one pre_transformer layer over a batch of N = sliding_window new frames +// attention runs over [(W-1)-frame prefix from the last batch] + [N new frames] +// RoPE positions come from a persisted counter, so phases line up across batches +ggml_tensor * clip_graph_qwen3tts_gen::code2wav::tfm_layer_forward(ggml_tensor * cur, const clip_layer & layer, int il) const { + const int n_head = hparams.wav_tfm_n_head; + const int n_head_kv = hparams.wav_tfm_n_head_kv; + const int64_t d_head = layer.q_w->ne[1] / n_head; + const float kq_scale = 1.0f / sqrtf((float) d_head); + const int64_t W = hparams.wav_tfm_swa; // == N, frames per batch + const int64_t N = cur->ne[1]; + const int64_t prefix = W - 1; + const int64_t total_kv = prefix + N; + + ggml_tensor * residual = cur; + ggml_tensor * h = ggml_rms_norm(ctx0, cur, hparams.wav_tfm_eps); + h = ggml_mul(ctx0, h, layer.ln_1_w); + + ggml_tensor * q = ggml_mul_mat(ctx0, layer.q_w, h); // [n_head*d_head, N] + ggml_tensor * k = ggml_mul_mat(ctx0, layer.k_w, h); // [n_head_kv*d_head, N] + ggml_tensor * v = ggml_mul_mat(ctx0, layer.v_w, h); // [n_head_kv*d_head, N] + + q = ggml_reshape_3d(ctx0, q, d_head, n_head, N); + k = ggml_reshape_3d(ctx0, k, d_head, n_head_kv, N); + + // real, ever-increasing positions: base (persisted) .. base+N-1 + ggml_tensor * base = ggml_reshape_1d(ctx0, state_in.at("tfm_pos"), 1); + ggml_tensor * offset = ggml_arange(ctx0, 0.0f, (float) N, 1.0f); + ggml_tensor * pos = ggml_cast(ctx0, ggml_add(ctx0, offset, base), GGML_TYPE_I32); + + q = ggml_rope_ext(ctx0, q, pos, nullptr, (int) d_head, GGML_ROPE_TYPE_NEOX, 0, + hparams.wav_tfm_rope_theta, 1.0f, 0.0f, 1.0f, 0.0f, 0.0f); + k = ggml_rope_ext(ctx0, k, pos, nullptr, (int) d_head, GGML_ROPE_TYPE_NEOX, 0, + hparams.wav_tfm_rope_theta, 1.0f, 0.0f, 1.0f, 0.0f, 0.0f); + + // the position counter is the same for all layers, push it once from layer 0 + if (il == 0) { + state_out.push_back({"tfm_pos", ggml_scale_bias(ctx0, state_in.at("tfm_pos"), 1.0f, (float) N)}); + } + + ggml_tensor * k_new = ggml_reshape_2d(ctx0, k, d_head * n_head_kv, N); + ggml_tensor * v_new = ggml_reshape_2d(ctx0, v, d_head * n_head_kv, N); + + ggml_tensor * old_k = state_in.at("tfm_k_" + std::to_string(il)); // [d_head*n_head_kv, W-1] + ggml_tensor * old_v = state_in.at("tfm_v_" + std::to_string(il)); + + ggml_tensor * k_full = ggml_concat(ctx0, old_k, k_new, 1); // [.., prefix+N] + ggml_tensor * v_full = ggml_concat(ctx0, old_v, v_new, 1); + + // next batch's prefix: the last (W-1) frames of this batch + state_out.push_back({"tfm_k_" + std::to_string(il), + ggml_cont(ctx0, ggml_view_2d(ctx0, k_full, k_full->ne[0], prefix, k_full->nb[1], (size_t) N * k_full->nb[1]))}); + state_out.push_back({"tfm_v_" + std::to_string(il), + ggml_cont(ctx0, ggml_view_2d(ctx0, v_full, v_full->ne[0], prefix, v_full->nb[1], (size_t) N * v_full->nb[1]))}); + + // banded causal mask: key j is visible to query i iff 0 <= (prefix+i) - j < W + ggml_tensor * pos_k = ggml_reshape_2d(ctx0, ggml_arange(ctx0, 0.0f, (float) total_kv, 1.0f), total_kv, 1); + ggml_tensor * pos_q = ggml_reshape_2d(ctx0, ggml_arange(ctx0, (float) prefix, (float) (prefix + N), 1.0f), 1, N); + ggml_tensor * pos_q_grid = ggml_repeat_4d(ctx0, pos_q, total_kv, N, 1, 1); + ggml_tensor * diff = ggml_sub(ctx0, pos_q_grid, pos_k); // [total_kv, N] + + ggml_tensor * causal_keep = ggml_step(ctx0, ggml_scale_bias(ctx0, diff, 1.0f, 0.5f)); // diff >= 0 + ggml_tensor * in_window = ggml_step(ctx0, ggml_scale_bias(ctx0, diff, -1.0f, (float) W - 0.5f)); // diff < W + ggml_tensor * keep = ggml_mul(ctx0, causal_keep, in_window); + + // on a cold start, key j is real state only when j >= prefix - tfm_pos, mask out the rest + ggml_tensor * warm = ggml_step(ctx0, ggml_scale_bias(ctx0, ggml_add(ctx0, pos_k, base), + 1.0f, 0.5f - (float) prefix)); // j + pos > prefix - 0.5 + keep = ggml_mul(ctx0, keep, warm); + + ggml_tensor * mask = ggml_reshape_4d(ctx0, ggml_log(ctx0, keep), total_kv, N, 1, 1); // 0 = keep, -inf = masked + + ggml_tensor * q_cur = ggml_reshape_4d(ctx0, q, d_head, n_head, N, 1); + ggml_tensor * k_cur = ggml_reshape_4d(ctx0, k_full, d_head, n_head_kv, total_kv, 1); + ggml_tensor * v_cur = ggml_reshape_4d(ctx0, v_full, d_head, n_head_kv, total_kv, 1); + + ggml_tensor * attn_out = build_attn(layer.o_w, layer.o_b, q_cur, k_cur, v_cur, mask, kq_scale, il); + if (layer.ls_1_w) { + attn_out = ggml_mul(ctx0, attn_out, layer.ls_1_w); + } + cur = ggml_add(ctx0, residual, attn_out); + + ggml_tensor * residual2 = cur; + ggml_tensor * h2 = ggml_rms_norm(ctx0, cur, hparams.wav_tfm_eps); + h2 = ggml_mul(ctx0, h2, layer.ln_2_w); + + ggml_tensor * gate = ggml_mul_mat(ctx0, layer.ff_gate_w, h2); + ggml_tensor * up = ggml_mul_mat(ctx0, layer.ff_up_w, h2); + ggml_tensor * gu = ggml_swiglu_split(ctx0, gate, up); + ggml_tensor * down = ggml_mul_mat(ctx0, layer.ff_down_w, gu); + if (layer.ls_2_w) { + down = ggml_mul(ctx0, down, layer.ls_2_w); + } + return ggml_add(ctx0, residual2, down); +} + +// dwconv -> LayerNorm -> pwconv1 -> GELU -> pwconv2 -> layer scale -> residual +// x: [T, C] T-first; LayerNorm/pwconv need C on ne0, so this transposes in and back out +ggml_tensor * clip_graph_qwen3tts_gen::code2wav::convnext_block(ggml_tensor * x, const clip_code2wav::upsample_block & blk, const std::string & state_prefix) const { + ggml_tensor * residual = x; + + ggml_tensor * h = causal_conv1d_dw(x, blk.dwconv_w, blk.dwconv_b, state_prefix + "_dwconv"); // [T, C] + ggml_tensor * hc = ggml_cont(ctx0, ggml_transpose(ctx0, h)); // [C, T] + + hc = ggml_norm(ctx0, hc, 1e-6f); + hc = ggml_mul(ctx0, hc, blk.norm_w); + hc = ggml_add(ctx0, hc, blk.norm_b); + + ggml_tensor * g = ggml_mul_mat(ctx0, blk.pw1_w, hc); + g = ggml_add(ctx0, g, blk.pw1_b); + g = ggml_gelu(ctx0, g); + g = ggml_mul_mat(ctx0, blk.pw2_w, g); + g = ggml_add(ctx0, g, blk.pw2_b); + g = ggml_mul(ctx0, g, blk.gamma); + + ggml_tensor * g_t = ggml_cont(ctx0, ggml_transpose(ctx0, g)); // back to [T, C] + return ggml_add(ctx0, residual, g_t); +} + +// SnakeBeta -> dilated causal conv (k=7) -> SnakeBeta -> pointwise causal conv (k=1) -> residual. +// x: [T, C]. returns [T, C]. +ggml_tensor * clip_graph_qwen3tts_gen::code2wav::dac_res_unit(ggml_tensor * x, const clip_code2wav::dac_res & res, int dilation, const std::string & state_name) const { + ggml_tensor * residual = x; + ggml_tensor * h = snake(x, res.act1_alpha, res.act1_beta); + h = causal_conv1d(h, res.conv1_w, res.conv1_b, dilation, state_name); + h = snake(h, res.act2_alpha, res.act2_beta); + h = causal_conv1d(h, res.conv2_w, res.conv2_b, 1, ""); // k=1, no left-context needed + return ggml_add(ctx0, residual, h); +} + +// RVQ codes -> raw PCM for a batch of N = sliding_window frames +ggml_tensor * clip_graph_qwen3tts_gen::code2wav::decode(ggml_tensor * inp_codes) const { + const auto & c2w = model.c2w; + + // 1. quantizer decode: N frames of 16 codes -> [512, N] (C-first) + ggml_tensor * hidden = quant_decode(inp_codes); + + // 2. pre_conv: [512, N] -> T-first [N, 512] -> causal conv k=3 -> [N, 1024] + ggml_tensor * x = ggml_cont(ctx0, ggml_transpose(ctx0, hidden)); // [N, 512] + x = causal_conv1d(x, c2w.pre_conv_w, c2w.pre_conv_b, 1, "pre_conv"); // [N, 1024] + cb(x, "wav_pre_conv_out", -1); + + // 3. pre_transformer: back to C-first [1024, N], project down, run the layers, project back up + ggml_tensor * cur = ggml_cont(ctx0, ggml_transpose(ctx0, x)); // [1024, N] + cur = ggml_mul_mat(ctx0, c2w.tfm_in_proj_w, cur); + cur = ggml_add(ctx0, cur, c2w.tfm_in_proj_b); // [512 (tfm hidden), N] + + for (int il = 0; il < hparams.wav_tfm_n_layer; il++) { + cur = tfm_layer_forward(cur, c2w.tfm_layers[il], il); + } + + cur = ggml_rms_norm(ctx0, cur, hparams.wav_tfm_eps); + cur = ggml_mul(ctx0, cur, c2w.tfm_output_norm_w); + cur = ggml_mul_mat(ctx0, c2w.tfm_out_proj_w, cur); + cur = ggml_add(ctx0, cur, c2w.tfm_out_proj_b); // [1024, N] + cb(cur, "wav_tfm_out", -1); + + // 4. upsample: 2x (causal ConvTranspose1d, stride 2 + ConvNeXt block), back to T-first + // kernel == stride here, so there is no overlap tail to persist + x = ggml_cont(ctx0, ggml_transpose(ctx0, cur)); // [N, 1024] + for (size_t il = 0; il < c2w.upsample.size(); il++) { + const auto & up = c2w.upsample[il]; + x = causal_conv_transpose1d(x, up.conv_w, up.conv_b, 2, ""); + x = convnext_block(x, up, "up" + std::to_string(il)); + cb(x, "wav_upsample_out", (int) il); + } + + // 5. DAC decoder: conv_pre -> n blocks (SnakeBeta -> ConvTranspose1d -> 3 res units) -> conv_post + static constexpr int DAC_DILATIONS[3] = { 1, 3, 9 }; + + x = causal_conv1d(x, c2w.dac_entry_w, c2w.dac_entry_b, 1, "dac_entry"); + cb(x, "wav_dac_entry_out", -1); + + for (size_t il = 0; il < c2w.dac.size(); il++) { + const auto & blk = c2w.dac[il]; + const int stride = (int) (blk.conv_w->ne[0] / 2); // kernel == 2*stride for all 4 blocks + const std::string blk_name = "dac" + std::to_string(il); + x = snake(x, blk.snake_alpha, blk.snake_beta); + x = causal_conv_transpose1d(x, blk.conv_w, blk.conv_b, stride, blk_name + "_tail"); + for (size_t ir = 0; ir < blk.res.size(); ir++) { + x = dac_res_unit(x, blk.res[ir], DAC_DILATIONS[ir], blk_name + "_res" + std::to_string(ir)); + } + cb(x, "wav_dac_block_out", (int) il); + } + + x = snake(x, c2w.dac_post_snake_alpha, c2w.dac_post_snake_beta); + x = causal_conv1d(x, c2w.dac_post_conv_w, c2w.dac_post_conv_b, 1, "dac_post_conv"); // [n_samples, 1] + + x = ggml_clamp(ctx0, x, -1.0f, 1.0f); + x = ggml_reshape_1d(ctx0, x, x->ne[0]); + cb(x, "wav_audio_out", -1); + return x; +} + +// code2wav's persisted state buffers: RoPE position counter, K/V per pre_transformer layer, +// left-context/tail per stateful conv. shape lookup only, no graph needed +std::vector list_c2w_state_slots(const clip_hparams & hparams, const clip_model & model) { + const auto & c2w = model.c2w; + std::vector slots; + + slots.push_back({"tfm_pos", 1, 1}); + + // prefix is (W-1) frames, the batch itself gives the other N=W frames (see tfm_layer_forward) + const int64_t d_head = c2w.tfm_layers[0].q_w->ne[1] / hparams.wav_tfm_n_head; + const int64_t kv_ch = d_head * hparams.wav_tfm_n_head_kv; + const int64_t prefix = hparams.wav_tfm_swa - 1; + for (int il = 0; il < hparams.wav_tfm_n_layer; il++) { + slots.push_back({"tfm_k_" + std::to_string(il), kv_ch, prefix}); + slots.push_back({"tfm_v_" + std::to_string(il), kv_ch, prefix}); + } + + slots.push_back({"pre_conv", c2w.pre_conv_w->ne[0] - 1, c2w.pre_conv_w->ne[1]}); + + for (size_t il = 0; il < c2w.upsample.size(); il++) { + const auto & up = c2w.upsample[il]; + slots.push_back({"up" + std::to_string(il) + "_dwconv", up.dwconv_w->ne[0] - 1, up.dwconv_w->ne[2]}); + } + + slots.push_back({"dac_entry", c2w.dac_entry_w->ne[0] - 1, c2w.dac_entry_w->ne[1]}); + + static constexpr int DAC_DILATIONS[3] = { 1, 3, 9 }; + for (size_t il = 0; il < c2w.dac.size(); il++) { + const auto & blk = c2w.dac[il]; + const int64_t stride = blk.conv_w->ne[0] / 2; // kernel == 2*stride for all 4 blocks + const std::string blk_name = "dac" + std::to_string(il); + slots.push_back({blk_name + "_tail", stride, blk.conv_w->ne[1]}); + for (size_t ir = 0; ir < blk.res.size(); ir++) { + const auto & res = blk.res[ir]; + slots.push_back({blk_name + "_res" + std::to_string(ir), + (res.conv1_w->ne[0] - 1) * DAC_DILATIONS[ir], res.conv1_w->ne[1]}); + } + } + + slots.push_back({"dac_post_conv", c2w.dac_post_conv_w->ne[0] - 1, c2w.dac_post_conv_w->ne[1]}); + + return slots; +} + +// both sub-graphs are always built, so the topology stays constant +// ggml_build_forward_select() then picks the one that actually runs +ggml_cgraph * clip_graph_qwen3tts_gen::build() { + GGML_ASSERT(n_batch == 1); // this module only ever processes one frame at a time + + int idx; + switch (gen_process) { + case CLIP_GEN_PROCESS_GEN_CODE: idx = 0; break; + case CLIP_GEN_PROCESS_GEN_WAV: idx = 1; break; + default: GGML_ABORT("unknown gen_process"); + } + + // ---- CLIP_GEN_PROCESS_GEN_CODE: backbone hidden state -> 16 RVQ codes + next-step embd ---- + // not build_inp_raw(), a GEN_WAV call's `img` has no hidden-state data + ggml_tensor * h_state = ggml_new_tensor_1d(ctx0, GGML_TYPE_F32, n_mmproj_embd); + ggml_set_name(h_state, "inp_raw"); // must keep this exact name, clip_encode() sets it by name + ggml_set_input(h_state); + + ggml_tensor * code0 = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, 1); + ggml_set_name(code0, "inp_code0"); + ggml_set_input(code0); + + ggml_tensor * code0_embd = ggml_get_rows(ctx0, model.gen_code_out_embd_w, code0); + code0_embd = ggml_reshape_1d(ctx0, code0_embd, code0_embd->ne[0]); + cb(code0_embd, "code0_embd", -1); + + const int64_t n_acoustic = model.gen_code_head_w->ne[2]; // 15 + const int n_codes = (int) n_acoustic + 1; // 16 + const int64_t n_kv_pad = n_codes; + const int n_layer = (int) model.layers.size(); + const int n_head = hparams.n_head; + const int n_head_kv = hparams.n_head_kv; + const int64_t d_head = model.layers[0].q_w->ne[1] / n_head; + + // zero-filled per layer k/v caches, so masked-out rows can't hold garbage + std::vector k_cache(n_layer), v_cache(n_layer); + for (int il = 0; il < n_layer; il++) { + k_cache[il] = ggml_fill(ctx0, ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, d_head * n_head_kv, n_kv_pad), 0.0f); + v_cache[il] = ggml_fill(ctx0, ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, d_head * n_head_kv, n_kv_pad), 0.0f); + } + + code_gen cg(*this, top_k, top_p); + + ggml_tensor * out_code_cache = ggml_new_tensor_2d(ctx0, GGML_TYPE_I32, 1, n_codes); + out_code_cache = cg.cache_set(out_code_cache, 0, code0); + + ggml_tensor * inp_rand0 = ggml_new_tensor_1d(ctx0, GGML_TYPE_F32, 1); + ggml_set_name(inp_rand0, "inp_rand_0"); + ggml_set_input(inp_rand0); + + cg.prefill(k_cache, v_cache, out_code_cache, h_state, code0_embd, inp_rand0); + + for (int g = 1; g < n_acoustic; g++) { + ggml_tensor * inp_rand = ggml_new_tensor_1d(ctx0, GGML_TYPE_F32, 1); + ggml_set_name(inp_rand, ("inp_rand_" + std::to_string(g)).c_str()); + ggml_set_input(inp_rand); + out_code_cache = cg.step(k_cache, v_cache, out_code_cache, inp_rand, g); + } + + // output 1: this frame's 16 sampled codes, for the caller's code2wav window + ggml_tensor * out_codes = ggml_cont(ctx0, out_code_cache); + ggml_set_name(out_codes, "out_codes"); + ggml_set_output(out_codes); + + // output 2: sum of all 16 codebook embeddings, fed back to the talker for the next frame + ggml_tensor * out_embd = code0_embd; + for (int g = 1; g <= n_acoustic; g++) { + ggml_tensor * code_g = ggml_view_1d(ctx0, out_code_cache, 1, (size_t) g * out_code_cache->nb[1]); + + ggml_tensor * embd_g = ggml_view_2d(ctx0, model.gen_code_embd_w, model.gen_code_embd_w->ne[0], model.gen_code_embd_w->ne[1], + model.gen_code_embd_w->nb[1], (size_t) (g - 1) * model.gen_code_embd_w->nb[2]); + ggml_tensor * e = ggml_get_rows(ctx0, embd_g, code_g); + e = ggml_reshape_1d(ctx0, e, e->ne[0]); + + out_embd = ggml_add(ctx0, out_embd, e); + } + out_embd = ggml_reshape_2d(ctx0, out_embd, out_embd->ne[0], 1); + cb(out_embd, "gen_audio_out", -1); + + // ---- CLIP_GEN_PROCESS_GEN_WAV: 16 RVQ codes -> raw PCM ---- + const int n_frames = hparams.wav_tfm_swa; // frames per batch, == the attention window + + ggml_tensor * inp_codes = ggml_new_tensor_2d(ctx0, GGML_TYPE_I32, n_frames, n_codes); + ggml_set_name(inp_codes, "inp_codes"); + ggml_set_input(inp_codes); + + code2wav c2w(*this); + for (const auto & slot : list_c2w_state_slots(hparams, model)) { + ggml_tensor * t = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, slot.ne0, slot.ne1); + ggml_set_name(t, ("state_in_" + slot.name).c_str()); + ggml_set_input(t); + c2w.state_in[slot.name] = t; + } + + ggml_tensor * out_audio = c2w.decode(inp_codes); + ggml_set_name(out_audio, "out_audio"); + ggml_set_output(out_audio); + + for (auto & slot : c2w.state_out) { + ggml_set_name(slot.second, ("state_out_" + slot.first).c_str()); + ggml_set_output(slot.second); + } + + // out_embd goes last, clip_encode() reads it back via ggml_graph_node(gf, -1) + ggml_tensor * outs[2]; + outs[0] = out_codes; outs[1] = out_audio; + ggml_build_forward_select(gf, outs, 2, idx); + for (auto & slot : c2w.state_out) { + outs[0] = out_codes; outs[1] = slot.second; + ggml_build_forward_select(gf, outs, 2, idx); + } + outs[0] = out_embd; outs[1] = out_audio; + ggml_build_forward_select(gf, outs, 2, idx); + + return gf; +} diff --git a/tools/mtmd/models/qwen3tts-spkenc.cpp b/tools/mtmd/models/qwen3tts-spkenc.cpp new file mode 100644 index 000000000000..d4659fd63dc4 --- /dev/null +++ b/tools/mtmd/models/qwen3tts-spkenc.cpp @@ -0,0 +1,197 @@ +#include "models.h" + +static constexpr int SPK_RES2NET_SCALE = 8; // enc_res2net_scale +static constexpr int SPK_DILATIONS[3] = { 2, 3, 4 }; // enc_dilations[1..3] + +// conv1d, kernel K, padding "same" (reflect), dilation d +// x: [C, T] (ne[0]=C, ne[1]=T) -> [out_c, T] +ggml_tensor * clip_graph_qwen3tts_spkenc::conv1d_same(ggml_tensor * x, ggml_tensor * w, ggml_tensor * b, int dilation) const { + const int K = (int) w->ne[0]; + const int IC = (int) w->ne[1]; + const int OC = (int) w->ne[2]; + const int pad = ((K - 1) * dilation) / 2; + + // ggml_pad_reflect_1d pads ne[0], so bring T onto ne[0] first, same layout as im2col wants + ggml_tensor * x_t = ggml_cont(ctx0, ggml_transpose(ctx0, x)); // [T, IC] + if (pad > 0) { + x_t = ggml_pad_reflect_1d(ctx0, x_t, pad, pad); // [T + 2*pad, IC] + } + ggml_tensor * x4d = ggml_reshape_4d(ctx0, x_t, x_t->ne[0], IC, 1, 1); + + // dummy F32 kernel, im2col only reads its shape, so a quantized w does not assert + ggml_tensor * dummy = ggml_new_tensor_4d(ctx0, GGML_TYPE_F32, K, IC, 1, 1); + + ggml_tensor * col = ggml_im2col(ctx0, dummy, x4d, 1, 1, 0, 0, dilation, 1, false, GGML_TYPE_F32); + const int64_t T_out = col->ne[1]; + col = ggml_reshape_2d(ctx0, col, (int64_t) K * IC, T_out); + + ggml_tensor * w2d = ggml_reshape_2d(ctx0, w, (int64_t) K * IC, OC); + ggml_tensor * y = ggml_mul_mat(ctx0, w2d, col); // [OC, T_out] + ggml_mul_mat_set_prec(y, GGML_PREC_F32); + + ggml_tensor * b2d = ggml_reshape_2d(ctx0, b, OC, 1); + y = ggml_add(ctx0, y, b2d); + return y; +} + +// Res2Net: split channel axis into `scale` chunks, chain dilated conv1d branches +// x: [C, T] -> [C, T] +ggml_tensor * clip_graph_qwen3tts_spkenc::res2net(ggml_tensor * x, const clip_layer & layer, int dilation, int scale) const { + const int64_t C = x->ne[0]; + const int64_t T = x->ne[1]; + const int64_t Cs = C / scale; + + std::vector outs; + outs.reserve(scale); + + auto chunk = [&](int i) -> ggml_tensor * { + return ggml_view_2d(ctx0, x, Cs, T, x->nb[1], (size_t) i * Cs * x->nb[0]); + }; + + ggml_tensor * prev = nullptr; + for (int i = 0; i < scale; i++) { + ggml_tensor * c = ggml_cont(ctx0, chunk(i)); + if (i == 0) { + outs.push_back(c); + continue; + } + ggml_tensor * inp = (i >= 2) ? ggml_add(ctx0, c, prev) : c; + ggml_tensor * y = conv1d_same(inp, layer.res2_conv_w[i - 1], layer.res2_conv_b[i - 1], dilation); + y = ggml_relu(ctx0, y); + outs.push_back(y); + prev = y; + } + + ggml_tensor * acc = outs[0]; + for (int i = 1; i < scale; i++) { + acc = ggml_concat(ctx0, acc, outs[i], 0); + } + return acc; +} + +// squeeze-and-excitation gate. x: [C, T] -> [C, T] +ggml_tensor * clip_graph_qwen3tts_spkenc::se_block(ggml_tensor * x, const clip_layer & layer) const { + // temporal mean, keepdim: transpose so T is on ne[0], reduce, transpose back + ggml_tensor * x_t = ggml_cont(ctx0, ggml_transpose(ctx0, x)); // [T, C] + ggml_tensor * mean = ggml_mean(ctx0, x_t); // [1, C] + mean = ggml_cont(ctx0, ggml_transpose(ctx0, mean)); // [C, 1] + + ggml_tensor * h = conv1d_same(mean, layer.se_conv1_w, layer.se_conv1_b, 1); + h = ggml_relu(ctx0, h); + h = conv1d_same(h, layer.se_conv2_w, layer.se_conv2_b, 1); + h = ggml_sigmoid(ctx0, h); // [C, 1] + + return ggml_mul(ctx0, x, h); // broadcast gate over T +} + +// tdnn1 -> res2net -> tdnn2 -> se, plus residual. x: [C, T] -> [C, T] +ggml_tensor * clip_graph_qwen3tts_spkenc::se_res2net_block(ggml_tensor * x, const clip_layer & layer, int dilation, int scale) const { + ggml_tensor * residual = x; + ggml_tensor * h = conv1d_same(x, layer.conv_pw1_w, layer.conv_pw1_b, 1); // tdnn1 + h = ggml_relu(ctx0, h); + h = res2net(h, layer, dilation, scale); + h = conv1d_same(h, layer.conv_pw2_w, layer.conv_pw2_b, 1); // tdnn2 + h = ggml_relu(ctx0, h); + h = se_block(h, layer); + return ggml_add(ctx0, h, residual); +} + +// attentive statistics pooling. x: [C, T] -> [2*C, 1] +ggml_tensor * clip_graph_qwen3tts_spkenc::attentive_stats_pool(ggml_tensor * x) const { + const int64_t T = x->ne[1]; + + // mean over T: [C, 1] + ggml_tensor * x_t = ggml_cont(ctx0, ggml_transpose(ctx0, x)); + ggml_tensor * mean = ggml_mean(ctx0, x_t); + mean = ggml_cont(ctx0, ggml_transpose(ctx0, mean)); + + // std over T: sqrt(clamp(mean((x - mean)^2), eps)) + ggml_tensor * mean_rep = ggml_repeat(ctx0, mean, x); + ggml_tensor * centered = ggml_sub(ctx0, x, mean_rep); + ggml_tensor * var_t = ggml_cont(ctx0, ggml_transpose(ctx0, ggml_sqr(ctx0, centered))); + ggml_tensor * var = ggml_mean(ctx0, var_t); + var = ggml_cont(ctx0, ggml_transpose(ctx0, var)); + var = ggml_scale_bias(ctx0, var, 1.0f, 1e-12f); + ggml_tensor * std = ggml_sqrt(ctx0, var); + + // attention input: cat([x, mean, std]) along channel axis -> [3C, T] + ggml_tensor * std_rep = ggml_repeat(ctx0, std, x); + ggml_tensor * cat = ggml_concat(ctx0, x, mean_rep, 0); + cat = ggml_concat(ctx0, cat, std_rep, 0); + + // attention TDNN (3C -> attn_c) + ReLU, tanh, then 1x1 conv (attn_c -> C) + ggml_tensor * a = conv1d_same(cat, model.spk_asp_tdnn_w, model.spk_asp_tdnn_b, 1); + a = ggml_relu(ctx0, a); + a = ggml_tanh(ctx0, a); + a = conv1d_same(a, model.spk_asp_attn_w, model.spk_asp_attn_b, 1); + + // softmax over T + ggml_tensor * a_t = ggml_cont(ctx0, ggml_transpose(ctx0, a)); // [T, C] + ggml_tensor * w_t = ggml_soft_max(ctx0, a_t); + ggml_tensor * w = ggml_cont(ctx0, ggml_transpose(ctx0, w_t)); // [C, T] + + // weighted mean: sum(w * x) over T, multiply by T to undo ggml_mean's 1/T scaling + ggml_tensor * wx = ggml_mul(ctx0, w, x); + ggml_tensor * wx_t = ggml_cont(ctx0, ggml_transpose(ctx0, wx)); + ggml_tensor * w_mean = ggml_mean(ctx0, wx_t); + w_mean = ggml_scale(ctx0, w_mean, (float) T); + w_mean = ggml_cont(ctx0, ggml_transpose(ctx0, w_mean)); // [C, 1] + + // weighted std: sum(w * (x - w_mean)^2) over T + ggml_tensor * w_mean_rep = ggml_repeat(ctx0, w_mean, x); + ggml_tensor * dev = ggml_sub(ctx0, x, w_mean_rep); + ggml_tensor * w_var_in = ggml_mul(ctx0, w, ggml_sqr(ctx0, dev)); + ggml_tensor * w_var_t = ggml_cont(ctx0, ggml_transpose(ctx0, w_var_in)); + ggml_tensor * w_var = ggml_mean(ctx0, w_var_t); + w_var = ggml_scale(ctx0, w_var, (float) T); + w_var = ggml_cont(ctx0, ggml_transpose(ctx0, w_var)); + w_var = ggml_scale_bias(ctx0, w_var, 1.0f, 1e-12f); + ggml_tensor * w_std = ggml_sqrt(ctx0, w_var); + + return ggml_concat(ctx0, w_mean, w_std, 0); // [2C, 1] +} + +ggml_cgraph * clip_graph_qwen3tts_spkenc::build() { + // inp_raw: [T, n_mel, 1, 1], from mtmd_audio_preprocessor_qwen3tts_spk + ggml_tensor * inp = build_inp_raw(1); + inp = ggml_reshape_2d(ctx0, inp, inp->ne[0], inp->ne[1]); + + // this file's convention is [C, T]; the preprocessor delivers [T, C] + ggml_tensor * mel = ggml_cont(ctx0, ggml_transpose(ctx0, inp)); // [n_mel, T] + cb(mel, "mel", -1); + + // frontend conv0 TDNN k=5, dilation=1: 128 -> 512 + ggml_tensor * cur = conv1d_same(mel, model.conv1d_1_w, model.conv1d_1_b, 1); + cur = ggml_relu(ctx0, cur); + cb(cur, "frontend", -1); + + // 3 SE-Res2Net blocks at dilations 2, 3, 4 + GGML_ASSERT((int) model.layers.size() == 3); + std::vector blk_out(3); + for (int il = 0; il < 3; il++) { + cur = se_res2net_block(cur, model.layers[il], SPK_DILATIONS[il], SPK_RES2NET_SCALE); + blk_out[il] = cur; + cb(cur, "block_out", il); + } + + // multi-layer feature aggregation: cat blk[0..2] then TDNN k=1 + ReLU + ggml_tensor * cat = ggml_concat(ctx0, blk_out[0], blk_out[1], 0); + cat = ggml_concat(ctx0, cat, blk_out[2], 0); // [1536, T] + ggml_tensor * mfa = conv1d_same(cat, model.conv_out_w, model.conv_out_b, 1); + mfa = ggml_relu(ctx0, mfa); + cb(mfa, "mfa", -1); + + // attentive statistics pooling: [1536, T] -> [3072, 1] + ggml_tensor * stats = attentive_stats_pool(mfa); + cb(stats, "asp", -1); + + // final FC k=1: [3072, 1] -> [enc_dim, 1] + ggml_tensor * emb = conv1d_same(stats, model.mm_fc_w, model.mm_fc_b, 1); + + emb = ggml_reshape_1d(ctx0, emb, emb->ne[0]); + emb = ggml_cont(ctx0, emb); + cb(emb, "spk_embedding", -1); + + ggml_build_forward_expand(gf, emb); + return gf; +} diff --git a/tools/mtmd/mtmd-audio.cpp b/tools/mtmd/mtmd-audio.cpp index fea03557d05c..ca4b64efa4a4 100644 --- a/tools/mtmd/mtmd-audio.cpp +++ b/tools/mtmd/mtmd-audio.cpp @@ -556,10 +556,8 @@ bool mtmd_audio_preprocessor_whisper::preprocess(const float * s } std::vector smpl; - // if input is too short, pad with zeros - // this is to avoid potential issues with stage1/2 padding in log_mel_spectrogram - // TODO: maybe handle this better - size_t min_samples = (size_t) hparams.audio_sample_rate * (hparams.audio_chunk_len + 1); // +1 second margin + // reflection padding needs one sample plus half an FFT window + size_t min_samples = (size_t) hparams.audio_n_fft / 2 + 1; if (n_samples < min_samples) { smpl.resize(min_samples, 0.0f); std::memcpy(smpl.data(), samples, n_samples * sizeof(float)); @@ -791,6 +789,66 @@ bool mtmd_audio_preprocessor_mimo_audio::preprocess(const float * return true; } +// +// mtmd_audio_preprocessor_qwen3tts_spk +// +// same as mel_spectrogram() in modeling_qwen3_tts.py +// ECAPA-TDNN takes the whole clip in one pass, so no Whisper-style chunking or normalization +// + +void mtmd_audio_preprocessor_qwen3tts_spk::initialize() { + cache.fill_sin_cos_table(hparams.audio_n_fft); + cache.fill_hann_window(hparams.audio_window_len, true); + cache.fill_mel_filterbank_matrix(hparams.n_mel_bins, hparams.audio_n_fft, hparams.audio_sample_rate); +} + +bool mtmd_audio_preprocessor_qwen3tts_spk::preprocess(const float * samples, + size_t n_samples, + std::vector & output) { + if (n_samples == 0) { + return false; + } + + GGML_ASSERT(!cache.sin_vals.empty()); + GGML_ASSERT(!cache.cos_vals.empty()); + GGML_ASSERT(!cache.filters.data.empty()); + + // reflect pad by (n_fft - hop) / 2 = 384, matching center=False STFT framing + const int pad = (hparams.audio_n_fft - hparams.audio_hop_len) / 2; + if (n_samples < (size_t) pad + 1) { + return false; + } + + std::vector padded(n_samples + 2 * pad, 0.0f); + for (int i = 0; i < pad; i++) { + padded[i] = samples[pad - i]; + } + std::copy(samples, samples + n_samples, padded.begin() + pad); + for (int i = 0; i < pad; i++) { + padded[n_samples + pad + i] = samples[n_samples - 2 - i]; + } + + filter_params params; + params.n_mel = hparams.n_mel_bins; + params.n_fft_bins = 1 + (hparams.audio_n_fft / 2); + params.hann_window_size = hparams.audio_window_len; + params.hop_length = hparams.audio_hop_len; + params.sample_rate = hparams.audio_sample_rate; + params.no_padding = true; // reflect padding already applied above + params.use_natural_log = true; + params.use_magnitude = true; + params.mel_floor = 1e-5f; + + mtmd_audio_mel out; + bool ok = log_mel_spectrogram(padded.data(), (int) padded.size(), 4, params, cache, out); + if (!ok) { + return false; + } + + output.push_back(std::move(out)); + return true; +} + // // mtmd_audio_preprocessor_conformer // diff --git a/tools/mtmd/mtmd-audio.h b/tools/mtmd/mtmd-audio.h index f65f282d96e2..b4d6f7259808 100644 --- a/tools/mtmd/mtmd-audio.h +++ b/tools/mtmd/mtmd-audio.h @@ -120,6 +120,15 @@ struct mtmd_audio_preprocessor_mimo_audio : mtmd_audio_preprocessor { mtmd_audio_cache cache; }; +struct mtmd_audio_preprocessor_qwen3tts_spk : mtmd_audio_preprocessor { + mtmd_audio_preprocessor_qwen3tts_spk(const clip_ctx * ctx) : mtmd_audio_preprocessor(ctx) {} + void initialize() override; + bool preprocess(const float * samples, size_t n_samples, std::vector & output) override; + + private: + mtmd_audio_cache cache; +}; + struct mtmd_audio_preprocessor_parakeet : mtmd_audio_preprocessor { mtmd_audio_preprocessor_parakeet(clip_ctx * ctx) : mtmd_audio_preprocessor(ctx) { } void initialize() override; diff --git a/tools/mtmd/mtmd-cli.cpp b/tools/mtmd/mtmd-cli.cpp index 08288c868139..07b45b644073 100644 --- a/tools/mtmd/mtmd-cli.cpp +++ b/tools/mtmd/mtmd-cli.cpp @@ -116,6 +116,14 @@ struct mtmd_cli_context { exit(1); } + init_vision_context(params); + + if (!mtmd_helper_model_can_chat(lctx, ctx_vision.get())) { + LOG_ERR("Model does not support chat mode\n"); + LOG_ERR("Hint: for TTS models, please use llama-tts\n"); + exit(1); + } + if (!llama_model_chat_template(model, nullptr) && params.chat_template.empty()) { LOG_ERR("Model does not have chat template.\n"); LOG_ERR(" For old llava models, you may need to use '--chat-template vicuna'\n"); @@ -129,8 +137,6 @@ struct mtmd_cli_context { chat_history.clear(); LOG_INF("%s: chat template example:\n%s\n", __func__, common_chat_format_example(tmpls.get(), params.use_jinja, params.default_template_kwargs).c_str()); - init_vision_context(params); - // load antiprompt tokens for legacy templates if (params.chat_template == "vicuna") { antiprompt_tokens = common_tokenize(lctx, "ASSISTANT:", false, true); diff --git a/tools/mtmd/mtmd-helper-common.h b/tools/mtmd/mtmd-helper-common.h new file mode 100644 index 000000000000..968b4df9c8f7 --- /dev/null +++ b/tools/mtmd/mtmd-helper-common.h @@ -0,0 +1,180 @@ +#pragma once + +// shared internal utilities for the mtmd-helper-*.cpp translation units +// (mtmd-helper.cpp, mtmd-helper-gen.cpp) +// NOT part of the public mtmd-helper.h API + +#include "ggml.h" +#include "llama.h" +#include "mtmd.h" + +#include +#include +#include +#include + +// +// logging +// + +struct mtmd_helper_logger { + ggml_log_callback default_callback = [](ggml_log_level level, const char * text, void * user_data) { + (void) level; + (void) user_data; + fputs(text, stderr); + fflush(stderr); + }; + + ggml_log_callback log_callback = default_callback; + void * log_callback_user_data; + + void log_v(enum ggml_log_level level, const char * format, va_list args) { + if (format == NULL) { + return; + } + va_list args_copy; + va_copy(args_copy, args); + char buffer[128]; + int len = vsnprintf(buffer, 128, format, args); + if (len < 128) { + log_callback(level, buffer, log_callback_user_data); + } else { + char * buffer2 = (char *) calloc(len + 1, sizeof(char)); + vsnprintf(buffer2, len + 1, format, args_copy); + buffer2[len] = 0; + log_callback(level, buffer2, log_callback_user_data); + free(buffer2); + } + va_end(args_copy); + } + + void log(enum ggml_log_level level, const char * format, ...) { + va_list args; + va_start(args, format); + log_v(level, format, args); + va_end(args); + } +}; + +// inline, so all TUs including this header share one instance +inline mtmd_helper_logger g_logger; + +#define LOG_DBG(...) g_logger.log(GGML_LOG_LEVEL_DEBUG, __VA_ARGS__) +#define LOG_INF(...) g_logger.log(GGML_LOG_LEVEL_INFO, __VA_ARGS__) +#define LOG_WRN(...) g_logger.log(GGML_LOG_LEVEL_WARN, __VA_ARGS__) +#define LOG_ERR(...) g_logger.log(GGML_LOG_LEVEL_ERROR, __VA_ARGS__) + +// +// embd batch +// + +// helper struct to make working with embd batch easier +// note: this will be removed after llama_batch_ext refactoring +struct decode_embd_batch { + int n_pos_per_embd; + int n_mmproj_embd; + std::vector pos; + std::vector pos_view; // used by mrope + std::vector n_seq_id; + std::vector seq_id_0; + std::vector seq_ids; + std::vector logits; + llama_batch batch; + decode_embd_batch(float * embd, int32_t n_tokens, int n_pos_per_embd, int n_mmproj_embd) : n_pos_per_embd(n_pos_per_embd), n_mmproj_embd(n_mmproj_embd) { + GGML_ASSERT(n_tokens > 0 && n_pos_per_embd > 0 && n_mmproj_embd > 0); + pos .resize(n_tokens * n_pos_per_embd); + n_seq_id.resize(n_tokens); + seq_ids .resize(n_tokens + 1); + logits .resize(n_tokens); + seq_id_0.resize(1); + seq_ids [n_tokens] = nullptr; + batch = { + /*n_tokens =*/ n_tokens, + /*tokens =*/ nullptr, + /*embd =*/ embd, + /*pos =*/ pos.data(), + /*n_seq_id =*/ n_seq_id.data(), + /*seq_id =*/ seq_ids.data(), + /*logits =*/ logits.data(), + }; + } + + void set_position_normal(llama_pos pos_0, llama_seq_id seq_id) { + seq_id_0[0] = seq_id; + for (int i = 0; i < batch.n_tokens; i++) { + batch.pos [i] = pos_0 + i; + batch.n_seq_id[i] = 1; + batch.seq_id [i] = seq_id_0.data(); + batch.logits [i] = false; + } + } + + // M-RoPE for image + void set_position_mrope_2d(const std::vector & rel_pos, llama_seq_id seq_id) { + GGML_ASSERT(n_pos_per_embd == 4); + GGML_ASSERT(!rel_pos.empty() && (int32_t)rel_pos.size() == batch.n_tokens); + seq_id_0[0] = seq_id; + for (int32_t i = 0; i < batch.n_tokens; i++) { + pos[i ] = rel_pos[i].t; + pos[i + batch.n_tokens ] = rel_pos[i].y; + pos[i + batch.n_tokens * 2] = rel_pos[i].x; + pos[i + batch.n_tokens * 3] = rel_pos[i].z; + } + for (int i = 0; i < batch.n_tokens; i++) { + batch.n_seq_id[i] = 1; + batch.seq_id [i] = seq_id_0.data(); + batch.logits [i] = false; + } + } + + // M-RoPE for audio + void set_position_mrope_1d(llama_pos pos_0, llama_seq_id seq_id) { + GGML_ASSERT(n_pos_per_embd == 4); + seq_id_0[0] = seq_id; + for (int i = 0; i < batch.n_tokens; i++) { + pos[i ] = pos_0 + i; + pos[i + batch.n_tokens ] = pos_0 + i; + pos[i + batch.n_tokens * 2] = pos_0 + i; + pos[i + batch.n_tokens * 3] = pos_0 + i; + } + for (int i = 0; i < batch.n_tokens; i++) { + batch.n_seq_id[i] = 1; + batch.seq_id [i] = seq_id_0.data(); + batch.logits [i] = false; + } + } + + llama_batch get_view(int offset, int n_tokens) { + GGML_ASSERT(offset >= 0 && n_tokens > 0 && offset + n_tokens <= batch.n_tokens); + llama_pos * pos_ptr; + pos_view.clear(); + pos_view.reserve(n_tokens * n_pos_per_embd); + if (n_pos_per_embd > 1) { + // mrope + // for example, with layout of src: 1234...1234...1234...1234... + // offset 2 will give us dst: 34...34...34...34... + for (int i = 0; i < n_pos_per_embd; i++) { + // assume n_tokens is less than or equal to batch.n_tokens + // batch.n_tokens is number of **total** tokens + // n_tokens is number of viewed token + size_t src_idx = i * batch.n_tokens + offset; + pos_view.insert(pos_view.end(), + pos.data() + src_idx, + pos.data() + src_idx + n_tokens); + } + pos_ptr = pos_view.data(); + } else { + // normal + pos_ptr = pos.data() + offset; + } + return { + /*n_tokens =*/ n_tokens, + /*tokens =*/ nullptr, + /*embd =*/ batch.embd + offset * n_mmproj_embd, + /*pos =*/ pos_ptr, + /*n_seq_id =*/ batch.n_seq_id + offset, + /*seq_id =*/ batch.seq_id + offset, + /*logits =*/ batch.logits + offset, + }; + } +}; diff --git a/tools/mtmd/mtmd-helper-gen.cpp b/tools/mtmd/mtmd-helper-gen.cpp new file mode 100644 index 000000000000..b52dc8e5a34e --- /dev/null +++ b/tools/mtmd/mtmd-helper-gen.cpp @@ -0,0 +1,505 @@ +#include "mtmd.h" +#include "mtmd-helper.h" +#include "mtmd-helper-common.h" +#include "llama.h" +#include "../src/llama-ext.h" + +#include +#include +#include +#include +#include +#include + +#ifdef MTMD_INTERNAL_HEADER +#error "mtmd-helper is a public library outside of mtmd. it must not include internal headers" +#endif + +// +// Audio generation helpers +// + +// --tts-lang codes -> language names used by the codec_language special tokens +static const std::unordered_map tts_lang_codes = { + { "zh", "chinese" }, + { "en", "english" }, + { "de", "german" }, + { "it", "italian" }, + { "pt", "portuguese" }, + { "es", "spanish" }, + { "ja", "japanese" }, + { "ko", "korean" }, + { "fr", "french" }, + { "ru", "russian" }, +}; + +static std::string tts_resolve_lang(const std::string & lang) { + auto it = tts_lang_codes.find(lang); + return it != tts_lang_codes.end() ? it->second : lang; +} + +static llama_token find_special_token(const llama_vocab * vocab, const std::string & piece) { + const int32_t n = llama_vocab_n_tokens(vocab); + for (llama_token t = 0; t < n; t++) { + if (piece == llama_vocab_get_text(vocab, t)) { + return t; + } + } + return LLAMA_TOKEN_NULL; +} + +static bool write_wav16(std::vector & buf, const std::vector & pcm, int32_t rate) { + // RIFF chunk sizes are 32-bit; refuse to emit a file with a truncated header + if (pcm.size() > ((size_t) UINT32_MAX - 36) / 2) { + return false; + } + const uint32_t data_sz = (uint32_t) (pcm.size() * 2); + const uint32_t riff_sz = 36 + data_sz; + const uint32_t fmt_sz = 16, byte_rate = (uint32_t) rate * 2; + const uint16_t fmt = 1, ch = 1, align = 2, bits = 16; + const uint32_t rate32 = (uint32_t) rate; + auto put = [&](const void * p, size_t n) { + const char * c = (const char *) p; + buf.insert(buf.end(), c, c + n); + }; + put("RIFF", 4); put(&riff_sz, 4); put("WAVE", 4); + put("fmt ", 4); put(&fmt_sz, 4); + put(&fmt, 2); put(&ch, 2); put(&rate32, 4); + put(&byte_rate, 4); put(&align, 2); put(&bits, 2); + put("data", 4); put(&data_sz, 4); + for (float v : pcm) { + int16_t s = (int16_t) (std::max(-1.0f, std::min(1.0f, v)) * 32767.0f); + put(&s, 2); + } + return true; +} + +class mtmd_gen_audio_pipeline { +public: + mtmd_gen_audio_pipeline(llama_context * lctx, mtmd_context * mctx) + : lctx(lctx), mctx(mctx), model(llama_get_model(lctx)), vocab(llama_model_get_vocab(model)), + n_embd(llama_model_n_embd(model)), info(mtmd_gen_audio_get_info(mctx)) {} + virtual ~mtmd_gen_audio_pipeline() = default; + + virtual void reset() = 0; + virtual int32_t set_input(const mtmd_helper_gen_audio_inp * inp) = 0; + // decodes at most n_batch prompt tokens; returns remaining count (0 = done), <0 on error + virtual int32_t step_prompt(int32_t n_batch) = 0; + // sampled can be LLAMA_TOKEN_NULL for pipelines with no discrete backbone token, + // those read what they need from h_state_in instead + virtual int32_t step_gen(llama_token sampled, const float * h_state_in, const float ** h_state_out) = 0; + virtual int32_t get_output(int32_t * out_sample_rate, const char ** out_data, size_t * out_data_len, int64_t * out_n_samples) = 0; + +protected: + llama_context * lctx; + mtmd_context * mctx; + const llama_model * model; + const llama_vocab * vocab; + int n_embd; + mtmd_gen_audio_info info; +}; + +// Qwen3-TTS: backbone samples codec_0, code_predictor gives the other 15 codebooks, +// then code2wav decodes them to PCM +class qwen3tts_gen_audio_pipeline : public mtmd_gen_audio_pipeline { +public: + using mtmd_gen_audio_pipeline::mtmd_gen_audio_pipeline; + + void reset() override { + seq_id = 0; + pos = 0; + codes_buf.clear(); + c2w_state.clear(); + audio_pcm.clear(); + overlay.clear(); + overlay_idx = 0; + h_state_buf.clear(); + out_buf.clear(); + prompt_embd_buf.clear(); + prompt_batch.reset(); + n_prompt = 0; + prompt_pos = 0; + } + + int32_t set_input(const mtmd_helper_gen_audio_inp * inp) override { + reset(); + seq_id = inp->seq_id; + + if (!ensure_cache()) { + return 1; + } + + const std::string lang = tts_resolve_lang((inp->lang && inp->lang[0]) ? inp->lang : "english"); + const llama_token c_lang = find_special_token(vocab, ("<|codec_language_" + lang + "|>").c_str()); + if (c_lang == LLAMA_TOKEN_NULL) { + LOG_ERR("mtmd_helper_gen_audio: unknown language '%s'\n", lang.c_str()); + return 1; + } + + std::vector speaker_embd; + if (inp->speaker_ref) { + if (!encode_speaker(inp->speaker_ref, speaker_embd)) { + return 1; + } + } + + const int n_e = n_embd; + auto row = [&](llama_token t) { + return std::vector(tok_embd.begin() + (size_t) t * n_e, + tok_embd.begin() + (size_t) (t + 1) * n_e); + }; + auto sum_row = [&](llama_token a, llama_token b) { + std::vector va = row(a), vb = row(b); + for (int i = 0; i < n_e; i++) va[(size_t) i] += vb[(size_t) i]; + return va; + }; + auto sum_vec = [&](llama_token a, const std::vector & vb) { + std::vector va = row(a); + for (int i = 0; i < n_e; i++) va[(size_t) i] += vb[(size_t) i]; + return va; + }; + + // upstream chat wrap, then slices: [0:3] role, [3:-5] utterance body + const std::string full = "<|im_start|>assistant\n" + std::string(inp->prompt, inp->prompt_len) + + "<|im_end|>\n<|im_start|>assistant\n"; + std::vector ids(full.size() + 16); + int n_ids = llama_tokenize(vocab, full.c_str(), (int32_t) full.size(), ids.data(), (int32_t) ids.size(), + false, true); + if (n_ids < 8) { + LOG_ERR("mtmd_helper_gen_audio: tokenization failed\n"); + return 1; + } + ids.resize((size_t) n_ids); + + std::vector> prompt; + for (int i = 0; i < 3; i++) prompt.push_back(row(ids[(size_t) i])); + prompt.push_back(sum_row(tts_pad, c_think)); + prompt.push_back(sum_row(tts_pad, c_think_b)); + prompt.push_back(sum_row(tts_pad, c_lang)); + prompt.push_back(sum_row(tts_pad, c_think_e)); + if (!speaker_embd.empty()) prompt.push_back(sum_vec(tts_pad, speaker_embd)); + prompt.push_back(sum_row(tts_bos, codec_pad)); + for (int i = 3; i < n_ids - 5; i++) prompt.push_back(sum_row(ids[(size_t) i], codec_pad)); + prompt.push_back(sum_row(tts_eos, codec_pad)); + prompt.push_back(sum_row(tts_pad, codec_bos)); + + n_prompt = (int) prompt.size(); + + // the talker uses the qwen3vl interleaved mrope, all sections are equal for a text/codec stream + mrope = llama_model_rope_type(model) == LLAMA_ROPE_TYPE_MROPE || + llama_model_rope_type(model) == LLAMA_ROPE_TYPE_IMROPE; + const int n_pos_per_embd = mrope ? 4 : 1; + + prompt_embd_buf.resize((size_t) n_prompt * (size_t) n_e); + for (int i = 0; i < n_prompt; i++) { + memcpy(prompt_embd_buf.data() + (size_t) i * n_e, prompt[(size_t) i].data(), (size_t) n_e * sizeof(float)); + } + + prompt_batch.reset(new decode_embd_batch(prompt_embd_buf.data(), n_prompt, n_pos_per_embd, n_e)); + if (mrope) prompt_batch->set_position_mrope_1d(0, seq_id); + else prompt_batch->set_position_normal (0, seq_id); + prompt_pos = 0; + + pos = 0; + top_k = inp->top_k > 0 ? inp->top_k : 50; + top_p = inp->top_p > 0 ? inp->top_p : 1.0f; + out_type = inp->out_type; + + // the text stream keeps flowing during generation: after frame k, the input adds + // trailing text row k on top of the codes embedding, then tts_eos, then tts_pad + for (int i = 3; i < n_ids - 5; i++) overlay.push_back(row(ids[(size_t) i])); + overlay.push_back(row(tts_eos)); + overlay.push_back(row(tts_pad)); + + return 0; + } + + int32_t step_prompt(int32_t n_batch) override { + GGML_ASSERT(n_batch > 0); + if (prompt_pos >= n_prompt) { + return 0; + } + const int32_t n_tokens_batch = std::min(n_batch, n_prompt - prompt_pos); + llama_batch batch_view = prompt_batch->get_view(prompt_pos, n_tokens_batch); + + const bool is_last_batch = (prompt_pos + n_tokens_batch) == n_prompt; + if (is_last_batch) { + batch_view.logits[n_tokens_batch - 1] = 1; + } + + if (llama_decode(lctx, batch_view) != 0) { + LOG_ERR("mtmd_helper_gen_audio: prompt decode failed\n"); + return -1; + } + + pos += n_tokens_batch; + prompt_pos += n_tokens_batch; + + if (prompt_pos >= n_prompt) { + // prompt fully processed, its embedding buffer is no longer needed + prompt_batch.reset(); + prompt_embd_buf.clear(); + return 0; + } + return n_prompt - prompt_pos; + } + + int32_t step_gen(llama_token sampled, const float * h_state_in, const float ** h_state_out) override { + mtmd_gen_inp inp{}; + inp.type = MTMD_GEN_PROCESS_TYPE_GEN_CODE; + inp.code0 = sampled - codec_0; + inp.embd = const_cast(h_state_in); + inp.top_k = top_k; + inp.top_p = top_p; + mtmd_gen_out out{}; + if (mtmd_gen_audio_process(mctx, &inp, &out) != 0) { + LOG_ERR("mtmd_helper_gen_audio: gen_code process failed\n"); + return 1; + } + + codes_buf.insert(codes_buf.end(), out.codes, out.codes + out.n_codes); + if (out.n_codes > 0 && codes_buf.size() / out.n_codes >= window_frames) { + if (!flush_gen_wav()) { + return 1; + } + } + + std::vector fb(out.embd, out.embd + n_embd); + const auto & ov = overlay[std::min(overlay_idx, overlay.size() - 1)]; + for (int i = 0; i < n_embd; i++) fb[(size_t) i] += ov[(size_t) i]; + overlay_idx++; + + const int n_pos_per_embd = mrope ? 4 : 1; + decode_embd_batch batch_embd(fb.data(), 1, n_pos_per_embd, n_embd); + if (mrope) batch_embd.set_position_mrope_1d(pos, seq_id); + else batch_embd.set_position_normal (pos, seq_id); + batch_embd.batch.logits[0] = 1; + pos++; + + if (llama_decode(lctx, batch_embd.batch) != 0) { + LOG_ERR("mtmd_helper_gen_audio: decode failed\n"); + return 1; + } + + const float * he = llama_get_embeddings_ith(lctx, -1); + h_state_buf.assign(he, he + n_embd); + *h_state_out = h_state_buf.data(); + + return 0; + } + + int32_t get_output(int32_t * out_sample_rate, const char ** out_data, size_t * out_data_len, int64_t * out_n_samples) override { + if (!flush_gen_wav()) { + return 1; + } + + *out_sample_rate = info.sample_rate; + if (out_n_samples) { + *out_n_samples = (int64_t) audio_pcm.size(); + } + + if (out_type == MTMD_HELPER_GEN_AUDIO_OUTTYPE_PCM) { + *out_data = (const char *) audio_pcm.data(); + *out_data_len = audio_pcm.size() * sizeof(float); + return 0; + } + + out_buf.clear(); + if (!write_wav16(out_buf, audio_pcm, info.sample_rate)) { + LOG_ERR("mtmd_helper_gen_audio: output too large for WAV\n"); + return 1; + } + *out_data = out_buf.data(); + *out_data_len = out_buf.size(); + return 0; + } + +private: + bool ensure_cache() { + if (specials_ok) { + return true; + } + codec_0 = find_special_token(vocab, "<|codec_0|>"); + codec_bos = find_special_token(vocab, "<|codec_bos|>"); + codec_eos = find_special_token(vocab, "<|codec_eos_token|>"); + codec_pad = find_special_token(vocab, "<|codec_pad|>"); + c_think = find_special_token(vocab, "<|codec_think|>"); + c_think_b = find_special_token(vocab, "<|codec_think_bos|>"); + c_think_e = find_special_token(vocab, "<|codec_think_eos|>"); + tts_pad = find_special_token(vocab, ""); + tts_bos = find_special_token(vocab, ""); + tts_eos = find_special_token(vocab, ""); + for (llama_token t : { codec_0, codec_bos, codec_eos, codec_pad, + c_think, c_think_b, c_think_e, + tts_pad, tts_bos, tts_eos }) { + if (t == LLAMA_TOKEN_NULL) { + LOG_ERR("mtmd_helper_gen_audio: missing a required special token in vocab\n"); + return false; + } + } + const uint32_t n_tok_embd = llama_model_get_tok_embd(model, nullptr); + if (n_tok_embd == 0) { + LOG_ERR("mtmd_helper_gen_audio: model has no token embeddings\n"); + return false; + } + tok_embd.resize(n_tok_embd); + if (llama_model_get_tok_embd(model, tok_embd.data()) != n_tok_embd) { + LOG_ERR("mtmd_helper_gen_audio: token embedding copy failed\n"); + return false; + } + specials_ok = true; + return true; + } + + // runs the reference wav through the speaker encoder, returns one x-vector embedding row + bool encode_speaker(mtmd_bitmap * bitmap, std::vector & out) { + if (!mtmd_support_audio(mctx)) { + LOG_ERR("mtmd_helper_gen_audio: mmproj has no speaker/audio encoder\n"); + return false; + } + const std::string marker = mtmd_default_marker(); + mtmd_input_text text{ marker.c_str(), marker.size(), false, true }; + mtmd_input_chunks * chunks = mtmd_input_chunks_init(); + const mtmd_bitmap * bptr = bitmap; + bool ok = mtmd_tokenize(mctx, chunks, &text, &bptr, 1) == 0; + if (ok) { + ok = false; + for (size_t i = 0; i < mtmd_input_chunks_size(chunks); i++) { + const mtmd_input_chunk * chunk = mtmd_input_chunks_get(chunks, i); + if (mtmd_input_chunk_get_type(chunk) != MTMD_INPUT_CHUNK_TYPE_AUDIO) { + continue; + } + if (mtmd_encode_chunk(mctx, chunk) != 0) { + LOG_ERR("mtmd_helper_gen_audio: speaker encode failed\n"); + break; + } + const float * embd = mtmd_get_output_embd(mctx); + const size_t n = (size_t) llama_model_n_embd_inp(model) * mtmd_input_chunk_get_n_tokens(chunk); + out.assign(embd, embd + n); + ok = true; + break; + } + } + mtmd_input_chunks_free(chunks); + return ok; + } + + // one GEN_WAV process() call over the buffered codes, state is carried across batches + bool flush_gen_wav() { + if (codes_buf.empty()) { + return true; + } + mtmd_gen_inp inp{}; + inp.type = MTMD_GEN_PROCESS_TYPE_GEN_WAV; + inp.codes = codes_buf.data(); + inp.n_codes = codes_buf.size(); + inp.state_data = c2w_state.empty() ? nullptr : (const char *) c2w_state.data(); + inp.state_size = c2w_state.size(); + mtmd_gen_out out{}; + if (mtmd_gen_audio_process(mctx, &inp, &out) != 0) { + LOG_ERR("mtmd_helper_gen_audio: gen_wav process failed\n"); + return false; + } + audio_pcm.insert(audio_pcm.end(), out.audio, out.audio + out.n_samples); + c2w_state.assign(out.state_data, out.state_data + out.state_size); + codes_buf.clear(); + return true; + } + + // vocab specials fixed across the whole session, looked up once + bool specials_ok = false; + llama_token codec_0 = LLAMA_TOKEN_NULL; + llama_token codec_bos = LLAMA_TOKEN_NULL; + llama_token codec_eos = LLAMA_TOKEN_NULL; + llama_token codec_pad = LLAMA_TOKEN_NULL; + llama_token c_think = LLAMA_TOKEN_NULL; + llama_token c_think_b = LLAMA_TOKEN_NULL; + llama_token c_think_e = LLAMA_TOKEN_NULL; + llama_token tts_pad = LLAMA_TOKEN_NULL; + llama_token tts_bos = LLAMA_TOKEN_NULL; + llama_token tts_eos = LLAMA_TOKEN_NULL; + std::vector tok_embd; // whole token embedding matrix, n_vocab * n_embd + + // must match hparams.wav_tfm_swa hardcoded in clip.cpp + size_t window_frames = 72; + + // per-generation state, cleared by reset() + llama_seq_id seq_id = 0; + bool mrope = false; + int pos = 0; + // prompt decode state, consumed batch-by-batch by step_prompt() + std::vector prompt_embd_buf; + std::unique_ptr prompt_batch; + int n_prompt = 0; + int prompt_pos = 0; + int32_t top_k = 50; + float top_p = 1.0f; + std::vector codes_buf; + std::vector c2w_state; + std::vector audio_pcm; + std::vector> overlay; + size_t overlay_idx = 0; + std::vector h_state_buf; + mtmd_helper_gen_audio_outtype out_type = MTMD_HELPER_GEN_AUDIO_OUTTYPE_WAV; + std::vector out_buf; +}; + +static std::unique_ptr make_pipeline(llama_context * lctx, mtmd_context * mctx) { + switch (mtmd_gen_audio_get_info(mctx).type) { + case MTMD_GEN_AUDIO_TYPE_QWEN3TTS: + return std::unique_ptr(new qwen3tts_gen_audio_pipeline(lctx, mctx)); + default: + return nullptr; + } +} + +struct mtmd_helper_gen_audio { + std::unique_ptr pipeline; +}; + +mtmd_helper_gen_audio * mtmd_helper_gen_audio_init(struct llama_context * lctx, struct mtmd_context * mctx) { + auto * ctx = new mtmd_helper_gen_audio(); + ctx->pipeline = make_pipeline(lctx, mctx); + return ctx; +} + +void mtmd_helper_gen_audio_free(mtmd_helper_gen_audio * ctx) { + delete ctx; +} + +void mtmd_helper_gen_audio_reset(mtmd_helper_gen_audio * ctx) { + if (ctx->pipeline) { + ctx->pipeline->reset(); + } +} + +int32_t mtmd_helper_gen_audio_set_input(mtmd_helper_gen_audio * ctx, const mtmd_helper_gen_audio_inp * inp) { + if (!ctx->pipeline) { + LOG_ERR("mtmd_helper_gen_audio: unsupported or missing gen-audio pipeline\n"); + return 1; + } + return ctx->pipeline->set_input(inp); +} + +int32_t mtmd_helper_gen_audio_step_prompt(mtmd_helper_gen_audio * ctx, int32_t n_batch) { + if (!ctx->pipeline) { + return -1; + } + return ctx->pipeline->step_prompt(n_batch); +} + +int32_t mtmd_helper_gen_audio_step_gen(mtmd_helper_gen_audio * ctx, llama_token sampled, + const float * h_state_in, const float ** h_state_out) { + if (!ctx->pipeline) { + return 1; + } + return ctx->pipeline->step_gen(sampled, h_state_in, h_state_out); +} + +int32_t mtmd_helper_gen_audio_get_output(mtmd_helper_gen_audio * ctx, int32_t * out_sample_rate, + const char ** out_data, size_t * out_data_len, int64_t * out_n_samples) { + if (!ctx->pipeline) { + return 1; + } + return ctx->pipeline->get_output(out_sample_rate, out_data, out_data_len, out_n_samples); +} diff --git a/tools/mtmd/mtmd-helper.cpp b/tools/mtmd/mtmd-helper.cpp index 90451d02ebd8..d77c93966471 100644 --- a/tools/mtmd/mtmd-helper.cpp +++ b/tools/mtmd/mtmd-helper.cpp @@ -9,6 +9,7 @@ #include "mtmd.h" #include "mtmd-helper.h" +#include "mtmd-helper-common.h" #include "llama.h" #include @@ -45,50 +46,6 @@ // internal logging functions // -struct mtmd_helper_logger { - ggml_log_callback default_callback = [](ggml_log_level level, const char * text, void * user_data) { - (void) level; - (void) user_data; - fputs(text, stderr); - fflush(stderr); - }; - - ggml_log_callback log_callback = default_callback; - void * log_callback_user_data; - - void log_v(enum ggml_log_level level, const char * format, va_list args) { - if (format == NULL) { - return; - } - va_list args_copy; - va_copy(args_copy, args); - char buffer[128]; - int len = vsnprintf(buffer, 128, format, args); - if (len < 128) { - log_callback(level, buffer, log_callback_user_data); - } else { - char * buffer2 = (char *) calloc(len + 1, sizeof(char)); - vsnprintf(buffer2, len + 1, format, args_copy); - buffer2[len] = 0; - log_callback(level, buffer2, log_callback_user_data); - free(buffer2); - } - va_end(args_copy); - } - - void log(enum ggml_log_level level, const char * format, ...) { - va_list args; - va_start(args, format); - log_v(level, format, args); - va_end(args); - } -} g_logger; - -#define LOG_DBG(...) g_logger.log(GGML_LOG_LEVEL_DEBUG, __VA_ARGS__) -#define LOG_INF(...) g_logger.log(GGML_LOG_LEVEL_INFO, __VA_ARGS__) -#define LOG_WRN(...) g_logger.log(GGML_LOG_LEVEL_WARN, __VA_ARGS__) -#define LOG_ERR(...) g_logger.log(GGML_LOG_LEVEL_ERROR, __VA_ARGS__) - void mtmd_helper_log_set(ggml_log_callback log_callback, void * user_data) { if (log_callback == nullptr) { log_callback = g_logger.default_callback; @@ -127,117 +84,6 @@ void mtmd_helper_image_get_decoder_pos(const mtmd_image_tokens * chunks, llama_p } } -// helper struct to make working with embd batch easier -// note: this will be removed after llama_batch_ext refactoring -struct decode_embd_batch { - int n_pos_per_embd; - int n_mmproj_embd; - std::vector pos; - std::vector pos_view; // used by mrope - std::vector n_seq_id; - std::vector seq_id_0; - std::vector seq_ids; - std::vector logits; - llama_batch batch; - decode_embd_batch(float * embd, int32_t n_tokens, int n_pos_per_embd, int n_mmproj_embd) : n_pos_per_embd(n_pos_per_embd), n_mmproj_embd(n_mmproj_embd) { - GGML_ASSERT(n_tokens > 0 && n_pos_per_embd > 0 && n_mmproj_embd > 0); - pos .resize(n_tokens * n_pos_per_embd); - n_seq_id.resize(n_tokens); - seq_ids .resize(n_tokens + 1); - logits .resize(n_tokens); - seq_id_0.resize(1); - seq_ids [n_tokens] = nullptr; - batch = { - /*n_tokens =*/ n_tokens, - /*tokens =*/ nullptr, - /*embd =*/ embd, - /*pos =*/ pos.data(), - /*n_seq_id =*/ n_seq_id.data(), - /*seq_id =*/ seq_ids.data(), - /*logits =*/ logits.data(), - }; - } - - void set_position_normal(llama_pos pos_0, llama_seq_id seq_id) { - seq_id_0[0] = seq_id; - for (int i = 0; i < batch.n_tokens; i++) { - batch.pos [i] = pos_0 + i; - batch.n_seq_id[i] = 1; - batch.seq_id [i] = seq_id_0.data(); - batch.logits [i] = false; - } - } - - // M-RoPE for image - void set_position_mrope_2d(const std::vector & rel_pos, llama_seq_id seq_id) { - GGML_ASSERT(n_pos_per_embd == 4); - GGML_ASSERT(!rel_pos.empty() && (int32_t)rel_pos.size() == batch.n_tokens); - seq_id_0[0] = seq_id; - for (int32_t i = 0; i < batch.n_tokens; i++) { - pos[i ] = rel_pos[i].t; - pos[i + batch.n_tokens ] = rel_pos[i].y; - pos[i + batch.n_tokens * 2] = rel_pos[i].x; - pos[i + batch.n_tokens * 3] = rel_pos[i].z; - } - for (int i = 0; i < batch.n_tokens; i++) { - batch.n_seq_id[i] = 1; - batch.seq_id [i] = seq_id_0.data(); - batch.logits [i] = false; - } - } - - // M-RoPE for audio - void set_position_mrope_1d(llama_pos pos_0, llama_seq_id seq_id) { - GGML_ASSERT(n_pos_per_embd == 4); - seq_id_0[0] = seq_id; - for (int i = 0; i < batch.n_tokens; i++) { - pos[i ] = pos_0 + i; - pos[i + batch.n_tokens ] = pos_0 + i; - pos[i + batch.n_tokens * 2] = pos_0 + i; - pos[i + batch.n_tokens * 3] = pos_0 + i; - } - for (int i = 0; i < batch.n_tokens; i++) { - batch.n_seq_id[i] = 1; - batch.seq_id [i] = seq_id_0.data(); - batch.logits [i] = false; - } - } - - llama_batch get_view(int offset, int n_tokens) { - GGML_ASSERT(offset >= 0 && n_tokens > 0 && offset + n_tokens <= batch.n_tokens); - llama_pos * pos_ptr; - pos_view.clear(); - pos_view.reserve(n_tokens * n_pos_per_embd); - if (n_pos_per_embd > 1) { - // mrope - // for example, with layout of src: 1234...1234...1234...1234... - // offset 2 will give us dst: 34...34...34...34... - for (int i = 0; i < n_pos_per_embd; i++) { - // assume n_tokens is less than or equal to batch.n_tokens - // batch.n_tokens is number of **total** tokens - // n_tokens is number of viewed token - size_t src_idx = i * batch.n_tokens + offset; - pos_view.insert(pos_view.end(), - pos.data() + src_idx, - pos.data() + src_idx + n_tokens); - } - pos_ptr = pos_view.data(); - } else { - // normal - pos_ptr = pos.data() + offset; - } - return { - /*n_tokens =*/ n_tokens, - /*tokens =*/ nullptr, - /*embd =*/ batch.embd + offset * n_mmproj_embd, - /*pos =*/ pos_ptr, - /*n_seq_id =*/ batch.n_seq_id + offset, - /*seq_id =*/ batch.seq_id + offset, - /*logits =*/ batch.logits + offset, - }; - } -}; - // Helper class to set non-causal attention via RAII class scope_non_causal { public: @@ -1084,3 +930,18 @@ int32_t mtmd_helper_video_read_next(mtmd_helper_video * ctx, GGML_ASSERT(false && "video is not supported in this build (MTMD_VIDEO is set to OFF)"); #endif } + +bool mtmd_helper_model_can_chat(llama_context * lctx, mtmd_context * mctx) { + if (!mctx) { + return true; + } + + auto * model = llama_get_model(lctx); + auto * tmpl = llama_model_chat_template(model, nullptr); + auto info = mtmd_gen_audio_get_info(mctx); + + // tts-only model cannot be used for chat (no chat template) + bool is_tts_only = info.type != MTMD_GEN_AUDIO_TYPE_NONE && tmpl == nullptr; + + return !is_tts_only; +} diff --git a/tools/mtmd/mtmd-helper.h b/tools/mtmd/mtmd-helper.h index 680a2317df0e..7e5cf9b5098c 100644 --- a/tools/mtmd/mtmd-helper.h +++ b/tools/mtmd/mtmd-helper.h @@ -157,6 +157,73 @@ MTMD_API int32_t mtmd_helper_video_read_next(mtmd_helper_video * ctx, mtmd_bitmap ** out_bitmap, char ** out_text); +// return true if model can be used for chat +MTMD_API bool mtmd_helper_model_can_chat(struct llama_context * lctx, struct mtmd_context * mctx); + +// +// Audio generation helpers +// (early-stage experimental, subjected to breaking changes) +// + +// audio generation helper context +// contains accumulator for generated audio features and PCM audio +struct mtmd_helper_gen_audio; +typedef struct mtmd_helper_gen_audio mtmd_helper_gen_audio; + +enum mtmd_helper_gen_audio_outtype { + MTMD_HELPER_GEN_AUDIO_OUTTYPE_PCM, // raw PCM + MTMD_HELPER_GEN_AUDIO_OUTTYPE_WAV, // WAV PCM 16-bit LE, mono +}; +struct mtmd_helper_gen_audio_inp { + llama_seq_id seq_id; + + const char * prompt; + size_t prompt_len; + + mtmd_bitmap * speaker_ref; // optional, can be NULL + const char * lang; // optional, can be NULL + + int32_t top_k; + float top_p; + + enum mtmd_helper_gen_audio_outtype out_type; +}; + +MTMD_API mtmd_helper_gen_audio * mtmd_helper_gen_audio_init( + struct llama_context * lctx, + struct mtmd_context * mctx); + +MTMD_API void mtmd_helper_gen_audio_free(mtmd_helper_gen_audio * ctx); + +MTMD_API void mtmd_helper_gen_audio_reset(mtmd_helper_gen_audio * ctx); + +MTMD_API int32_t mtmd_helper_gen_audio_set_input( + mtmd_helper_gen_audio * ctx, + const struct mtmd_helper_gen_audio_inp * inp); + +// processes at most n_batch prompt tokens per call +// returns: >0 = number of prompt tokens remaining, 0 = done, <0 = error +MTMD_API int32_t mtmd_helper_gen_audio_step_prompt( + mtmd_helper_gen_audio * ctx, + int32_t n_batch); + +// generates one frame; must only be called after step_prompt() has returned 0 +// h_state_out is valid until next step_gen() or reset() call +MTMD_API int32_t mtmd_helper_gen_audio_step_gen( + mtmd_helper_gen_audio * ctx, + llama_token sampled, + const float * h_state_in, + const float ** h_state_out); + +// out_data valid until next get_output() or reset() call +// out_n_samples (optional, can be NULL) receives the number of generated PCM samples +MTMD_API int32_t mtmd_helper_gen_audio_get_output( + mtmd_helper_gen_audio * ctx, + int32_t * out_sample_rate, + const char ** out_data, + size_t * out_data_len, + int64_t * out_n_samples); + #ifdef __cplusplus } // extern "C" #endif @@ -177,6 +244,31 @@ struct mtmd_helper_video_deleter { }; using video_ptr = std::unique_ptr; +// audio generation-related C++ wrappers +struct mtmd_helper_gen_audio_deleter { + void operator()(mtmd_helper_gen_audio * val) { mtmd_helper_gen_audio_free(val); } +}; +using gen_audio_ptr = std::unique_ptr; +struct gen_audio { + gen_audio_ptr ctx; + gen_audio(struct llama_context * lctx, struct mtmd_context * mctx) : ctx(mtmd_helper_gen_audio_init(lctx, mctx)) {} + void reset() { + mtmd_helper_gen_audio_reset(ctx.get()); + } + int32_t set_input(const struct mtmd_helper_gen_audio_inp * inp) { + return mtmd_helper_gen_audio_set_input(ctx.get(), inp); + } + int32_t step_prompt(int32_t n_batch) { + return mtmd_helper_gen_audio_step_prompt(ctx.get(), n_batch); + } + int32_t step_gen(llama_token sampled, const float * h_state, const float ** h_state_out) { + return mtmd_helper_gen_audio_step_gen(ctx.get(), sampled, h_state, h_state_out); + } + int32_t get_output(int32_t * out_sample_rate, const char ** out_data, size_t * out_data_len, int64_t * out_n_samples = nullptr) { + return mtmd_helper_gen_audio_get_output(ctx.get(), out_sample_rate, out_data, out_data_len, out_n_samples); + } +}; + } // namespace mtmd_helper #endif diff --git a/tools/mtmd/mtmd-image.cpp b/tools/mtmd/mtmd-image.cpp index 72d35fce6918..10cfe52f56f7 100644 --- a/tools/mtmd/mtmd-image.cpp +++ b/tools/mtmd/mtmd-image.cpp @@ -972,6 +972,26 @@ mtmd_image_preproc_out mtmd_image_preprocessor_longest_edge::preprocess(const cl return output; } +// +// mtmd_image_preprocessor_minicpmv +// + +mtmd_image_preprocessor_llava_uhd::slice_instructions mtmd_image_preprocessor_minicpmv::get_slice_instructions(const clip_image_size & original_size) { + if (hparams.n_merge == 2) { + const int slice_size = hparams.image_size; + const float ratio = (float)original_size.width * original_size.height / (slice_size * slice_size); + if (ratio <= 1.0f) { + mtmd_image_preprocessor_llava_uhd::slice_instructions inst; + const int patch_size = hparams.patch_size * hparams.n_merge; + inst.overview_size = get_best_resize(original_size, slice_size, patch_size, true); + inst.refined_size = clip_image_size{0, 0}; + inst.grid_size = clip_image_size{0, 0}; + return inst; + } + } + return mtmd_image_preprocessor_llava_uhd::get_slice_instructions(original_size); +} + // // mtmd_image_preprocessor_lfm2 // diff --git a/tools/mtmd/mtmd-image.h b/tools/mtmd/mtmd-image.h index 115cba51e8f4..ecb203f76791 100644 --- a/tools/mtmd/mtmd-image.h +++ b/tools/mtmd/mtmd-image.h @@ -74,7 +74,6 @@ struct mtmd_image_preprocessor_llava_uhd : mtmd_image_preprocessor { std::vector slices; }; - // LFM2 override this function to implement its custom slicing logic virtual slice_instructions get_slice_instructions(const clip_image_size & original_size); struct slice_output { @@ -83,9 +82,10 @@ struct mtmd_image_preprocessor_llava_uhd : mtmd_image_preprocessor { }; slice_output slice_image(const clip_image_u8 & img, const slice_instructions & inst); -private: +protected: clip_image_size get_best_resize(const clip_image_size & original_size, int scale_resolution, int patch_size, bool allow_upscale = false); +private: clip_image_size resize_maintain_aspect_ratio(const clip_image_size & orig, const clip_image_size & target_max); /** @@ -129,6 +129,12 @@ struct mtmd_image_preprocessor_longest_edge : mtmd_image_preprocessor { mtmd_image_preproc_out preprocess(const clip_image_u8 & img) override; }; +// custom llava-uhd slicing logic for MiniCPM-V +struct mtmd_image_preprocessor_minicpmv : mtmd_image_preprocessor_llava_uhd { + using mtmd_image_preprocessor_llava_uhd::mtmd_image_preprocessor_llava_uhd; + slice_instructions get_slice_instructions(const clip_image_size & original_size) override; +}; + // custom llava-uhd slicing logic for LFM2 // ref: https://github.com/huggingface/transformers/blob/v5.1.0/src/transformers/models/lfm2_vl/image_processing_lfm2_vl_fast.py struct mtmd_image_preprocessor_lfm2 : mtmd_image_preprocessor_llava_uhd { diff --git a/tools/mtmd/mtmd.cpp b/tools/mtmd/mtmd.cpp index 93ca8cbcf8ae..ff90d6818cb5 100644 --- a/tools/mtmd/mtmd.cpp +++ b/tools/mtmd/mtmd.cpp @@ -262,6 +262,13 @@ struct mtmd_context { struct clip_ctx * ctx_a; // audio std::vector out_embd; // image embedding vector + // generation context + struct clip_ctx * ctx_gen_a; // audio + std::vector gen_out_codes; // this frame's 16 sampled codes (GEN_CODE) + std::vector gen_out_embd; // next-step hidden state fed back to backbone (GEN_CODE) + std::vector gen_out_audio; // decoded PCM samples for the current frame (GEN_WAV) + std::vector gen_out_state; // state to feed into the next GEN_WAV call + bool print_timings; int n_threads; std::string media_marker; @@ -354,6 +361,7 @@ struct mtmd_context { auto res = clip_init(mmproj_fname, ctx_clip_params); ctx_v = res.ctx_v; ctx_a = res.ctx_a; + ctx_gen_a = res.ctx_gen_a; if (!ctx_v && !ctx_a) { throw std::runtime_error(string_format("Failed to load CLIP model from %s\n", mmproj_fname)); } @@ -378,6 +386,15 @@ struct mtmd_context { "hint: you may be using wrong mmproj\n", n_embd_text, n_embd_clip)); } + if (ctx_gen_a) { + int n_embd_gen = clip_n_mmproj_embd(ctx_gen_a); + if (n_embd_text > 0 && n_embd_text != n_embd_gen) { + throw std::runtime_error(string_format( + "mismatch between text model (n_embd = %d) and gen-audio mmproj (n_embd = %d)\n" + "hint: you may be using wrong mmproj\n", + n_embd_text, n_embd_gen)); + } + } if (ctx_v) { init_vision(); } @@ -451,7 +468,7 @@ struct mtmd_context { tok_row_end = {lookup_token("\n")}; tok_row_end_trail = false; // no trailing end-of-row token ov_img_first = true; - image_preproc = std::make_unique(ctx_v); + image_preproc = std::make_unique(ctx_v); } break; case PROJECTOR_TYPE_QWEN2VL: case PROJECTOR_TYPE_QWEN25VL: @@ -740,6 +757,10 @@ struct mtmd_context { aud_end = "<|mimo_audio_end|>"; audio_preproc = std::make_unique(ctx_a); } break; + case PROJECTOR_TYPE_QWEN3TTS_SPKENC: + { + audio_preproc = std::make_unique(ctx_a); + } break; default: throw std::runtime_error(string_format("%s: unexpected audio projector type %d\n", __func__, proj)); } @@ -780,6 +801,7 @@ struct mtmd_context { ~mtmd_context() { clip_free(ctx_a); clip_free(ctx_v); + clip_free(ctx_gen_a); } private: @@ -1553,6 +1575,125 @@ float * mtmd_get_output_embd(mtmd_context * ctx) { return ctx->out_embd.data(); } +// +// audio generation +// + +mtmd_gen_audio_info mtmd_gen_audio_get_info(const mtmd_context * ctx) { + mtmd_gen_audio_info info; + if (!ctx->ctx_gen_a) { + info.type = MTMD_GEN_AUDIO_TYPE_NONE; + return info; + } + switch (clip_get_projector_type(ctx->ctx_gen_a)) { + case PROJECTOR_TYPE_QWEN3TTS_GEN: + info.type = MTMD_GEN_AUDIO_TYPE_QWEN3TTS; + info.sample_rate = 24000; + break; + default: + info.type = MTMD_GEN_AUDIO_TYPE_NONE; + break; + } + return info; +} + +static int32_t mtmd_gen_audio_process_impl(mtmd_context * ctx, const mtmd_gen_inp * inp, mtmd_gen_out * out) { + clip_ctx * ctx_clip = ctx->ctx_gen_a; + if (!ctx_clip) { + LOG_ERR("%s: model does not support audio generation\n", __func__); + return 1; + } + + if (inp->type == MTMD_GEN_PROCESS_TYPE_GEN_CODE) { + const size_t n_embd = (size_t) clip_n_mmproj_embd(ctx_clip); + + clip_image_f32 hidden_state; + hidden_state.set_size({(int) n_embd, 1}, false, true); + hidden_state.cpy_buf(std::vector(inp->embd, inp->embd + n_embd)); + + clip_image_f32_batch batch; + batch.is_audio = true; + batch.entries.push_back(std::move(hidden_state)); + + std::vector out_embd(n_embd); + std::vector out_codes; + + clip_encode_params params; + params.imgs = &batch; + params.n_threads = ctx->n_threads; + params.gen_process = CLIP_GEN_PROCESS_GEN_CODE; + params.out_embd = &out_embd; + params.out_codes = &out_codes; + params.code0 = inp->code0; + params.top_k = inp->top_k; + params.top_p = inp->top_p; + + if (!clip_encode(ctx_clip, ¶ms)) { + LOG_ERR("%s: clip_encode failed (gen_code)\n", __func__); + return 1; + } + + ctx->gen_out_embd = std::move(out_embd); + ctx->gen_out_codes = std::move(out_codes); + + out->embd = ctx->gen_out_embd.data(); + out->codes = ctx->gen_out_codes.data(); + out->n_codes = ctx->gen_out_codes.size(); + return 0; + } + + // MTMD_GEN_PROCESS_TYPE_GEN_WAV + if (!inp->codes || inp->n_codes == 0) { + LOG_ERR("%s: codes required for gen_wav\n", __func__); + return 1; + } + std::vector in_codes(inp->codes, inp->codes + inp->n_codes); + std::vector in_state; + if (inp->state_data) { + in_state.assign(inp->state_data, inp->state_data + inp->state_size); + } + + // gen_wav has no hidden-state input, the batch entry is an unused placeholder + // TODO @ngxson : some models in the future may require hidden-state input, need to update this code later + clip_image_f32 dummy; + dummy.set_size({1, 1}, false, true); + dummy.cpy_buf(std::vector(1, 0.0f)); + + clip_image_f32_batch batch; + batch.is_audio = true; + batch.entries.push_back(std::move(dummy)); + + clip_encode_params params; + params.imgs = &batch; + params.n_threads = ctx->n_threads; + params.gen_process = CLIP_GEN_PROCESS_GEN_WAV; + params.codes = &in_codes; + params.out_audio = &ctx->gen_out_audio; + params.state_in = inp->state_data ? &in_state : nullptr; + params.state_out = &ctx->gen_out_state; + + if (!clip_encode(ctx_clip, ¶ms)) { + LOG_ERR("%s: clip_encode failed (code2wav)\n", __func__); + return 1; + } + + out->audio = ctx->gen_out_audio.data(); + out->n_samples = ctx->gen_out_audio.size(); + out->state_data = (const char *) ctx->gen_out_state.data(); + out->state_size = ctx->gen_out_state.size(); + + return 0; +} + +int32_t mtmd_gen_audio_process(mtmd_context * ctx, const struct mtmd_gen_inp * inp, struct mtmd_gen_out * out) { + try { + return mtmd_gen_audio_process_impl(ctx, inp, out); + } catch (const std::exception & e) { + LOG_ERR("%s: error: %s\n", __func__, e.what()); + return 1; + } +} + mtmd_batch * mtmd_batch_init(mtmd_context * ctx) { return new mtmd_batch(ctx); } diff --git a/tools/mtmd/mtmd.h b/tools/mtmd/mtmd.h index 3b8c1200b566..84651f8dcd00 100644 --- a/tools/mtmd/mtmd.h +++ b/tools/mtmd/mtmd.h @@ -327,6 +327,60 @@ struct mtmd_caps { }; MTMD_API struct mtmd_caps mtmd_get_cap_from_file(const char * mmproj_fname); +///////////////////////////////////////// +// EXPERIMENTAL API for audio generation, subjected to breaking changes + +// represent the pipeline type +enum mtmd_gen_audio_type { + MTMD_GEN_AUDIO_TYPE_NONE, // not supported + MTMD_GEN_AUDIO_TYPE_QWEN3TTS, +}; +struct mtmd_gen_audio_info { + enum mtmd_gen_audio_type type; + int32_t sample_rate; // in Hz, for example 24000 for qwen3tts +}; +MTMD_API struct mtmd_gen_audio_info mtmd_gen_audio_get_info(const mtmd_context * ctx); + +enum mtmd_gen_process_type { + MTMD_GEN_PROCESS_TYPE_GEN_CODE, // h_state to semantic (codes, mel-spectrogram, etc.) + MTMD_GEN_PROCESS_TYPE_GEN_WAV, // convert semantic to PCM audio + // for qwen3tts, this is code2wav +}; +struct mtmd_gen_inp { + enum mtmd_gen_process_type type; + + // for MTMD_GEN_PROCESS_TYPE_GEN_CODE + int32_t code0; // the sampled codebook 0 entry from backbone + float * embd; // the hidden state from backbone, must have n_text_embd elements + int32_t top_k; + float top_p; + + // for MTMD_GEN_PROCESS_TYPE_GEN_WAV + int32_t * codes; + size_t n_codes; + const char * state_data; + size_t state_size; +}; +struct mtmd_gen_out { + // note: output memory is allocated by the context, valid until next process() call + + // for MTMD_GEN_PROCESS_TYPE_GEN_CODE + const int32_t * codes; + size_t n_codes; + const float * embd; // the generated hidden state, to be fed back to backbone + // it must have n_text_embd elements + + // for MTMD_GEN_PROCESS_TYPE_GEN_WAV + const float * audio; + size_t n_samples; + const char * state_data; + size_t state_size; +}; +// note: this API is stateless, caller must handle state management and audio frame accumulation +MTMD_API int32_t mtmd_gen_audio_process(mtmd_context * ctx, + const struct mtmd_gen_inp * inp, + struct mtmd_gen_out * out); + ///////////////////////////////////////// // test function, to be used in test-mtmd-c-api.c diff --git a/tools/mtmd/tests/test-deepseek-ocr.py b/tools/mtmd/tests/test-deepseek-ocr.py index 8a9640550ce5..f1edaebd8bf5 100644 --- a/tools/mtmd/tests/test-deepseek-ocr.py +++ b/tools/mtmd/tests/test-deepseek-ocr.py @@ -215,7 +215,7 @@ def run_mtmd_cli(spec: "ModelSpec", model_path, mmproj_path, image_path, bin_pat "--dry-multiplier", "0.8", "--dry-base", "1.75", "--dry-allowed-length", "2", - "--dry-penalty-last-n", "-1", + "--dry-penalty-last-n", "64", "--dry-sequence-breaker", "none", ] if spec.n_ctx is not None: diff --git a/tools/parser/debug-template-parser.cpp b/tools/parser/debug-template-parser.cpp index 50e8f1efb7d6..8a916f79c78e 100644 --- a/tools/parser/debug-template-parser.cpp +++ b/tools/parser/debug-template-parser.cpp @@ -9,6 +9,7 @@ #include "peg-parser.h" #include +#include #include #include #include @@ -398,7 +399,7 @@ int main(int argc, char ** argv) { if (std::optional spec_tmpl = common_chat_try_specialized_template(chat_template, template_source, params)) { LOG_ERR("\n"); - LOG_ERR("This template uses a specialized parser, analysis results will not be available."); + LOG_ERR("This template uses a specialized parser, analysis results will not be available.\n"); parser_data = *spec_tmpl; } else { // Render template scenarios if requested @@ -426,7 +427,9 @@ int main(int argc, char ** argv) { // Generate Parser parser_data = autoparser::peg_generator::generate_parser(chat_template, params, analysis); } + } + if (!std::empty(parser_data.parser)) { LOG_ERR("\n=== Generated Parser ===\n"); common_peg_arena arena; arena.load(parser_data.parser); diff --git a/tools/server/README-dev.md b/tools/server/README-dev.md index b41d70c63ac8..45bcdcca7699 100644 --- a/tools/server/README-dev.md +++ b/tools/server/README-dev.md @@ -199,6 +199,9 @@ Invoke a tool call, request body is a JSON object with: - `tool` (string): the name of the tool - `params` (object): a mapping from argument name (string) to argument value +Headers: +- `x-tool-cwd`: optional; if set, use as the CWD for tool; this is not part of tool's params because it's meant to be set by the runtime, not the LLM itself + Returns JSON object. There are two response formats (MCP tools use the same two formats: their result content is concatenated into `plain_text_response`, and RPC or tool errors are surfaced as the `error` string): Format 1: Plain text. The text will be placed into a field called `plain_text_response`, example: diff --git a/tools/server/README.md b/tools/server/README.md index f45c018972d2..c8e7fcdcf2e0 100644 --- a/tools/server/README.md +++ b/tools/server/README.md @@ -133,14 +133,14 @@ For the full list of features, please refer to [server's changelog](https://gith | `--xtc-probability N` | xtc probability (default: 0.00, 0.0 = disabled) | | `--xtc-threshold N` | xtc threshold (default: 0.10, 1.0 = disabled) | | `--typical, --typical-p N` | locally typical sampling, parameter p (default: 1.00, 1.0 = disabled) | -| `--repeat-last-n N` | last n tokens to consider for penalize (default: 64, 0 = disabled, -1 = ctx_size) | +| `--repeat-last-n N` | last n tokens to consider for penalize (default: 64, 0 = disabled) | | `--repeat-penalty N` | penalize repeat sequence of tokens (default: 1.00, 1.0 = disabled) | | `--presence-penalty N` | repeat alpha presence penalty (default: 0.00, 0.0 = disabled) | | `--frequency-penalty N` | repeat alpha frequency penalty (default: 0.00, 0.0 = disabled) | | `--dry-multiplier N` | set DRY sampling multiplier (default: 0.00, 0.0 = disabled) | | `--dry-base N` | set DRY sampling base value (default: 1.75) | | `--dry-allowed-length N` | set allowed length for DRY sampling (default: 2) | -| `--dry-penalty-last-n N` | set DRY penalty for the last n tokens (default: -1, 0 = disable, -1 = context size) | +| `--dry-penalty-last-n N` | set DRY penalty for the last n tokens (default: 64, 0 = disable) | | `--dry-sequence-breaker STRING` | add sequence breaker for DRY sampling, clearing out default breakers ('\n', ':', '"', '*') in the process; use "none" to not use any sequence breakers | | `--adaptive-target N` | adaptive-p: select tokens near this probability (valid range 0.0 to 1.0; negative = disabled) (default: -1.00)
[(more info)](https://github.com/ggml-org/llama.cpp/pull/17927) | | `--adaptive-decay N` | adaptive-p: decay rate for target adaptation over time. lower values are more reactive, higher values are more stable.
(valid range 0.0 to 0.99) (default: 0.90) | @@ -198,7 +198,9 @@ For the full list of features, please refer to [server's changelog](https://gith | `--ui-config, --webui-config JSON` | JSON that provides default UI settings (overrides UI defaults)
(env: LLAMA_ARG_UI_CONFIG) | | `--ui-config-file, --webui-config-file PATH` | JSON file that provides default UI settings (overrides UI defaults)
(env: LLAMA_ARG_UI_CONFIG_FILE) | | `--ui-mcp-proxy, --webui-mcp-proxy, --no-ui-mcp-proxy, --no-webui-mcp-proxy` | experimental: whether to enable MCP CORS proxy - do not enable in untrusted environments (default: disabled)
(env: LLAMA_ARG_UI_MCP_PROXY) | -| `--tools TOOL1,TOOL2,...` | experimental: whether to enable built-in tools for AI agents - do not enable in untrusted environments (default: no tools)
specify "all" to enable all tools
available tools: read_file, file_glob_search, grep_search, exec_shell_command, write_file, edit_file, get_datetime
note: for security reasons, this will limit --cors-origins to localhost by default
(env: LLAMA_ARG_TOOLS) | +| `--tools TOOL1,TOOL2,...` | experimental: whether to enable built-in tools for AI agents - do not enable in untrusted environments (default: no tools)
specify "all" to enable all tools
available tools: read_file, file_glob_search, grep_search, exec_shell_command, write_file, edit_file, get_datetime, get_info
note: for security reasons, this will limit --cors-origins to localhost by default
(env: LLAMA_ARG_TOOLS) | +| `--mcp-servers-config PATH` | experimental: path to JSON file with MCP server definitions (Cursor-compatible format) - do not enable in untrusted environments (default: none)
note: for security reasons, this will limit --cors-origins to localhost by default
(env: LLAMA_ARG_MCP_SERVERS_CONFIG) | +| `--mcp-servers-json JSON` | experimental: inline JSON with MCP server definitions (Cursor-compatible format) - do not enable in untrusted environments (default: none)
note: for security reasons, this will limit --cors-origins to localhost by default
(env: LLAMA_ARG_MCP_SERVERS_JSON) | | `-ag, --agent, -no-ag, --no-agent` | whether to enable CORS proxy and all built-in tools - do not enable in untrusted environments (default: disabled)
note: for security reasons, this will limit --cors-origins to localhost by default
(env: LLAMA_ARG_AGENT) | | `--ui, --webui, --no-ui, --no-webui` | whether to enable the Web UI (default: enabled)
(env: LLAMA_ARG_UI) | | `--embedding, --embeddings` | restrict to only support embedding use case; use only with dedicated embedding models (default: disabled)
(env: LLAMA_ARG_EMBEDDINGS) | @@ -474,7 +476,7 @@ These words will not be included in the completion, so make sure to add them to `repeat_penalty`: Control the repetition of token sequences in the generated text. Default: `1.1` -`repeat_last_n`: Last n tokens to consider for penalizing repetition. Default: `64`, where `0` is disabled and `-1` is ctx-size. +`repeat_last_n`: Last n tokens to consider for penalizing repetition. Default: `64`, where `0` is disabled. `presence_penalty`: Repeat alpha presence penalty. Default: `0.0`, which is disabled. @@ -486,7 +488,7 @@ These words will not be included in the completion, so make sure to add them to `dry_allowed_length`: Tokens that extend repetition beyond this receive exponentially increasing penalty: multiplier * base ^ (length of repeating sequence before token - allowed length). Default: `2` -`dry_penalty_last_n`: How many tokens to scan for repetitions. Default: `-1`, where `0` is disabled and `-1` is context size. +`dry_penalty_last_n`: How many tokens to scan for repetitions. Default: `64`, where `0` is disabled. `dry_sequence_breakers`: Specify an array of sequence breakers for DRY sampling. Only a JSON array of strings is accepted. Default: `['\n', ':', '"', '*']` @@ -794,7 +796,7 @@ By default, it is read-only. To make POST request to change global properties, y "dry_multiplier": 0.0, "dry_base": 1.75, "dry_allowed_length": 2, - "dry_penalty_last_n": -1, + "dry_penalty_last_n": 64, "dry_sequence_breakers": [ "\n", ":", diff --git a/tools/server/server-context.cpp b/tools/server/server-context.cpp index 0f7ada435a29..380e62af6728 100644 --- a/tools/server/server-context.cpp +++ b/tools/server/server-context.cpp @@ -212,6 +212,7 @@ struct server_slot { llama_tokens spec_prompt; std::vector spec_i_batch; common_prompt_checkpoint spec_ckpt; + bool spec_is_replay = false; // TODO: move members that belong to the task (such as `generated_text`, `has_new_line`) to task_results_state // see https://github.com/ggml-org/llama.cpp/pull/18283#issuecomment-3710175837 @@ -332,6 +333,8 @@ struct server_slot { void reset() { SLT_DBG(*this, "%s", "\n"); + spec_is_replay = false; + n_prompt_tokens_cache = 0; last_nl_pos = 0; @@ -3875,6 +3878,7 @@ struct server_context_impl { } // partial acceptance is not supported by the context -> truncate the draft and restore the state + slot.spec_is_replay = true; slot.spec_draft = std::move(accepted); const auto & ckpt = slot.spec_ckpt; @@ -3909,16 +3913,22 @@ struct server_context_impl { const auto ids = std::move(slot.spec_draft); + size_t n_accepted = ids.size() - 1; + if (slot.spec_is_replay && n_accepted > 0) { + n_accepted--; + } + slot.spec_is_replay = false; + slot.t_token_generation = std::max(1, t_now - slot.t_start_generation) / 1e3; // update how many tokens out of those tested were accepted - slot.n_draft_accepted += ids.size() - 1; + slot.n_draft_accepted += n_accepted; slot.n_draft_verif_steps += 1; if (slot.n_accepted_per_pos.empty()) { slot.n_accepted_per_pos.resize(common_speculative_n_max(¶ms_base.speculative), 0); } - for (size_t i = 0; i < ids.size() - 1 && i < slot.n_accepted_per_pos.size(); ++i) { + for (size_t i = 0; i < n_accepted && i < slot.n_accepted_per_pos.size(); ++i) { slot.n_accepted_per_pos[i]++; } @@ -3954,7 +3964,7 @@ struct server_context_impl { slot.print_timings_tg(); - SLT_DBG(slot, "accepted %d/%d draft tokens, new n_tokens = %d\n", (int) ids.size() - 1, (int) n_draft, slot.prompt.n_tokens()); + SLT_DBG(slot, "accepted %d/%d draft tokens, new n_tokens = %d\n", (int) n_accepted, (int) n_draft, slot.prompt.n_tokens()); }); } @@ -4137,7 +4147,6 @@ std::unique_ptr server_routes::handle_completions_impl( task.params = server_schema::eval_llama_cmpl_schema( ctx_server.vocab, params, - meta->slot_n_ctx, meta->logit_bias_eog, data); diff --git a/tools/server/server-schema.cpp b/tools/server/server-schema.cpp index 674d3ba337bc..5cef3908faa5 100644 --- a/tools/server/server-schema.cpp +++ b/tools/server/server-schema.cpp @@ -124,8 +124,8 @@ std::vector> make_llama_cmpl_schema(const common_params & ->set_desc("Dynamic temperature exponent, controls how entropy maps to temperature")); add((new field_num("repeat_last_n", params.sampling.penalty_last_n)) - ->set_hard_limits(-1, INT32_MAX) - ->set_desc("Last n tokens to consider for penalizing repetition (0 = disabled, -1 = ctx-size)")); + ->set_hard_limits(0, INT32_MAX) + ->set_desc("Last n tokens to consider for penalizing repetition (0 = disabled)")); add((new field_num("repeat_penalty", params.sampling.penalty_repeat)) ->set_desc("Control the repetition of token sequences in the generated text (1.0 = disabled)")); @@ -151,8 +151,8 @@ std::vector> make_llama_cmpl_schema(const common_params & ->set_desc("Tokens that extend repetition beyond this length receive exponentially increasing penalty: multiplier * base ^ (sequence_length - allowed_length)")); add((new field_num("dry_penalty_last_n", params.sampling.dry_penalty_last_n)) - ->set_hard_limits(-1, INT32_MAX) - ->set_desc("How many tokens to scan for repetitions (0 = disabled, -1 = context size)")); + ->set_hard_limits(0, INT32_MAX) + ->set_desc("How many tokens to scan for repetitions (0 = disabled)")); add((new field_num("mirostat", params.sampling.mirostat)) ->set_limits(0, 2) @@ -515,7 +515,6 @@ std::vector> make_llama_cmpl_schema(const common_params & task_params eval_llama_cmpl_schema( const llama_vocab * vocab, const common_params & params_base, - const int n_ctx_slot, const std::vector & logit_bias_eog, const json & data) { task_params params; @@ -549,15 +548,6 @@ task_params eval_llama_cmpl_schema( // post-processing { - if (params.sampling.penalty_last_n == -1) { - // note: should be the slot's context and not the full context, but it's ok - params.sampling.penalty_last_n = n_ctx_slot; - } - - if (params.sampling.dry_penalty_last_n == -1) { - params.sampling.dry_penalty_last_n = n_ctx_slot; - } - // if "reasoning_format" is not provided, its handler will not be called, we will need to handle it here auto reasoning_format = params.chat_parser_params.reasoning_format; params.chat_parser_params.reasoning_in_content = params.stream && (reasoning_format == COMMON_REASONING_FORMAT_DEEPSEEK_LEGACY); diff --git a/tools/server/server-schema.h b/tools/server/server-schema.h index 08cf427dc983..d0a81431bc6b 100644 --- a/tools/server/server-schema.h +++ b/tools/server/server-schema.h @@ -98,7 +98,6 @@ std::vector> make_llama_cmpl_schema( task_params eval_llama_cmpl_schema( const llama_vocab * vocab, const common_params & params_base, - const int n_ctx_slot, const std::vector & logit_bias_eog, const json & data); diff --git a/tools/server/server-tools.cpp b/tools/server/server-tools.cpp index 90b7e2a9f0ee..5309de5ef3bc 100644 --- a/tools/server/server-tools.cpp +++ b/tools/server/server-tools.cpp @@ -10,17 +10,67 @@ #include #include #include +#include #include #include +#include #include #include +#if defined(_WIN32) +# ifndef NOMINMAX +# define NOMINMAX +# endif +# include +#endif + namespace fs = std::filesystem; // // internal helpers // +#if defined(_WIN32) +// A chunk can end in the middle of a multi-byte sequence, so the incomplete +// tail is dropped before validating what precedes it. +static bool is_utf8_text(const std::string & text) { + return is_valid_utf8(text.substr(0, validate_utf8(text))); +} + +// A child process writes its output in the OEM code page, which is not UTF-8 +// on a western Windows install, so accented text reaches the JSON layer as +// invalid bytes and is replaced there. Text that already decodes as UTF-8 is +// returned untouched, so a child that emits UTF-8 is never decoded twice. +// run() spawns without a console, so the console code page does not apply. +static std::string console_output_to_utf8(const std::string & text) { + if (text.empty() || is_utf8_text(text)) { + return text; + } + + const UINT cp = GetOEMCP(); + + // fail rather than emit replacement characters when the code page is wrong + const int wide_len = MultiByteToWideChar(cp, MB_ERR_INVALID_CHARS, text.data(), (int) text.size(), nullptr, 0); + if (wide_len <= 0) { + return text; + } + std::wstring wide(wide_len, L'\0'); + MultiByteToWideChar(cp, MB_ERR_INVALID_CHARS, text.data(), (int) text.size(), wide.data(), wide_len); + + const int utf8_len = WideCharToMultiByte(CP_UTF8, 0, wide.data(), wide_len, nullptr, 0, nullptr, nullptr); + if (utf8_len <= 0) { + return text; + } + std::string utf8(utf8_len, '\0'); + WideCharToMultiByte(CP_UTF8, 0, wide.data(), wide_len, utf8.data(), utf8_len, nullptr, nullptr); + return utf8; +} +#else +static std::string console_output_to_utf8(const std::string & text) { + return text; +} +#endif + json server_tool::to_json() const { return { {"display_name", display_name}, @@ -34,7 +84,40 @@ json server_tool::to_json() const { } static constexpr size_t SERVER_TOOL_GIT_LS_FILES_MAX_OUTPUT = 8 * 1024 * 1024; // 8 MB -static constexpr int SERVER_TOOL_GIT_LS_FILES_TIMEOUT = 15; // seconds +// budget for one listing call, shared by the git and walker paths +static constexpr int SERVER_TOOL_LIST_ENTRIES_TIMEOUT = 15; // seconds + +// entry kinds a directory listing may return +enum class list_kind { + files, // regular files only + dirs, // directories only + all, // both +}; + +// home directory, read once at first use (getenv is not thread safe against setenv) +static const std::string & home_dir() { + static const std::string home = [] { + const char * h = getenv("HOME"); +#ifdef _WIN32 + if (h == nullptr) h = getenv("USERPROFILE"); +#endif + return h ? std::string(h) : std::string(); + }(); + return home; +} + +static std::string expand_home(const std::string & path) { + if (path.empty() || path[0] != '~') return path; + if (path.size() > 1 && path[1] != '/' && path[1] != '\\') return path; + const std::string & home = home_dir(); + if (home.empty()) return path; + return home + path.substr(1); +} + +// depth of a '/'-separated relative path: "a/b/c" is 3 +static int entry_depth(const std::string & rel) { + return 1 + (int) std::count(rel.begin(), rel.end(), '/'); +} class tools_io { public: @@ -51,8 +134,17 @@ class tools_io { virtual bool file_size(const std::string & path, uintmax_t & out_size) const = 0; virtual bool read_file(const std::string & path, std::string & out) const = 0; virtual bool write_file(const std::string & path, const std::string & content) const = 0; - // paths relative to `base`, '/'-separated; sets `err` if `base` isn't a directory - virtual std::vector list_files(const std::string & base, std::string & err) const = 0; + // resolve `path` against the IO's working directory; absolute paths are returned unchanged + virtual std::string resolve(const std::string & path) const = 0; + struct list_entry { + std::string rel; // '/'-separated, relative to `base` + bool is_dir = false; + }; + // entries relative to `base`; sets `err` if `base` isn't a directory + // max_depth == 0 means unlimited, 1 means direct children of `base` only + // `base` must already be resolved (absolute); `caller_path` is the path the + // caller passed, used only for error messages + virtual std::vector list_entries(const std::string & base, const std::string & caller_path, int max_depth, list_kind kind, std::string & err, bool & truncated) const = 0; // on_chunk, if set, is called with each chunk of output as it is read (before truncation cuts in); // returning false terminates the process early (e.g. the client disconnected) virtual exec_result run( @@ -64,24 +156,43 @@ class tools_io { class tools_io_basic : public tools_io { public: + // cwd, if non-empty, is used to resolve relative paths and as the working directory for run() + explicit tools_io_basic(std::string cwd = "") : cwd(std::move(cwd)) {} + + // expands a leading `~`, then resolves `path` against `cwd` (or the server + // working directory when `cwd` is unset); the result is always absolute + std::string resolve(const std::string & path) const override { + std::string p = expand_home(path); + if (fs::path(p).is_absolute()) { + return p; + } + if (cwd.empty()) { + std::error_code ec; + fs::path cur = fs::current_path(ec); + if (ec) return p; + return (cur / p).string(); + } + return (fs::path(cwd) / p).string(); + } + bool is_directory(const std::string & path) const override { std::error_code ec; - return fs::is_directory(path, ec) && !ec; + return fs::is_directory(resolve(path), ec) && !ec; } bool is_regular_file(const std::string & path) const override { std::error_code ec; - return fs::is_regular_file(path, ec) && !ec; + return fs::is_regular_file(resolve(path), ec) && !ec; } bool file_size(const std::string & path, uintmax_t & out_size) const override { std::error_code ec; - out_size = fs::file_size(path, ec); + out_size = fs::file_size(resolve(path), ec); return !ec; } bool read_file(const std::string & path, std::string & out) const override { - std::ifstream f(path, std::ios::binary); + std::ifstream f(resolve(path), std::ios::binary); if (!f) return false; std::ostringstream ss; ss << f.rdbuf(); @@ -91,44 +202,52 @@ class tools_io_basic : public tools_io { bool write_file(const std::string & path, const std::string & content) const override { std::error_code ec; - fs::path fpath(path); + fs::path fpath(resolve(path)); if (fpath.has_parent_path()) { fs::create_directories(fpath.parent_path(), ec); if (ec) return false; } - std::ofstream f(path, std::ios::binary); + std::ofstream f(fpath, std::ios::binary); if (!f) return false; f << content; return (bool) f; } - std::vector list_files(const std::string & base, std::string & err) const override { + std::vector list_entries(const std::string & base, const std::string & caller_path, int max_depth, list_kind kind, std::string & err, bool & truncated) const override { err.clear(); - if (!is_directory(base)) { - err = "path does not exist or is not a directory: " + base; + truncated = false; + std::error_code ec; + if (!fs::is_directory(base, ec) || ec) { + err = "path does not exist or is not a directory: " + caller_path; return {}; } - auto res = run( - {"git", "-C", base, "ls-files", "--cached", "--others", "--exclude-standard"}, - SERVER_TOOL_GIT_LS_FILES_MAX_OUTPUT, SERVER_TOOL_GIT_LS_FILES_TIMEOUT); - - if (res.exit_code == 0 && !res.timed_out) { - std::vector result; - std::istringstream iss(res.output); - std::string line; - while (std::getline(iss, line)) { - if (!line.empty() && line.back() == '\r') line.pop_back(); - if (line.empty()) continue; - std::replace(line.begin(), line.end(), '\\', '/'); - if (is_regular_file((fs::path(base) / line).string())) { - result.push_back(line); + const auto deadline = std::chrono::steady_clock::now() + std::chrono::seconds(SERVER_TOOL_LIST_ENTRIES_TIMEOUT); + + // git ls-files cannot list directories; use the walker when they are requested + if (kind == list_kind::files) { + auto res = run( + {"git", "-C", base, "ls-files", "--cached", "--others", "--exclude-standard"}, + SERVER_TOOL_GIT_LS_FILES_MAX_OUTPUT, SERVER_TOOL_LIST_ENTRIES_TIMEOUT); + + if (res.exit_code == 0 && !res.timed_out) { + std::vector result; + std::istringstream iss(res.output); + std::string line; + while (std::getline(iss, line)) { + if (!line.empty() && line.back() == '\r') line.pop_back(); + if (line.empty()) continue; + std::replace(line.begin(), line.end(), '\\', '/'); + if (max_depth > 0 && entry_depth(line) > max_depth) continue; + if (is_regular_file((fs::path(base) / line).string())) { + result.push_back({line, false}); + } } + return result; } - return result; } - return list_files_fallback(base); + return list_entries_fallback(base, max_depth, kind, deadline, truncated); } exec_result run( @@ -145,7 +264,7 @@ class tools_io_basic : public tools_io { | subprocess_option_inherit_environment | subprocess_option_search_user_path; - if (!proc.create(args, options)) { + if (!proc.create(args, options, {}, cwd.empty() ? nullptr : cwd.c_str())) { res.output = "failed to spawn process"; return res; } @@ -175,14 +294,14 @@ class tools_io_basic : public tools_io { size_t len = strlen(buf); if (output.size() + len <= max_output) { output.append(buf, len); - if (on_chunk && !on_chunk(std::string(buf, len))) { + if (on_chunk && !on_chunk(console_output_to_utf8(std::string(buf, len)))) { proc.terminate(); break; } } else { size_t remaining = max_output - output.size(); output.append(buf, remaining); - if (on_chunk && remaining > 0) on_chunk(std::string(buf, remaining)); + if (on_chunk && remaining > 0) on_chunk(console_output_to_utf8(std::string(buf, remaining))); truncated = true; } } @@ -196,7 +315,7 @@ class tools_io_basic : public tools_io { res.exit_code = proc.join(); - res.output = output; + res.output = console_output_to_utf8(output); res.timed_out = timed_out.load(); if (truncated) { res.output += "\n[output truncated]"; @@ -205,6 +324,8 @@ class tools_io_basic : public tools_io { } private: + std::string cwd; + static const std::unordered_set & junk_dir_names() { static const std::unordered_set names = { ".git", ".svn", ".hg", "node_modules", "__pycache__", @@ -213,28 +334,50 @@ class tools_io_basic : public tools_io { return names; } - std::vector list_files_fallback(const std::string & base) const { - std::vector result; + std::vector list_entries_fallback(const std::string & base, int max_depth, list_kind kind, + std::chrono::steady_clock::time_point deadline, bool & truncated) const { + std::vector result; std::error_code ec; - std::vector> stack; - stack.emplace_back(fs::path(base), fs::path()); + std::vector> stack; + stack.emplace_back(fs::path(base), fs::path(), 0); while (!stack.empty()) { - auto [dir, rel_dir] = stack.back(); + auto [dir, rel_dir, depth] = stack.back(); stack.pop_back(); - for (const auto & entry : fs::directory_iterator(dir, fs::directory_options::skip_permission_denied, ec)) { + // the throwing increment would escape the tool on a directory that + // goes away mid walk, so step the iterator explicitly + fs::directory_iterator it(dir, fs::directory_options::skip_permission_denied, ec); + for (const fs::directory_iterator end; it != end; it.increment(ec)) { if (ec) break; + if (std::chrono::steady_clock::now() >= deadline) { + truncated = true; + return result; + } + const fs::directory_entry & entry = *it; std::string fname = entry.path().filename().string(); std::error_code tec; if (entry.is_directory(tec)) { + std::string rel = (rel_dir / fname).string(); + std::replace(rel.begin(), rel.end(), '\\', '/'); + if (kind == list_kind::dirs || kind == list_kind::all) { + result.push_back({rel, true}); + } + // junk directories stay selectable but are never walked: they + // hold nothing worth searching and can be enormous if (junk_dir_names().count(fname) > 0) continue; - stack.emplace_back(entry.path(), rel_dir / fname); + // do not descend into symlinks: a link can point back to an + // ancestor and loop forever + if (!entry.is_symlink(tec) && (max_depth == 0 || depth + 1 < max_depth)) { + stack.emplace_back(entry.path(), rel_dir / fname, depth + 1); + } } else if (entry.is_regular_file(tec)) { std::string rel = (rel_dir / fname).string(); std::replace(rel.begin(), rel.end(), '\\', '/'); - result.push_back(rel); + if (kind == list_kind::files || kind == list_kind::all) { + result.push_back({rel, false}); + } } } } @@ -244,8 +387,8 @@ class tools_io_basic : public tools_io { }; static std::unique_ptr make_tools_io(const json & params) { - GGML_UNUSED(params); // TODO in follow-up PR - return std::make_unique(); + std::string cwd = json_value(params, "cwd", std::string()); + return std::make_unique(cwd); } // no '/' in pattern -> match basename at any depth; else match full relative path @@ -349,6 +492,9 @@ struct server_tool_read_file : server_tool { // static constexpr size_t SERVER_TOOL_FILE_SEARCH_MAX_RESULTS = 100; +static constexpr const char * SERVER_TOOL_FILE_SEARCH_TYPE_FILE = "file"; +static constexpr const char * SERVER_TOOL_FILE_SEARCH_TYPE_DIR = "dir"; +static constexpr const char * SERVER_TOOL_FILE_SEARCH_TYPE_ALL = "all"; struct server_tool_file_glob_search : server_tool { server_tool_file_glob_search() { @@ -368,13 +514,18 @@ struct server_tool_file_glob_search : server_tool { "and common junk directories (.git, node_modules, build, dist, etc.) otherwise. " "A pattern with no '/' (e.g. \"*.cpp\") matches the file's basename at any depth. " "A pattern containing '/' matches the full relative path; unless already anchored with " - "\"**/\" or a leading '/', it is automatically prefixed with \"**/\"."}, + "\"**/\" or a leading '/', it is automatically prefixed with \"**/\". " + "Use type=\"dir\" or \"all\" to also list directories; directory entries are suffixed with '/' in the output. " + "Note: directory listings do not apply .gitignore filtering."}, {"parameters", { {"type", "object"}, {"properties", { - {"path", {{"type", "string"}, {"description", "Base directory to search in"}}}, - {"include", {{"type", "string"}, {"description", "Glob pattern for files to include (e.g. \"*.cpp\" or \"src/**/*.cpp\"). Default: **"}}}, - {"exclude", {{"type", "string"}, {"description", "Glob pattern for files to exclude"}}}, + {"path", {{"type", "string"}, {"description", "Base directory to search in"}}}, + {"include", {{"type", "string"}, {"description", "Glob pattern for files to include (e.g. \"*.cpp\" or \"src/**/*.cpp\"). Default: **"}}}, + {"exclude", {{"type", "string"}, {"description", "Glob pattern for files to exclude"}}}, + {"type", {{"type", "string"}, {"description", "Entry type to return: \"file\" (default), \"dir\" or \"all\""}}}, + {"max_depth", {{"type", "integer"}, {"description", "Maximum depth to descend into subdirectories (default: 0 = unlimited; 1 = direct children only)"}}}, + {"limit", {{"type", "integer"}, {"description", string_format("Maximum number of results to return (default %zu; values below 1 fall back to the default)", SERVER_TOOL_FILE_SEARCH_MAX_RESULTS)}}}, }}, {"required", json::array({"path"})}, }}, @@ -383,30 +534,56 @@ struct server_tool_file_glob_search : server_tool { } json invoke(json params, server_tool::stream *) const override { - std::string base = params.at("path").get(); - std::string include = json_value(params, "include", std::string("**")); - std::string exclude = json_value(params, "exclude", std::string("")); - auto io = make_tools_io(params); + + std::string base = io->resolve(params.at("path").get()); + // normalize to forward slashes so the web UI (which assumes '/') can + // join the relative entries into absolute paths on Windows too + std::replace(base.begin(), base.end(), '\\', '/'); + std::string include = json_value(params, "include", std::string("**")); + std::string exclude = json_value(params, "exclude", std::string("")); + std::string type = json_value(params, "type", std::string("file")); + int max_depth = std::max(0, json_value(params, "max_depth", 0)); + int limit = json_value(params, "limit", (int) SERVER_TOOL_FILE_SEARCH_MAX_RESULTS); + if (limit < 1) limit = SERVER_TOOL_FILE_SEARCH_MAX_RESULTS; + limit = std::min(limit, (int) SERVER_TOOL_FILE_SEARCH_MAX_RESULTS); + + list_kind kind; + if (type == SERVER_TOOL_FILE_SEARCH_TYPE_FILE) { + kind = list_kind::files; + } else if (type == SERVER_TOOL_FILE_SEARCH_TYPE_DIR) { + kind = list_kind::dirs; + } else if (type == SERVER_TOOL_FILE_SEARCH_TYPE_ALL) { + kind = list_kind::all; + } else { + return {{"error", "invalid type: " + type + " (expected \"file\", \"dir\" or \"all\")"}}; + } + std::string err; - auto files = io->list_files(base, err); + bool truncated = false; + auto entries = io->list_entries(base, params.at("path").get(), max_depth, kind, err, truncated); if (!err.empty()) { return {{"error", err}}; } - std::vector matches; - for (const auto & rel : files) { - if (!path_glob_match(include, rel)) continue; - if (!exclude.empty() && path_glob_match(exclude, rel)) continue; - matches.push_back(rel); + std::vector matches; + for (const auto & entry : entries) { + if (!path_glob_match(include, entry.rel)) continue; + if (!exclude.empty() && path_glob_match(exclude, entry.rel)) continue; + matches.push_back(entry); } size_t total = matches.size(); - size_t shown = std::min(total, SERVER_TOOL_FILE_SEARCH_MAX_RESULTS); + size_t shown = std::min(total, (size_t) limit); std::ostringstream output_text; + json entries_json = json::array(); for (size_t i = 0; i < shown; i++) { - output_text << matches[i] << "\n"; + output_text << matches[i].rel << (matches[i].is_dir ? "/" : "") << "\n"; + entries_json.push_back({ + {"path", matches[i].rel}, + {"type", matches[i].is_dir ? "dir" : "file"}, + }); } output_text << "\n---\nTotal matches: " << total << "\n"; @@ -415,8 +592,16 @@ struct server_tool_file_glob_search : server_tool { "[%zu results limit reached (%zu total matches). Refine the glob pattern to narrow the search.]\n", shown, total); } + if (truncated) { + output_text << "[search timed out, results truncated]\n"; + } - return {{"plain_text_response", output_text.str()}}; + // `base` is always absolute (resolve falls back to the server cwd), so + // API clients (e.g. the web UI picker) can join the relative entries + // into absolute paths. `plain_text_response` is what the model sees; + // `entries` is the same data as structured JSON for the UI picker, + // which reads `entries`/`base` instead of re-parsing the text. + return {{"plain_text_response", output_text.str()}, {"entries", entries_json}, {"base", base}}; } }; @@ -499,18 +684,20 @@ struct server_tool_grep_search : server_tool { // collect (absolute_path, display_path) pairs to search std::vector> files; - if (io->is_regular_file(path)) { - files.emplace_back(path, path); - } else if (io->is_directory(path)) { + const std::string abs_path = io->resolve(path); + if (io->is_regular_file(abs_path)) { + files.emplace_back(abs_path, path); + } else if (io->is_directory(abs_path)) { std::string err; - auto candidates = io->list_files(path, err); + bool truncated = false; + auto candidates = io->list_entries(abs_path, path, 0, list_kind::files, err, truncated); if (!err.empty()) { return {{"error", err}}; } - for (const auto & rel : candidates) { - if (!path_glob_match(include, rel)) continue; - if (!exclude.empty() && path_glob_match(exclude, rel)) continue; - files.emplace_back((fs::path(path) / rel).string(), rel); + for (const auto & entry : candidates) { + if (!path_glob_match(include, entry.rel)) continue; + if (!exclude.empty() && path_glob_match(exclude, entry.rel)) continue; + files.emplace_back((fs::path(abs_path) / entry.rel).string(), entry.rel); } } else { return {{"error", "path does not exist: " + path}}; @@ -1076,6 +1263,59 @@ struct server_tool_get_datetime : server_tool { } }; +// +// get_info: returns runtime info (OS name/version and cwd) +// + +static constexpr size_t SERVER_TOOL_GET_INFO_MAX_OUTPUT = 4096; +static constexpr int SERVER_TOOL_GET_INFO_TIMEOUT = 5; // seconds + +struct server_tool_get_info : server_tool { + server_tool_get_info() { + name = "get_info"; + display_name = "Get Runtime Info"; + permission_write = false; + } + + json get_definition() const override { + return { + {"type", "function"}, + {"function", { + {"name", name}, + {"description", "Returns runtime info: the OS name/version and the current working directory"}, + {"parameters", { + {"type", "object"}, + {"properties", json::object()}, + }}, + }}, + }; + } + + json invoke(json params, server_tool::stream *) const override { + auto io = make_tools_io(params); + +#ifdef _WIN32 + auto res = io->run({"cmd", "/c", "ver"}, SERVER_TOOL_GET_INFO_MAX_OUTPUT, SERVER_TOOL_GET_INFO_TIMEOUT); +#else + auto res = io->run({"uname", "-a"}, SERVER_TOOL_GET_INFO_MAX_OUTPUT, SERVER_TOOL_GET_INFO_TIMEOUT); +#endif + // "ver" prints a blank line before the version, so the output is stripped on both ends; + // a failed spawn or a timeout leaves a diagnostic in res.output, which is not an OS name + std::string os_info = res.exit_code == 0 && !res.timed_out ? string_strip(res.output) : "unknown"; + + std::string cwd = json_value(params, "cwd", std::string()); + if (cwd.empty()) { + std::error_code ec; + cwd = fs::current_path(ec).string(); + } + + return { + {"os", os_info}, + {"cwd", cwd}, + }; + } +}; + struct server_tool_stream_result : server_task_result { std::string chunk; bool done = false; @@ -1185,9 +1425,26 @@ static std::vector> build_tools() { tools.push_back(std::make_unique()); tools.push_back(std::make_unique()); tools.push_back(std::make_unique()); + tools.push_back(std::make_unique()); return tools; } +static std::string str_to_lower(const std::string & value) { + std::string lowered(value.size(), '\0'); + std::transform(value.begin(), value.end(), lowered.begin(), [](unsigned char c) { return std::tolower(c); }); + return lowered; +} + +static std::string get_header(const std::map & headers, const std::string & key, std::string default_value = "") { + const auto lowered_key = str_to_lower(key); + for (const auto & h : headers) { + if (str_to_lower(h.first) == lowered_key) { + return h.second; + } + } + return default_value; +} + void server_tools::setup(const std::vector & enabled_tools, server_mcp & mcp_mgr) { if (!enabled_tools.empty()) { @@ -1271,6 +1528,12 @@ void server_tools::setup(const std::vector & enabled_tools, json params = body.value("params", json::object()); bool stream = body.value("stream", false); + // accept x-tool-cwd header to override of the process + auto cwd = get_header(req.headers, "x-tool-cwd"); + if (!cwd.empty()) { + params["cwd"] = cwd; + } + server_tool & tool = find_tool(tools, tool_name, stream); if (stream) { diff --git a/tools/server/server.cpp b/tools/server/server.cpp index a3b2a8b0fe1b..aafb1f307966 100644 --- a/tools/server/server.cpp +++ b/tools/server/server.cpp @@ -486,6 +486,13 @@ int llama_server(common_params & params, int argc, char ** argv) { SRV_INF("listening on %s\n", ctx_http.listening_address.c_str()); + // TODO: remove this in the future + // check the string to also handle the .sock case + if (string_ends_with(ctx_http.listening_address, ":8080")) { + SRV_WRN("%s", "NOTICE: server default port will be changed to :9931 in a future release\n"); + SRV_WRN("%s", " ref: https://github.com/ggml-org/llama.cpp/pull/26508\n"); + } + if (is_router_server) { if (!params.models_preset_hf.empty()) { SRV_WRN( "NOTE: using preset.ini from HF repo '%s'\n", params.models_preset_hf.c_str()); diff --git a/tools/server/tests/unit/test_tools_builtin.py b/tools/server/tests/unit/test_tools_builtin.py index 1b2d0db43231..e713758d91df 100755 --- a/tools/server/tests/unit/test_tools_builtin.py +++ b/tools/server/tests/unit/test_tools_builtin.py @@ -19,8 +19,8 @@ def create_server(): server.server_tools = "all" -def call_tool(name: str, params: dict) -> dict: - res = server.make_request("POST", "/tools", data={"tool": name, "params": params}) +def call_tool(name: str, params: dict, headers: dict | None = None) -> dict: + res = server.make_request("POST", "/tools", data={"tool": name, "params": params}, headers=headers) assert res.status_code == 200, res.body assert "error" not in res.body, res.body return res.body @@ -123,6 +123,29 @@ def test_tools_builtin_exec_shell_command_stream(): assert "[exit code: 0]" in chunks +def test_tools_builtin_cwd_header(): + global server + server.start() + + cwd_dir = os.path.join(PROJECT_ROOT, "tools", "server", "tests", "unit") + headers = {"x-tool-cwd": cwd_dir} + + res = call_tool("read_file", {"path": "test_tools_builtin.py"}, headers=headers) + assert GREP_MARKER in res["plain_text_response"] + + # exec_shell_command should also run with that directory as its working directory: + # writing to a relative filename must land inside cwd_dir + marker_name = "llama_cpp_test_tools_builtin_cwd_marker.txt" + marker_path = os.path.join(cwd_dir, marker_name) + try: + command = f"echo hello > {marker_name}" + call_tool("exec_shell_command", {"command": command}, headers=headers) + assert os.path.exists(marker_path) + finally: + if os.path.exists(marker_path): + os.remove(marker_path) + + def test_tools_builtin_edit_file_rejects_overlapping_edits(): global server server.start() @@ -141,3 +164,101 @@ def test_tools_builtin_edit_file_rejects_overlapping_edits(): finally: if os.path.exists(log_path): os.remove(log_path) + + +def test_tools_builtin_file_glob_search_type_dir(tmp_path): + global server + server.start() + + (tmp_path / "project-alpha" / "src").mkdir(parents=True) + (tmp_path / "project-alpha" / "README.md").write_text("alpha") + (tmp_path / "project-alpha" / "src" / "main.cpp").write_text("int main() {}") + (tmp_path / "project-beta").mkdir() + (tmp_path / "project-beta" / "notes.txt").write_text("beta") + + res = call_tool("file_glob_search", {"path": str(tmp_path), "type": "dir"}) + text = res["plain_text_response"] + assert "project-alpha/" in text + assert "project-beta/" in text + assert "project-alpha/src/" in text + assert "README.md" not in text + types = {e["path"]: e["type"] for e in res["entries"]} + assert types["project-alpha"] == "dir" + assert types["project-alpha/src"] == "dir" + + res_all = call_tool("file_glob_search", {"path": str(tmp_path), "type": "all", "include": "*proj*"}) + paths = [e["path"] for e in res_all["entries"]] + assert "project-alpha" in paths + assert "project-beta" in paths + + +def test_tools_builtin_file_glob_search_max_depth_and_limit(tmp_path): + global server + server.start() + + (tmp_path / "a" / "b" / "c").mkdir(parents=True) + (tmp_path / "top.txt").write_text("top") + (tmp_path / "a" / "mid.txt").write_text("mid") + (tmp_path / "a" / "b" / "deep.txt").write_text("deep") + + res = call_tool("file_glob_search", {"path": str(tmp_path), "max_depth": 1}) + assert "top.txt" in res["plain_text_response"] + assert "mid.txt" not in res["plain_text_response"] + + res = call_tool("file_glob_search", {"path": str(tmp_path), "max_depth": 2}) + assert "mid.txt" in res["plain_text_response"] + assert "deep.txt" not in res["plain_text_response"] + + res = call_tool("file_glob_search", {"path": str(tmp_path), "limit": 1}) + assert len(res["entries"]) == 1 + assert "Total matches: 3" in res["plain_text_response"] + + +def test_tools_builtin_file_glob_search_rejects_invalid_type(tmp_path): + global server + server.start() + + err = call_tool_expect_error("file_glob_search", {"path": str(tmp_path), "type": "bogus"}) + assert "invalid type" in err + + +def test_tools_builtin_cwd_header_overrides_model_param(tmp_path): + global server + server.start() + + workdir = tmp_path / "workdir" + workdir.mkdir() + (workdir / "marker.txt").write_text("marker") + + # a model-provided "cwd" in the params is overridden by the x-tool-cwd header + res = call_tool("read_file", {"path": "marker.txt", "cwd": "/definitely/not/a/real/path"}, + headers={"x-tool-cwd": str(workdir)}) + assert "marker" in res["plain_text_response"] + + +def test_tools_builtin_cwd_relative_paths(tmp_path): + global server + server.start() + + workdir = tmp_path / "workdir" + workdir.mkdir() + (workdir / "rel.txt").write_text("relative-content") + + headers = {"x-tool-cwd": str(workdir)} + + # relative paths in file tools resolve against the header cwd + res = call_tool("read_file", {"path": "rel.txt"}, headers=headers) + assert "relative-content" in res["plain_text_response"] + + res = call_tool("write_file", {"path": "sub/out.txt", "content": "written"}, headers=headers) + assert (workdir / "sub" / "out.txt").read_text() == "written" + + res = call_tool("file_glob_search", {"path": ".", "include": "*.txt"}, headers=headers) + assert "rel.txt" in res["plain_text_response"] + + # absolute paths are unaffected by the cwd + other = tmp_path / "other" + other.mkdir() + (other / "abs.txt").write_text("absolute-content") + res = call_tool("read_file", {"path": str(other / "abs.txt")}, headers=headers) + assert "absolute-content" in res["plain_text_response"] diff --git a/tools/tts/CMakeLists.txt b/tools/tts/CMakeLists.txt index 26a8bb8f2d1f..0a0b5730eaa6 100644 --- a/tools/tts/CMakeLists.txt +++ b/tools/tts/CMakeLists.txt @@ -1,6 +1,6 @@ set(TARGET llama-tts) add_executable(${TARGET} tts.cpp) -target_link_libraries(${TARGET} PRIVATE llama llama-common ${CMAKE_THREAD_LIBS_INIT}) +target_link_libraries(${TARGET} PRIVATE llama llama-common mtmd ${CMAKE_THREAD_LIBS_INIT}) target_compile_features(${TARGET} PRIVATE cxx_std_17) if(LLAMA_TOOLS_INSTALL) diff --git a/tools/tts/README.md b/tools/tts/README.md index 4749bb9f5a72..dd84336c3990 100644 --- a/tools/tts/README.md +++ b/tools/tts/README.md @@ -1,117 +1,34 @@ -# llama.cpp/example/tts -This example demonstrates the Text To Speech feature. It uses a -[model](https://www.outeai.com/blog/outetts-0.2-500m) from -[outeai](https://www.outeai.com/). +# llama.cpp TTS -## Quickstart -If you have built llama.cpp with SSL support you can simply run the -following command and the required models will be downloaded automatically: -```console -$ build/bin/llama-tts --tts-oute-default -p "Hello world" && aplay output.wav -``` -For details about the models and how to convert them to the required format -see the following sections. +This is a tool to demonstrate audio generation capability in llama.cpp via `libmtmd`. It was added via PR [#26254](https://github.com/ggml-org/llama.cpp/pull/26254) -### Model conversion -Checkout or download the model that contains the LLM model: -```console -$ pushd models -$ git clone --branch main --single-branch --depth 1 https://huggingface.co/OuteAI/OuteTTS-0.2-500M -$ cd OuteTTS-0.2-500M && git lfs install && git lfs pull -$ popd -``` -Convert the model to .gguf format: -```console -(venv) python convert_hf_to_gguf.py models/OuteTTS-0.2-500M \ - --outfile models/outetts-0.2-0.5B-f16.gguf --outtype f16 -``` -The generated model will be `models/outetts-0.2-0.5B-f16.gguf`. +Note: this tool used to serve as a demo for OuteTTS, but it was converted to a more model-agnostic tool. -We can optionally quantize this to Q8_0 using the following command: -```console -$ build/bin/llama-quantize models/outetts-0.2-0.5B-f16.gguf \ - models/outetts-0.2-0.5B-q8_0.gguf q8_0 -``` -The quantized model will be `models/outetts-0.2-0.5B-q8_0.gguf`. - -Next we do something similar for the audio decoder. First download or checkout -the model for the voice decoder: -```console -$ pushd models -$ git clone --branch main --single-branch --depth 1 https://huggingface.co/novateur/WavTokenizer-large-speech-75token -$ cd WavTokenizer-large-speech-75token && git lfs install && git lfs pull -$ popd -``` -This model file is a PyTorch checkpoint (.ckpt) and we first need to convert it to -huggingface format: -```console -(venv) python tools/tts/convert_pt_to_hf.py \ - models/WavTokenizer-large-speech-75token/wavtokenizer_large_speech_320_24k.ckpt -... -Model has been successfully converted and saved to models/WavTokenizer-large-speech-75token/model.safetensors -Metadata has been saved to models/WavTokenizer-large-speech-75token/index.json -Config has been saved to models/WavTokenizer-large-speech-75tokenconfig.json -``` -Then we can convert the huggingface format to gguf: -```console -(venv) python convert_hf_to_gguf.py models/WavTokenizer-large-speech-75token \ - --outfile models/wavtokenizer-large-75-f16.gguf --outtype f16 -... -INFO:hf-to-gguf:Model successfully exported to models/wavtokenizer-large-75-f16.gguf -``` +## Common usage -### Running the example +Simple usage: -With both of the models generated, the LLM model and the voice decoder model, -we can run the example: -```console -$ build/bin/llama-tts -m ./models/outetts-0.2-0.5B-q8_0.gguf \ - -mv ./models/wavtokenizer-large-75-f16.gguf \ - -p "Hello world" -... -main: audio written to file 'output.wav' -``` -The output.wav file will contain the audio of the prompt. This can be heard -by playing the file with a media player. On Linux the following command will -play the audio: -```console -$ aplay output.wav +```sh +llama-tts -hf ggml-org/Qwen3-TTS-12Hz-1.7B-Base-GGUF -p "Hello world" --output out.wav ``` -### Running the example with llama-server -Running this example with `llama-server` is also possible and requires two -server instances to be started. One will serve the LLM model and the other -will serve the voice decoder model. +Common params: +- Sampling params such as `--top-k`, `--top-p`, `--temp`, etc. +- `-n ` limits the output length, e.g. `-n 500`. Note that how many milliseconds each frame represents varies by model +- Core inference params such as `-ngl`, `-b`, `-ub`, etc. -The LLM model server can be started with the following command: -```console -$ ./build/bin/llama-server -m ./models/outetts-0.2-0.5B-q8_0.gguf --port 8020 -``` +## Qwen3-TTS -And the voice decoder model server can be started using: -```console -./build/bin/llama-server -m ./models/wavtokenizer-large-75-f16.gguf --port 8021 --embeddings --pooling none -``` +Available params: +- `--tts-lang` can be `zh`, `en`, `de`, `it`, `pt`, `es`, `ja`, `ko`, `fr`, `ru` (default: `en`) +- `--tts-speaker-file` should point to a speaker reference audio file (wav, mp3) -Then we can run [tts-outetts.py](tts-outetts.py) to generate the audio. +Example usage: -First create a virtual environment for python and install the required -dependencies (this in only required to be done once): -```console -$ python3 -m venv venv -$ source venv/bin/activate -(venv) pip install requests numpy -``` - -And then run the python script using: -```conole -(venv) python ./tools/tts/tts-outetts.py http://localhost:8020 http://localhost:8021 "Hello world" -spectrogram generated: n_codes: 90, n_embd: 1282 -converting to audio ... -audio generated: 28800 samples -audio written to file "output.wav" -``` -And to play the audio we can again use aplay or any other media player: -```console -$ aplay output.wav +```sh +llama-tts -hf ggml-org/Qwen3-TTS-12Hz-1.7B-Base-GGUF \ + -p "Hello world" \ + --tts-lang english \ + --tts-speaker-file speaker.mp3 \ + --output out.wav ``` diff --git a/tools/tts/convert_pt_to_hf.py b/tools/tts/convert_pt_to_hf.py deleted file mode 100644 index ebd55d9657b2..000000000000 --- a/tools/tts/convert_pt_to_hf.py +++ /dev/null @@ -1,180 +0,0 @@ -# convert the https://huggingface.co/novateur/WavTokenizer-large-speech-75token to HF format -# the goal is to be able to reuse the convert_hf_to_gguf.py after that to create a GGUF file with the WavTokenizer decoder -# -# TODO: this script is LLM-generated and probably very inefficient and should be rewritten - -import torch -import json -import os -import sys -import re - -from safetensors.torch import save_file - -# default -model_path = './model.pt' - -# read from CLI -if len(sys.argv) > 1: - model_path = sys.argv[1] - -# get the directory of the input model -path_dst = os.path.dirname(model_path) - -print(f"Loading model from {model_path}") - -model = torch.load(model_path, map_location='cpu') - -#print(model) - -# print all keys -for key in model.keys(): - print(key) - if key == 'hyper_parameters': - #print(model[key]) - # dump as json pretty - print(json.dumps(model[key], indent=4)) - #if key != 'state_dict' and key != 'optimizer_states': - # print(model[key]) - -# Check if the loaded model is a state_dict or a model instance -if isinstance(model, torch.nn.Module): - state_dict = model.state_dict() -else: - state_dict = model - -# Print the structure of the state_dict to understand its format -print("State dictionary keys:") -for key in state_dict.keys(): - print(key) - -# Ensure the state_dict is flat and contains only torch.Tensor objects -def flatten_state_dict(state_dict, parent_key='', sep='.'): - items = [] - items_new = [] - - for k, v in state_dict.items(): - new_key = f"{parent_key}{sep}{k}" if parent_key else k - if isinstance(v, torch.Tensor): - items.append((new_key, v)) - elif isinstance(v, dict): - items.extend(flatten_state_dict(v, new_key, sep=sep).items()) - return dict(items) - - size_total_mb = 0 - - for key, value in list(items): - # keep only what we need for inference - if not key.startswith('state_dict.feature_extractor.encodec.quantizer.') and \ - not key.startswith('state_dict.backbone.') and \ - not key.startswith('state_dict.head.out'): - print('Skipping key: ', key) - continue - - new_key = key - - new_key = new_key.replace('state_dict.', '') - new_key = new_key.replace('pos_net', 'posnet') - - # check if matches "backbone.posnet.%d.bias" or "backbone.posnet.%d.weight" - if new_key.startswith("backbone.posnet."): - match = re.match(r"backbone\.posnet\.(\d+)\.(bias|weight)", new_key) - if match: - new_key = f"backbone.posnet.{match.group(1)}.norm.{match.group(2)}" - - # "feature_extractor.encodec.quantizer.vq.layers.0._codebook.embed" -> "backbone.embedding.weight" - if new_key == "feature_extractor.encodec.quantizer.vq.layers.0._codebook.embed": - new_key = "backbone.embedding.weight" - - # these are the only rows used - # ref: https://github.com/edwko/OuteTTS/blob/a613e79c489d8256dd657ea9168d78de75895d82/outetts/wav_tokenizer/audio_codec.py#L100 - if new_key.endswith("norm.scale.weight"): - new_key = new_key.replace("norm.scale.weight", "norm.weight") - value = value[0] - - if new_key.endswith("norm.shift.weight"): - new_key = new_key.replace("norm.shift.weight", "norm.bias") - value = value[0] - - if new_key.endswith("gamma"): - new_key = new_key.replace("gamma", "gamma.weight") - - # convert from 1D [768] to 2D [768, 1] so that ggml_add can broadcast the bias - if (new_key.endswith("norm.weight") or new_key.endswith("norm1.weight") or new_key.endswith("norm2.weight") or new_key.endswith(".bias")) and (new_key.startswith("backbone.posnet") or new_key.startswith("backbone.embed.bias")): - value = value.unsqueeze(1) - - if new_key.endswith("dwconv.bias"): - value = value.unsqueeze(1) - - size_mb = value.element_size() * value.nelement() / (1024 * 1024) - print(f"{size_mb:8.2f} MB - {new_key}: {value.shape}") - - size_total_mb += size_mb - - #print(key, '->', new_key, ': ', value) - #print(key, '->', new_key) - - items_new.append((new_key, value)) - - print(f"Total size: {size_total_mb:8.2f} MB") - - return dict(items_new) - -flattened_state_dict = flatten_state_dict(state_dict) - - -# Convert the model to the safetensors format -output_path = path_dst + '/model.safetensors' -save_file(flattened_state_dict, output_path) - -print(f"Model has been successfully converted and saved to {output_path}") - -# Calculate the total size of the .safetensors file -total_size = os.path.getsize(output_path) - -# Create the weight map -weight_map = { - "model.safetensors": ["*"] # Assuming all weights are in one file -} - -# Create metadata for the index.json file -metadata = { - "total_size": total_size, - "weight_map": weight_map -} - -# Save the metadata to index.json -index_path = path_dst + '/index.json' -with open(index_path, 'w') as f: - json.dump(metadata, f, indent=4) - -print(f"Metadata has been saved to {index_path}") - -config = { - "architectures": [ - "WavTokenizerDec" - ], - "hidden_size": 1282, - "n_embd_features": 512, - "n_ff": 2304, - "vocab_size": 4096, - "n_head": 1, - "layer_norm_epsilon": 1e-6, - "group_norm_epsilon": 1e-6, - "group_norm_groups": 32, - "max_position_embeddings": 8192, # ? - "n_layer": 12, - "posnet": { - "n_embd": 768, - "n_layer": 6 - }, - "convnext": { - "n_embd": 768, - "n_layer": 12 - }, -} - -with open(path_dst + '/config.json', 'w') as f: - json.dump(config, f, indent=4) - -print(f"Config has been saved to {path_dst + 'config.json'}") diff --git a/tools/tts/tts-outetts.py b/tools/tts/tts-outetts.py deleted file mode 100644 index 3791f9fc3ebc..000000000000 --- a/tools/tts/tts-outetts.py +++ /dev/null @@ -1,299 +0,0 @@ -import sys -#import json -#import struct -import requests -import re -import struct -import numpy as np -from concurrent.futures import ThreadPoolExecutor - - -def fill_hann_window(size, periodic=True): - if periodic: - return np.hanning(size + 1)[:-1] - return np.hanning(size) - - -def irfft(n_fft, complex_input): - return np.fft.irfft(complex_input, n=n_fft) - - -def fold(buffer, n_out, n_win, n_hop, n_pad): - result = np.zeros(n_out) - n_frames = len(buffer) // n_win - - for i in range(n_frames): - start = i * n_hop - end = start + n_win - result[start:end] += buffer[i * n_win:(i + 1) * n_win] - - return result[n_pad:-n_pad] if n_pad > 0 else result - - -def process_frame(args): - l, n_fft, ST, hann = args - frame = irfft(n_fft, ST[l]) - frame = frame * hann - hann2 = hann * hann - return frame, hann2 - - -def embd_to_audio(embd, n_codes, n_embd, n_thread=4): - embd = np.asarray(embd, dtype=np.float32).reshape(n_codes, n_embd) - - n_fft = 1280 - n_hop = 320 - n_win = 1280 - n_pad = (n_win - n_hop) // 2 - n_out = (n_codes - 1) * n_hop + n_win - - hann = fill_hann_window(n_fft, True) - - E = np.zeros((n_embd, n_codes), dtype=np.float32) - for l in range(n_codes): - for k in range(n_embd): - E[k, l] = embd[l, k] - - half_embd = n_embd // 2 - S = np.zeros((n_codes, half_embd + 1), dtype=np.complex64) - - for k in range(half_embd): - for l in range(n_codes): - mag = E[k, l] - phi = E[k + half_embd, l] - - mag = np.clip(np.exp(mag), 0, 1e2) - S[l, k] = mag * np.exp(1j * phi) - - res = np.zeros(n_codes * n_fft) - hann2_buffer = np.zeros(n_codes * n_fft) - - with ThreadPoolExecutor(max_workers=n_thread) as executor: - args = [(l, n_fft, S, hann) for l in range(n_codes)] - results = list(executor.map(process_frame, args)) - - for l, (frame, hann2) in enumerate(results): - res[l*n_fft:(l+1)*n_fft] = frame - hann2_buffer[l*n_fft:(l+1)*n_fft] = hann2 - - audio = fold(res, n_out, n_win, n_hop, n_pad) - env = fold(hann2_buffer, n_out, n_win, n_hop, n_pad) - - mask = env > 1e-10 - audio[mask] /= env[mask] - - return audio - - -def save_wav(filename, audio_data, sample_rate): - num_channels = 1 - bits_per_sample = 16 - bytes_per_sample = bits_per_sample // 8 - data_size = len(audio_data) * bytes_per_sample - byte_rate = sample_rate * num_channels * bytes_per_sample - block_align = num_channels * bytes_per_sample - chunk_size = 36 + data_size # 36 = size of header minus first 8 bytes - - header = struct.pack( - '<4sI4s4sIHHIIHH4sI', - b'RIFF', - chunk_size, - b'WAVE', - b'fmt ', - 16, # fmt chunk size - 1, # audio format (PCM) - num_channels, - sample_rate, - byte_rate, - block_align, - bits_per_sample, - b'data', - data_size - ) - - audio_data = np.clip(audio_data * 32767, -32768, 32767) - pcm_data = audio_data.astype(np.int16) - - with open(filename, 'wb') as f: - f.write(header) - f.write(pcm_data.tobytes()) - - -def process_text(text: str): - text = re.sub(r'\d+(\.\d+)?', lambda x: x.group(), text.lower()) # TODO this needs to be fixed - text = re.sub(r'[-_/,\.\\]', ' ', text) - text = re.sub(r'[^a-z\s]', '', text) - text = re.sub(r'\s+', ' ', text).strip() - return text.split() - -# usage: -# python tts-outetts.py http://server-llm:port http://server-dec:port "text" - -if len(sys.argv) <= 3: - print("usage: python tts-outetts.py http://server-llm:port http://server-dec:port \"text\"") - exit(1) - -host_llm = sys.argv[1] -host_dec = sys.argv[2] -text = sys.argv[3] - -prefix = """<|im_start|> -<|text_start|>the<|text_sep|>overall<|text_sep|>package<|text_sep|>from<|text_sep|>just<|text_sep|>two<|text_sep|>people<|text_sep|>is<|text_sep|>pretty<|text_sep|>remarkable<|text_sep|>sure<|text_sep|>i<|text_sep|>have<|text_sep|>some<|text_sep|>critiques<|text_sep|>about<|text_sep|>some<|text_sep|>of<|text_sep|>the<|text_sep|>gameplay<|text_sep|>aspects<|text_sep|>but<|text_sep|>its<|text_sep|>still<|text_sep|>really<|text_sep|>enjoyable<|text_sep|>and<|text_sep|>it<|text_sep|>looks<|text_sep|>lovely<|text_sep|>""" - -words = process_text(text) -words = "<|text_sep|>".join([i.strip() for i in words]) -words += "<|text_end|>\n" - -# voice data -# TODO: load from json -#suffix = """<|audio_start|> -#the<|t_0.08|><|code_start|><|257|><|740|><|636|><|913|><|788|><|1703|><|code_end|> -#overall<|t_0.36|><|code_start|><|127|><|201|><|191|><|774|><|700|><|532|><|1056|><|557|><|798|><|298|><|1741|><|747|><|1662|><|1617|><|1702|><|1527|><|368|><|1588|><|1049|><|1008|><|1625|><|747|><|1576|><|728|><|1019|><|1696|><|1765|><|code_end|> -#package<|t_0.56|><|code_start|><|935|><|584|><|1319|><|627|><|1016|><|1491|><|1344|><|1117|><|1526|><|1040|><|239|><|1435|><|951|><|498|><|723|><|1180|><|535|><|789|><|1649|><|1637|><|78|><|465|><|1668|><|901|><|595|><|1675|><|117|><|1009|><|1667|><|320|><|840|><|79|><|507|><|1762|><|1508|><|1228|><|1768|><|802|><|1450|><|1457|><|232|><|639|><|code_end|> -#from<|t_0.19|><|code_start|><|604|><|782|><|1682|><|872|><|1532|><|1600|><|1036|><|1761|><|647|><|1554|><|1371|><|653|><|1595|><|950|><|code_end|> -#just<|t_0.25|><|code_start|><|1782|><|1670|><|317|><|786|><|1748|><|631|><|599|><|1155|><|1364|><|1524|><|36|><|1591|><|889|><|1535|><|541|><|440|><|1532|><|50|><|870|><|code_end|> -#two<|t_0.24|><|code_start|><|1681|><|1510|><|673|><|799|><|805|><|1342|><|330|><|519|><|62|><|640|><|1138|><|565|><|1552|><|1497|><|1552|><|572|><|1715|><|1732|><|code_end|> -#people<|t_0.39|><|code_start|><|593|><|274|><|136|><|740|><|691|><|633|><|1484|><|1061|><|1138|><|1485|><|344|><|428|><|397|><|1562|><|645|><|917|><|1035|><|1449|><|1669|><|487|><|442|><|1484|><|1329|><|1832|><|1704|><|600|><|761|><|653|><|269|><|code_end|> -#is<|t_0.16|><|code_start|><|566|><|583|><|1755|><|646|><|1337|><|709|><|802|><|1008|><|485|><|1583|><|652|><|10|><|code_end|> -#pretty<|t_0.32|><|code_start|><|1818|><|1747|><|692|><|733|><|1010|><|534|><|406|><|1697|><|1053|><|1521|><|1355|><|1274|><|816|><|1398|><|211|><|1218|><|817|><|1472|><|1703|><|686|><|13|><|822|><|445|><|1068|><|code_end|> -#remarkable<|t_0.68|><|code_start|><|230|><|1048|><|1705|><|355|><|706|><|1149|><|1535|><|1787|><|1356|><|1396|><|835|><|1583|><|486|><|1249|><|286|><|937|><|1076|><|1150|><|614|><|42|><|1058|><|705|><|681|><|798|><|934|><|490|><|514|><|1399|><|572|><|1446|><|1703|><|1346|><|1040|><|1426|><|1304|><|664|><|171|><|1530|><|625|><|64|><|1708|><|1830|><|1030|><|443|><|1509|><|1063|><|1605|><|1785|><|721|><|1440|><|923|><|code_end|> -#sure<|t_0.36|><|code_start|><|792|><|1780|><|923|><|1640|><|265|><|261|><|1525|><|567|><|1491|><|1250|><|1730|><|362|><|919|><|1766|><|543|><|1|><|333|><|113|><|970|><|252|><|1606|><|133|><|302|><|1810|><|1046|><|1190|><|1675|><|code_end|> -#i<|t_0.08|><|code_start|><|123|><|439|><|1074|><|705|><|1799|><|637|><|code_end|> -#have<|t_0.16|><|code_start|><|1509|><|599|><|518|><|1170|><|552|><|1029|><|1267|><|864|><|419|><|143|><|1061|><|0|><|code_end|> -#some<|t_0.16|><|code_start|><|619|><|400|><|1270|><|62|><|1370|><|1832|><|917|><|1661|><|167|><|269|><|1366|><|1508|><|code_end|> -#critiques<|t_0.60|><|code_start|><|559|><|584|><|1163|><|1129|><|1313|><|1728|><|721|><|1146|><|1093|><|577|><|928|><|27|><|630|><|1080|><|1346|><|1337|><|320|><|1382|><|1175|><|1682|><|1556|><|990|><|1683|><|860|><|1721|><|110|><|786|><|376|><|1085|><|756|><|1523|><|234|><|1334|><|1506|><|1578|><|659|><|612|><|1108|><|1466|><|1647|><|308|><|1470|><|746|><|556|><|1061|><|code_end|> -#about<|t_0.29|><|code_start|><|26|><|1649|><|545|><|1367|><|1263|><|1728|><|450|><|859|><|1434|><|497|><|1220|><|1285|><|179|><|755|><|1154|><|779|><|179|><|1229|><|1213|><|922|><|1774|><|1408|><|code_end|> -#some<|t_0.23|><|code_start|><|986|><|28|><|1649|><|778|><|858|><|1519|><|1|><|18|><|26|><|1042|><|1174|><|1309|><|1499|><|1712|><|1692|><|1516|><|1574|><|code_end|> -#of<|t_0.07|><|code_start|><|197|><|716|><|1039|><|1662|><|64|><|code_end|> -#the<|t_0.08|><|code_start|><|1811|><|1568|><|569|><|886|><|1025|><|1374|><|code_end|> -#gameplay<|t_0.48|><|code_start|><|1269|><|1092|><|933|><|1362|><|1762|><|1700|><|1675|><|215|><|781|><|1086|><|461|><|838|><|1022|><|759|><|649|><|1416|><|1004|><|551|><|909|><|787|><|343|><|830|><|1391|><|1040|><|1622|><|1779|><|1360|><|1231|><|1187|><|1317|><|76|><|997|><|989|><|978|><|737|><|189|><|code_end|> -#aspects<|t_0.56|><|code_start|><|1423|><|797|><|1316|><|1222|><|147|><|719|><|1347|><|386|><|1390|><|1558|><|154|><|440|><|634|><|592|><|1097|><|1718|><|712|><|763|><|1118|><|1721|><|1311|><|868|><|580|><|362|><|1435|><|868|><|247|><|221|><|886|><|1145|><|1274|><|1284|><|457|><|1043|><|1459|><|1818|><|62|><|599|><|1035|><|62|><|1649|><|778|><|code_end|> -#but<|t_0.20|><|code_start|><|780|><|1825|><|1681|><|1007|><|861|><|710|><|702|><|939|><|1669|><|1491|><|613|><|1739|><|823|><|1469|><|648|><|code_end|> -#its<|t_0.09|><|code_start|><|92|><|688|><|1623|><|962|><|1670|><|527|><|599|><|code_end|> -#still<|t_0.27|><|code_start|><|636|><|10|><|1217|><|344|><|713|><|957|><|823|><|154|><|1649|><|1286|><|508|><|214|><|1760|><|1250|><|456|><|1352|><|1368|><|921|><|615|><|5|><|code_end|> -#really<|t_0.36|><|code_start|><|55|><|420|><|1008|><|1659|><|27|><|644|><|1266|><|617|><|761|><|1712|><|109|><|1465|><|1587|><|503|><|1541|><|619|><|197|><|1019|><|817|><|269|><|377|><|362|><|1381|><|507|><|1488|><|4|><|1695|><|code_end|> -#enjoyable<|t_0.49|><|code_start|><|678|><|501|><|864|><|319|><|288|><|1472|><|1341|><|686|><|562|><|1463|><|619|><|1563|><|471|><|911|><|730|><|1811|><|1006|><|520|><|861|><|1274|><|125|><|1431|><|638|><|621|><|153|><|876|><|1770|><|437|><|987|><|1653|><|1109|><|898|><|1285|><|80|><|593|><|1709|><|843|><|code_end|> -#and<|t_0.15|><|code_start|><|1285|><|987|><|303|><|1037|><|730|><|1164|><|502|><|120|><|1737|><|1655|><|1318|><|code_end|> -#it<|t_0.09|><|code_start|><|848|><|1366|><|395|><|1601|><|1513|><|593|><|1302|><|code_end|> -#looks<|t_0.27|><|code_start|><|1281|><|1266|><|1755|><|572|><|248|><|1751|><|1257|><|695|><|1380|><|457|><|659|><|585|><|1315|><|1105|><|1776|><|736|><|24|><|736|><|654|><|1027|><|code_end|> -#lovely<|t_0.56|><|code_start|><|634|><|596|><|1766|><|1556|><|1306|><|1285|><|1481|><|1721|><|1123|><|438|><|1246|><|1251|><|795|><|659|><|1381|><|1658|><|217|><|1772|><|562|><|952|><|107|><|1129|><|1112|><|467|><|550|><|1079|><|840|><|1615|><|1469|><|1380|><|168|><|917|><|836|><|1827|><|437|><|583|><|67|><|595|><|1087|><|1646|><|1493|><|1677|><|code_end|>""" - -# TODO: tokenization is slow for some reason - here is pre-tokenized input -suffix = [ 151667, 198, 1782, 155780, 151669, 151929, 152412, 152308, 152585, 152460, 153375, 151670, 198, 74455, - 155808, 151669, 151799, 151873, 151863, 152446, 152372, 152204, 152728, 152229, 152470, 151970, 153413, - 152419, 153334, 153289, 153374, 153199, 152040, 153260, 152721, 152680, 153297, 152419, 153248, 152400, - 152691, 153368, 153437, 151670, 198, 1722, 155828, 151669, 152607, 152256, 152991, 152299, 152688, 153163, - 153016, 152789, 153198, 152712, 151911, 153107, 152623, 152170, 152395, 152852, 152207, 152461, 153321, - 153309, 151750, 152137, 153340, 152573, 152267, 153347, 151789, 152681, 153339, 151992, 152512, 151751, - 152179, 153434, 153180, 152900, 153440, 152474, 153122, 153129, 151904, 152311, 151670, 198, 1499, 155791, - 151669, 152276, 152454, 153354, 152544, 153204, 153272, 152708, 153433, 152319, 153226, 153043, 152325, - 153267, 152622, 151670, 198, 4250, 155797, 151669, 153454, 153342, 151989, 152458, 153420, 152303, 152271, - 152827, 153036, 153196, 151708, 153263, 152561, 153207, 152213, 152112, 153204, 151722, 152542, 151670, 198, - 19789, 155796, 151669, 153353, 153182, 152345, 152471, 152477, 153014, 152002, 152191, 151734, 152312, 152810, - 152237, 153224, 153169, 153224, 152244, 153387, 153404, 151670, 198, 16069, 155811, 151669, 152265, 151946, - 151808, 152412, 152363, 152305, 153156, 152733, 152810, 153157, 152016, 152100, 152069, 153234, 152317, - 152589, 152707, 153121, 153341, 152159, 152114, 153156, 153001, 153504, 153376, 152272, 152433, 152325, - 151941, 151670, 198, 285, 155788, 151669, 152238, 152255, 153427, 152318, 153009, 152381, 152474, 152680, - 152157, 153255, 152324, 151682, 151670, 198, 32955, 155804, 151669, 153490, 153419, 152364, 152405, 152682, - 152206, 152078, 153369, 152725, 153193, 153027, 152946, 152488, 153070, 151883, 152890, 152489, 153144, - 153375, 152358, 151685, 152494, 152117, 152740, 151670, 198, 37448, 480, 155840, 151669, 151902, 152720, - 153377, 152027, 152378, 152821, 153207, 153459, 153028, 153068, 152507, 153255, 152158, 152921, 151958, - 152609, 152748, 152822, 152286, 151714, 152730, 152377, 152353, 152470, 152606, 152162, 152186, 153071, - 152244, 153118, 153375, 153018, 152712, 153098, 152976, 152336, 151843, 153202, 152297, 151736, 153380, - 153502, 152702, 152115, 153181, 152735, 153277, 153457, 152393, 153112, 152595, 151670, 198, 19098, 155808, - 151669, 152464, 153452, 152595, 153312, 151937, 151933, 153197, 152239, 153163, 152922, 153402, 152034, - 152591, 153438, 152215, 151673, 152005, 151785, 152642, 151924, 153278, 151805, 151974, 153482, 152718, - 152862, 153347, 151670, 198, 72, 155780, 151669, 151795, 152111, 152746, 152377, 153471, 152309, 151670, 198, - 19016, 155788, 151669, 153181, 152271, 152190, 152842, 152224, 152701, 152939, 152536, 152091, 151815, 152733, - 151672, 151670, 198, 14689, 155788, 151669, 152291, 152072, 152942, 151734, 153042, 153504, 152589, 153333, - 151839, 151941, 153038, 153180, 151670, 198, 36996, 8303, 155832, 151669, 152231, 152256, 152835, 152801, - 152985, 153400, 152393, 152818, 152765, 152249, 152600, 151699, 152302, 152752, 153018, 153009, 151992, - 153054, 152847, 153354, 153228, 152662, 153355, 152532, 153393, 151782, 152458, 152048, 152757, 152428, - 153195, 151906, 153006, 153178, 153250, 152331, 152284, 152780, 153138, 153319, 151980, 153142, 152418, - 152228, 152733, 151670, 198, 9096, 155801, 151669, 151698, 153321, 152217, 153039, 152935, 153400, 152122, - 152531, 153106, 152169, 152892, 152957, 151851, 152427, 152826, 152451, 151851, 152901, 152885, 152594, - 153446, 153080, 151670, 198, 14689, 155795, 151669, 152658, 151700, 153321, 152450, 152530, 153191, 151673, - 151690, 151698, 152714, 152846, 152981, 153171, 153384, 153364, 153188, 153246, 151670, 198, 1055, 155779, - 151669, 151869, 152388, 152711, 153334, 151736, 151670, 198, 1782, 155780, 151669, 153483, 153240, 152241, - 152558, 152697, 153046, 151670, 198, 5804, 1363, 155820, 151669, 152941, 152764, 152605, 153034, 153434, - 153372, 153347, 151887, 152453, 152758, 152133, 152510, 152694, 152431, 152321, 153088, 152676, 152223, - 152581, 152459, 152015, 152502, 153063, 152712, 153294, 153451, 153032, 152903, 152859, 152989, 151748, - 152669, 152661, 152650, 152409, 151861, 151670, 198, 300, 7973, 155828, 151669, 153095, 152469, 152988, - 152894, 151819, 152391, 153019, 152058, 153062, 153230, 151826, 152112, 152306, 152264, 152769, 153390, - 152384, 152435, 152790, 153393, 152983, 152540, 152252, 152034, 153107, 152540, 151919, 151893, 152558, - 152817, 152946, 152956, 152129, 152715, 153131, 153490, 151734, 152271, 152707, 151734, 153321, 152450, - 151670, 198, 8088, 155792, 151669, 152452, 153497, 153353, 152679, 152533, 152382, 152374, 152611, 153341, - 153163, 152285, 153411, 152495, 153141, 152320, 151670, 198, 1199, 155781, 151669, 151764, 152360, 153295, - 152634, 153342, 152199, 152271, 151670, 198, 43366, 155799, 151669, 152308, 151682, 152889, 152016, 152385, - 152629, 152495, 151826, 153321, 152958, 152180, 151886, 153432, 152922, 152128, 153024, 153040, 152593, - 152287, 151677, 151670, 198, 53660, 155808, 151669, 151727, 152092, 152680, 153331, 151699, 152316, 152938, - 152289, 152433, 153384, 151781, 153137, 153259, 152175, 153213, 152291, 151869, 152691, 152489, 151941, - 152049, 152034, 153053, 152179, 153160, 151676, 153367, 151670, 198, 268, 4123, 480, 155821, 151669, 152350, - 152173, 152536, 151991, 151960, 153144, 153013, 152358, 152234, 153135, 152291, 153235, 152143, 152583, - 152402, 153483, 152678, 152192, 152533, 152946, 151797, 153103, 152310, 152293, 151825, 152548, 153442, - 152109, 152659, 153325, 152781, 152570, 152957, 151752, 152265, 153381, 152515, 151670, 198, 437, 155787, - 151669, 152957, 152659, 151975, 152709, 152402, 152836, 152174, 151792, 153409, 153327, 152990, 151670, 198, - 275, 155781, 151669, 152520, 153038, 152067, 153273, 153185, 152265, 152974, 151670, 198, 94273, 155799, - 151669, 152953, 152938, 153427, 152244, 151920, 153423, 152929, 152367, 153052, 152129, 152331, 152257, - 152987, 152777, 153448, 152408, 151696, 152408, 152326, 152699, 151670, 198, 385, 16239, 155828, 151669, - 152306, 152268, 153438, 153228, 152978, 152957, 153153, 153393, 152795, 152110, 152918, 152923, 152467, - 152331, 153053, 153330, 151889, 153444, 152234, 152624, 151779, 152801, 152784, 152139, 152222, 152751, - 152512, 153287, 153141, 153052, 151840, 152589, 152508, 153499, 152109, 152255, 151739, 152267, 152759, - 153318, 153165, 153349, 151670, ] - -response = requests.post( - host_llm + "/completion", - json={ - "prompt": [prefix + words, *suffix], - "n_predict": 1024, - "cache_prompt": True, - "return_tokens": True, - "samplers": ["top_k"], - "top_k": 16, - "seed": 1003, - } -) - -response_json = response.json() - -#print(json.dumps(response_json, indent=4)) -#print(json.dumps(response_json["prompt"], indent=4).replace("\\n", "\n")) -#print(json.dumps(response_json["timings"], indent=4)) -#print(json.dumps(response_json["tokens"], indent=4)) - -codes = response_json["tokens"] - -codes = [t - 151672 for t in codes if t >= 151672 and t <= 155772] - -response = requests.post( - host_dec + "/embeddings", - json={ - "input": [*codes], - } -) - -response_json = response.json() - -#print(json.dumps(response_json, indent=4)) - -# spectrogram -embd = response_json[0]["embedding"] - -n_codes = len(embd) -n_embd = len(embd[0]) - -print('spectrogram generated: n_codes: %d, n_embd: %d' % (n_codes, n_embd)) - -# post-process the spectrogram to convert to audio -print('converting to audio ...') -audio = embd_to_audio(embd, n_codes, n_embd) -print('audio generated: %d samples' % len(audio)) - -filename = "output.wav" -sample_rate = 24000 # sampling rate - -# zero out first 0.25 seconds -audio[:24000 // 4] = 0.0 - -save_wav(filename, audio, sample_rate) -print('audio written to file "%s"' % filename) diff --git a/tools/tts/tts.cpp b/tools/tts/tts.cpp index 2a1bdccc9192..b68edcaf5758 100644 --- a/tools/tts/tts.cpp +++ b/tools/tts/tts.cpp @@ -1,1096 +1,205 @@ -#define _USE_MATH_DEFINES // For M_PI on MSVC - #include "arg.h" #include "common.h" #include "sampling.h" #include "log.h" #include "llama.h" +#include "mtmd.h" +#include "mtmd-helper.h" -#define JSON_ASSERT GGML_ASSERT -#include - -#include -#include -#include #include -#include -#include -#include +#include #include -#include -#include - -using json = nlohmann::ordered_json; - -enum outetts_version { - OUTETTS_V0_2, - OUTETTS_V0_3, -}; - -// -// Terminal utils -// - -#define SQR(X) ((X) * (X)) -#define UNCUBE(x) x < 48 ? 0 : x < 115 ? 1 : (x - 35) / 40 /** - * Quantizes 24-bit RGB to xterm256 code range [16,256). + * Please note that this is NOT a production-ready binary. + * It is a playground for trying TTS support in llama.cpp. + * For contributors: please keep this code simple and easy to understand. Do not add unnecessary complexity. The goal is to have a simple CLI for testing TTS support. */ -static int rgb2xterm256(int r, int g, int b) { - unsigned char cube[] = {0, 0137, 0207, 0257, 0327, 0377}; - int av, ir, ig, ib, il, qr, qg, qb, ql; - av = r * .299 + g * .587 + b * .114 + .5; - ql = (il = av > 238 ? 23 : (av - 3) / 10) * 10 + 8; - qr = cube[(ir = UNCUBE(r))]; - qg = cube[(ig = UNCUBE(g))]; - qb = cube[(ib = UNCUBE(b))]; - if (SQR(qr - r) + SQR(qg - g) + SQR(qb - b) <= - SQR(ql - r) + SQR(ql - g) + SQR(ql - b)) - return ir * 36 + ig * 6 + ib + 020; - return il + 0350; -} - -static std::string set_xterm256_foreground(int r, int g, int b) { - int x = rgb2xterm256(r, g, b); - std::ostringstream oss; - oss << "\033[38;5;" << x << "m"; - return oss.str(); -} - -const std::vector k_colors = { - set_xterm256_foreground(220, 5, 12), - set_xterm256_foreground(232, 96, 28), - set_xterm256_foreground(241, 147, 45), - set_xterm256_foreground(246, 193, 65), - set_xterm256_foreground(247, 240, 86), - set_xterm256_foreground(144, 201, 135), - set_xterm256_foreground( 78, 178, 101), -}; - -static void print_usage(int, char ** argv) { - LOG("\nexample usage:\n"); - LOG("\n %s -m model.gguf -p \"Hello!\"\n", argv[0]); - LOG("\n"); -} - -struct wav_header { - char riff[4] = {'R', 'I', 'F', 'F'}; - uint32_t chunk_size; - char wave[4] = {'W', 'A', 'V', 'E'}; - char fmt[4] = {'f', 'm', 't', ' '}; - uint32_t fmt_chunk_size = 16; - uint16_t audio_format = 1; // PCM - uint16_t num_channels = 1; // Mono - uint32_t sample_rate; - uint32_t byte_rate; - uint16_t block_align; - uint16_t bits_per_sample = 16; - char data[4] = {'d', 'a', 't', 'a'}; - uint32_t data_size; -}; - -static bool save_wav16(const std::string & fname, const std::vector & data, int sample_rate) { - std::ofstream file(fname, std::ios::binary); - if (!file) { - LOG_ERR("%s: Failed to open file '%s' for writing.\n", __func__, fname.c_str()); - return false; - } - - wav_header header; - header.sample_rate = sample_rate; - header.byte_rate = header.sample_rate * header.num_channels * (header.bits_per_sample / 8); - header.block_align = header.num_channels * (header.bits_per_sample / 8); - header.data_size = data.size() * (header.bits_per_sample / 8); - header.chunk_size = 36 + header.data_size; - - file.write(reinterpret_cast(&header), sizeof(header)); - - for (const auto & sample : data) { - int16_t pcm_sample = static_cast(std::clamp(sample * 32767.0, -32768.0, 32767.0)); - file.write(reinterpret_cast(&pcm_sample), sizeof(pcm_sample)); - } - - return file.good(); -} -static void fill_hann_window(int length, bool periodic, float * output) { - int offset = -1; - if (periodic) { - offset = 0; - } - for (int i = 0; i < length; i++) { - output[i] = 0.5 * (1.0 - cosf((2.0 * M_PI * i) / (length + offset))); - } -} - -// very poor-man fft -static void twiddle(float * real, float * imag, int k, int N) { - float angle = 2 * M_PI * k / N; - *real = cos(angle); - *imag = sin(angle); -} - -static void irfft(int n, const float * inp_cplx, float * out_real) { - int N = n / 2 + 1; - - std::vector real_input(N); - std::vector imag_input(N); - for (int i = 0; i < N; ++i) { - real_input[i] = inp_cplx[2 * i]; - imag_input[i] = inp_cplx[2 * i + 1]; - } +struct tts_timings { + int64_t t_start_us = ggml_time_us(); + int64_t t_last_us = t_start_us; - std::vector real_output(n); - std::vector imag_output(n); - - for (int k = 0; k < n; ++k) { - real_output[k] = 0.0f; - imag_output[k] = 0.0f; - for (int m = 0; m < N; ++m) { - float twiddle_real; - float twiddle_imag; - - twiddle(&twiddle_real, &twiddle_imag, k * m, n); - - real_output[k] += real_input[m] * twiddle_real - imag_input[m] * twiddle_imag; - imag_output[k] += real_input[m] * twiddle_imag + imag_input[m] * twiddle_real; + void report(int n_frames) { + const int64_t t_now_us = ggml_time_us(); + if (t_now_us - t_last_us < 2000000) { + return; } + t_last_us = t_now_us; + const double t_elapsed_s = (t_now_us - t_start_us) / 1e6; + const double fps = t_elapsed_s > 0 ? n_frames / t_elapsed_s : 0.0; + LOG_INF("frames generated: %d, speed: %.2f frames/s\n", n_frames, fps); } - - for (int i = 0; i < n; ++i) { - out_real[i] = real_output[i] / N; - } -} - -// -// y = torch.nn.functional.fold( -// data, output_size=(1, output_size), kernel_size=(1, self.win_length), stride=(1, self.hop_length), -// )[:, 0, 0, pad:-pad] -// -// data.shape = torch.Size([1, 1280, 261]) -// output_size = 84480 -// win_length = 1280 -// hop_length = 320 -// pad = 480 -// -static void fold(const std::vector & data, int64_t n_out, int64_t n_win, int64_t n_hop, int64_t n_pad, std::vector & output) { - int64_t output_height = n_out; - int64_t kernel_w = n_win; - int64_t stride_w = n_hop; - int64_t width = n_out; - - output.resize(width, 0.0f); - - int64_t col_idx = 0; - for (int64_t w_col = 0; w_col < width; ++w_col) { - int64_t start = w_col * stride_w - n_pad; - int64_t end = start + kernel_w; - - for (int64_t w_im = start; w_im < end; ++w_im) { - if (w_im >= 0 && w_im < output_height && col_idx < (int64_t) data.size()) { - output[w_im] += data[col_idx]; - } - col_idx++; - } - } - - output.resize(n_out - 2 * n_pad); -} - -// TODO: not optimized at all -static std::vector embd_to_audio( - const float * embd, - const int n_codes, - const int n_embd, - const int n_thread) { - const int n_fft = 1280; - const int n_hop = 320; - const int n_win = 1280; - const int n_pad = (n_win - n_hop)/2; - const int n_out = (n_codes - 1)*n_hop + n_win; - - std::vector hann(n_fft); - - fill_hann_window(hann.size(), true, hann.data()); - - int n_spec = n_embd*n_codes; - - std::vector E (n_spec); - std::vector S (n_spec); - std::vector ST(n_spec); - - for (int l = 0; l < n_codes; ++l) { - for (int k = 0; k < n_embd; ++k) { - E[k*n_codes + l] = embd[l*n_embd + k]; - } - } - - for (int k = 0; k < n_embd/2; ++k) { - for (int l = 0; l < n_codes; ++l) { - float mag = E[(k )*n_codes + l]; - float phi = E[(k + n_embd/2)*n_codes + l]; - - mag = exp(mag); - - if (mag > 1e2) { - mag = 1e2; - } - S[2*(k*n_codes + l) + 0] = mag*cosf(phi); - S[2*(k*n_codes + l) + 1] = mag*sinf(phi); - } - } - - for (int l = 0; l < n_codes; ++l) { - for (int k = 0; k < n_embd/2; ++k) { - ST[l*n_embd + 2*k + 0] = S[2*(k*n_codes + l) + 0]; - ST[l*n_embd + 2*k + 1] = S[2*(k*n_codes + l) + 1]; - } - } - - std::vector res (n_codes*n_fft); - std::vector hann2(n_codes*n_fft); - - std::vector workers(n_thread); - for (int i = 0; i < n_thread; ++i) { - workers[i] = std::thread([&, i]() { - for (int l = i; l < n_codes; l += n_thread) { - irfft(n_fft, ST.data() + l*n_embd, res.data() + l*n_fft); - for (int j = 0; j < n_fft; ++j) { - res [l*n_fft + j] *= hann[j]; - hann2[l*n_fft + j] = hann[j] * hann[j]; - } - } - }); - } - for (int i = 0; i < n_thread; ++i) { - workers[i].join(); - } - - std::vector audio; - std::vector env; - - fold(res, n_out, n_win, n_hop, n_pad, audio); - fold(hann2, n_out, n_win, n_hop, n_pad, env); // TODO: can be done once - - for (size_t i = 0; i < audio.size(); ++i) { - audio[i] /= env[i]; - } - - return audio; -} - -static const std::map ones = { - {0, "zero"}, {1, "one"}, {2, "two"}, {3, "three"}, {4, "four"}, - {5, "five"}, {6, "six"}, {7, "seven"}, {8, "eight"}, {9, "nine"}, - {10, "ten"}, {11, "eleven"}, {12, "twelve"}, {13, "thirteen"}, {14, "fourteen"}, - {15, "fifteen"}, {16, "sixteen"}, {17, "seventeen"}, {18, "eighteen"}, {19, "nineteen"} }; -static const std::map tens = { - {2, "twenty"}, {3, "thirty"}, {4, "forty"}, {5, "fifty"}, - {6, "sixty"}, {7, "seventy"}, {8, "eighty"}, {9, "ninety"} -}; - -// Convert a number less than 1000 to words -static std::string convert_less_than_thousand(int num) { - std::string result; - - if (num >= 100) { - result += ones.at(num / 100) + " hundred "; - num %= 100; - } - - if (num >= 20) { - result += tens.at(num / 10); - if (num % 10 > 0) { - result += "-" + ones.at(num % 10); - } - } else if (num > 0) { - result += ones.at(num); - } - - return result; -} - -static std::string number_to_words(const std::string & number_str) { - try { - size_t decimal_pos = number_str.find('.'); - std::string integer_part = number_str.substr(0, decimal_pos); - - int int_number = std::stoi(integer_part); - std::string result; - - if (int_number == 0) { - result = "zero"; - } else { - if (int_number >= 1000000000) { - int billions = int_number / 1000000000; - result += convert_less_than_thousand(billions) + " billion "; - int_number %= 1000000000; - } - - if (int_number >= 1000000) { - int millions = int_number / 1000000; - result += convert_less_than_thousand(millions) + " million "; - int_number %= 1000000; - } - - if (int_number >= 1000) { - int thousands = int_number / 1000; - result += convert_less_than_thousand(thousands) + " thousand "; - int_number %= 1000; - } - - if (int_number > 0) { - result += convert_less_than_thousand(int_number); - } - } - - // Handle decimal part - if (decimal_pos != std::string::npos) { - result += " point"; - std::string decimal_part = number_str.substr(decimal_pos + 1); - for (char digit : decimal_part) { - result += " " + ones.at(digit - '0'); - } - } - - return result; - } catch (const std::exception& e) { - // Skip if fails - return " "; - } -} - -static std::string replace_numbers_with_words(const std::string & input_text) { - std::regex number_pattern(R"(\d+(\.\d+)?)"); - std::string result; - auto it = std::sregex_iterator(input_text.begin(), input_text.end(), number_pattern); - auto end = std::sregex_iterator(); - - size_t last_pos = 0; - for (std::sregex_iterator i = it; i != end; ++i) { - const std::smatch& match = *i; - result.append(input_text, last_pos, match.position() - last_pos); - result.append(number_to_words(match.str())); - last_pos = match.position() + match.length(); - } - result.append(input_text, last_pos); - - return result; -} - -// Based on: https://github.com/edwko/OuteTTS/blob/a613e79c489d8256dd657ea9168d78de75895d82/outetts/version/v1/prompt_processor.py#L39 -static std::string process_text(const std::string & text, const outetts_version tts_version = OUTETTS_V0_2) { - - // For now I skipped text romanization as I am unsure how to handle - // uroman and MeCab implementations in C++ - // maybe something like https://github.com/anyascii/anyascii/ could work. - // currently only English would be supported in this function - - std::string processed_text = replace_numbers_with_words(text); - - std::transform(processed_text.begin(), processed_text.end(), - processed_text.begin(), ::tolower); - - std::regex special_chars(R"([-_/,\.\\])"); - processed_text = std::regex_replace(processed_text, special_chars, " "); - - std::regex non_alpha(R"([^a-z\s])"); - processed_text = std::regex_replace(processed_text, non_alpha, ""); - - std::regex multiple_spaces(R"(\s+)"); - processed_text = std::regex_replace(processed_text, multiple_spaces, " "); - - processed_text = std::regex_replace(processed_text, std::regex(R"(^\s+|\s+$)"), ""); - - /* - Replace spaces with the separator token same as in line 365 - - for (auto & c : prompt_user) { - if (c == ' ') { - prompt_clean += "<|text_sep|>"; - */ - std::string separator = (tts_version == OUTETTS_V0_3) ? "<|space|>" : "<|text_sep|>"; - processed_text = std::regex_replace(processed_text, std::regex(R"(\s)"), separator); - - return processed_text; -} - -static void prompt_add(llama_tokens & prompt, llama_token token) { - prompt.push_back(token); -} - -static void prompt_add(llama_tokens & prompt, const llama_tokens & tokens) { - prompt.insert(prompt.end(), tokens.begin(), tokens.end()); -} - -static void prompt_add(llama_tokens & prompt, const llama_vocab * vocab, const std::string & txt, bool add_special, bool parse_special) { - auto tmp = common_tokenize(vocab, txt, add_special, parse_special); - prompt_add(prompt, tmp); -} - -static void prompt_init(llama_tokens & prompt, const llama_vocab * vocab) { - prompt.clear(); - - prompt_add(prompt, vocab, "<|im_start|>\n", true, true); -} - -static std::vector prepare_guide_tokens(const llama_vocab * vocab, const std::string & str, const outetts_version tts_version = OUTETTS_V0_2) { - const std::string& delimiter = (tts_version == OUTETTS_V0_3 ? "<|space|>" : "<|text_sep|>"); - - std::vector result; - size_t start = 0; - size_t end = str.find(delimiter); - - //first token is always a newline, as it was not previously added - result.push_back(common_tokenize(vocab, "\n", false, true)[0]); - - while (end != std::string::npos) { - std::string current_word = str.substr(start, end - start); - auto tmp = common_tokenize(vocab, current_word, false, true); - result.push_back(tmp[0]); - start = end + delimiter.length(); - end = str.find(delimiter, start); - } - - // Add the last part - std::string current_word = str.substr(start); - auto tmp = common_tokenize(vocab, current_word, false, true); - if (tmp.size() > 0) { - result.push_back(tmp[0]); - } - return result; -} - -static json speaker_from_file(const std::string & speaker_file) { - std::ifstream file(speaker_file); - if (!file) { - LOG_ERR("%s: Failed to open file '%s' for reading\n", __func__, speaker_file.c_str()); - return json(); - } - - json speaker = json::parse(file); - return speaker; -} - -static outetts_version get_tts_version(llama_model *model, json speaker = json::object()) { - if (speaker.contains("version")) { - std::string version = speaker["version"].get(); - if (version == "0.2") { - return OUTETTS_V0_2; - } else if (version == "0.3") { - return OUTETTS_V0_3; - } else { - LOG_ERR("%s: Unsupported speaker version '%s'\n", __func__, version.c_str()); - } - } - - // Also could get version from model itself - const char *chat_template = llama_model_chat_template(model, nullptr); - if (chat_template && std::string(chat_template) == "outetts-0.3") { - return OUTETTS_V0_3; - } - - // Use 0.2 as the default version - return OUTETTS_V0_2; -} - -static std::string audio_text_from_speaker(json speaker, const outetts_version tts_version = OUTETTS_V0_2) { - std::string audio_text = "<|text_start|>"; - - if (tts_version == OUTETTS_V0_2 || tts_version == OUTETTS_V0_3) { - std::string separator = (tts_version == OUTETTS_V0_3) ? "<|space|>" : "<|text_sep|>"; - for (const auto &word : speaker["words"]) { - audio_text += word["word"].get() + separator; - } - } - - return audio_text; -} - -static std::string audio_data_from_speaker(json speaker, const outetts_version tts_version = OUTETTS_V0_2) { - std::string audio_data = "<|audio_start|>\n"; - - if (tts_version == OUTETTS_V0_2 || tts_version == OUTETTS_V0_3) { - std::string code_start = (tts_version == OUTETTS_V0_3) ? "" : "<|code_start|>"; - std::string code_end = (tts_version == OUTETTS_V0_3) ? "<|space|>" : "<|code_end|>"; - for (const auto &word : speaker["words"]) { - std::string word_text = word["word"].get(); - double duration = word["duration"].get(); - std::vector codes = word["codes"].get>(); - - // Create the audio output entry - std::ostringstream word_entry; - word_entry << word_text << "<|t_" << std::fixed << std::setprecision(2) - << duration << "|>" + code_start; - for (const auto &Code : codes) { - word_entry << "<|" << Code << "|>"; - } - word_entry << code_end << "\n"; - audio_data += word_entry.str(); - } - } - - return audio_data; +static void print_usage(int, char ** argv) { + LOG("\nexample usage:\n"); + LOG("\n %s -m backbone.gguf -mm mmproj.gguf -p \"text to speak\" -o output.wav", argv[0]); + LOG("\n %s -hf user/model -p \"text to speak\" -o output.wav\n", argv[0]); + LOG("\nnote: --tts-lang and --tts-speaker-file may not be supported in all models"); + LOG("\n use -n to limit the output length"); + LOG("\n see tts/README.md for per-model usage notes"); + LOG("\n\n"); } int main(int argc, char ** argv) { - std::setlocale(LC_NUMERIC, "C"); - common_params params; - params.out_file = "output.wav"; - params.prompt = ""; - - params.n_predict = 4096; - params.n_batch = 8192; - params.n_ctx = 8192; - - params.sampling.top_k = 4; - params.sampling.samplers = { COMMON_SAMPLER_TYPE_TOP_K, }; - common_init(); if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_TTS, print_usage)) { return 1; } - const int n_parallel = params.n_parallel; - const int n_predict = params.n_predict; - - // init LLM - - llama_backend_init(); - llama_numa_init(params.numa); - - llama_model * model_ttc = NULL; // text-to-codes - llama_model * model_cts = NULL; // codes-to-speech - - llama_context * ctx_ttc = NULL; - llama_context * ctx_cts = NULL; - - auto llama_init_ttc = common_init_from_params(params); - - model_ttc = llama_init_ttc->model(); - ctx_ttc = llama_init_ttc->context(); + mtmd_helper_log_set(common_log_default_callback, nullptr); - if (model_ttc == nullptr || ctx_ttc == nullptr) { - return ENOENT; + if (params.prompt.empty()) { + LOG_ERR("no prompt provided, use -p \"text\"\n"); + return 1; + } + if (params.mmproj.path.empty()) { + LOG_ERR("no mmproj provided, use --mmproj\n"); + return 1; } - const llama_vocab * vocab = llama_model_get_vocab(model_ttc); + // important: keep this file as generic as possible + // model-specific logic should be in mtmd-helper-gen or mtmd API - params.model = params.vocoder.model; + // always enable embd, so that we can pass hidden states to the audio generation helper params.embedding = true; - params.n_ubatch = params.n_batch; - auto llama_init_cts = common_init_from_params(params); + llama_backend_init(); + llama_numa_init(params.numa); - model_cts = llama_init_cts->model(); - ctx_cts = llama_init_cts->context(); + // + // load backbone model and mmproj + // - if (model_cts == nullptr || ctx_cts == nullptr) { - return ENOENT; + auto llama_init = common_init_from_params(params); + llama_model * model = llama_init->model(); + llama_context * lctx = llama_init->context(); + common_sampler * smpl = llama_init->sampler(0); + if (!model || !lctx) { + LOG_ERR("failed to init model/context\n"); + return 1; } - std::vector smpl(n_parallel); - for (int i = 0; i < n_parallel; ++i) { - params.sampling.no_perf = (i != 0); - params.sampling.seed = params.sampling.seed + 1; - - smpl[i] = common_sampler_init(model_ttc, params.sampling); + mtmd_context_params mtmd_params = mtmd_context_params_default(); + mtmd_params.use_gpu = params.mmproj_use_gpu; + mtmd::context_ptr mctx(mtmd_init_from_file(params.mmproj.path.c_str(), model, mtmd_params)); + if (!mctx) { + LOG_ERR("failed to load mmproj %s\n", params.mmproj.path.c_str()); + return 1; } - - LOG_INF("sampler seed: %u\n", common_sampler_get_seed(smpl[0])); - LOG_INF("sampler chain: %s\n", common_sampler_print(smpl[0]).c_str()); - LOG_INF("sampler params: \n%s\n", params.sampling.print().c_str()); - - LOG_INF("%s: loading done\n", __func__); - - const auto t_main_start = ggml_time_us(); - - std::vector codes; - std::vector guide_tokens; - - // the default speaker profile is from: https://github.com/edwko/OuteTTS/blob/main/outetts/version/v1/default_speakers/en_male_1.json - std::string audio_text = "<|text_start|>the<|text_sep|>overall<|text_sep|>package<|text_sep|>from<|text_sep|>just<|text_sep|>two<|text_sep|>people<|text_sep|>is<|text_sep|>pretty<|text_sep|>remarkable<|text_sep|>sure<|text_sep|>i<|text_sep|>have<|text_sep|>some<|text_sep|>critiques<|text_sep|>about<|text_sep|>some<|text_sep|>of<|text_sep|>the<|text_sep|>gameplay<|text_sep|>aspects<|text_sep|>but<|text_sep|>its<|text_sep|>still<|text_sep|>really<|text_sep|>enjoyable<|text_sep|>and<|text_sep|>it<|text_sep|>looks<|text_sep|>lovely<|text_sep|>"; - std::string audio_data = R"(<|audio_start|> -the<|t_0.08|><|code_start|><|257|><|740|><|636|><|913|><|788|><|1703|><|code_end|> -overall<|t_0.36|><|code_start|><|127|><|201|><|191|><|774|><|700|><|532|><|1056|><|557|><|798|><|298|><|1741|><|747|><|1662|><|1617|><|1702|><|1527|><|368|><|1588|><|1049|><|1008|><|1625|><|747|><|1576|><|728|><|1019|><|1696|><|1765|><|code_end|> -package<|t_0.56|><|code_start|><|935|><|584|><|1319|><|627|><|1016|><|1491|><|1344|><|1117|><|1526|><|1040|><|239|><|1435|><|951|><|498|><|723|><|1180|><|535|><|789|><|1649|><|1637|><|78|><|465|><|1668|><|901|><|595|><|1675|><|117|><|1009|><|1667|><|320|><|840|><|79|><|507|><|1762|><|1508|><|1228|><|1768|><|802|><|1450|><|1457|><|232|><|639|><|code_end|> -from<|t_0.19|><|code_start|><|604|><|782|><|1682|><|872|><|1532|><|1600|><|1036|><|1761|><|647|><|1554|><|1371|><|653|><|1595|><|950|><|code_end|> -just<|t_0.25|><|code_start|><|1782|><|1670|><|317|><|786|><|1748|><|631|><|599|><|1155|><|1364|><|1524|><|36|><|1591|><|889|><|1535|><|541|><|440|><|1532|><|50|><|870|><|code_end|> -two<|t_0.24|><|code_start|><|1681|><|1510|><|673|><|799|><|805|><|1342|><|330|><|519|><|62|><|640|><|1138|><|565|><|1552|><|1497|><|1552|><|572|><|1715|><|1732|><|code_end|> -people<|t_0.39|><|code_start|><|593|><|274|><|136|><|740|><|691|><|633|><|1484|><|1061|><|1138|><|1485|><|344|><|428|><|397|><|1562|><|645|><|917|><|1035|><|1449|><|1669|><|487|><|442|><|1484|><|1329|><|1832|><|1704|><|600|><|761|><|653|><|269|><|code_end|> -is<|t_0.16|><|code_start|><|566|><|583|><|1755|><|646|><|1337|><|709|><|802|><|1008|><|485|><|1583|><|652|><|10|><|code_end|> -pretty<|t_0.32|><|code_start|><|1818|><|1747|><|692|><|733|><|1010|><|534|><|406|><|1697|><|1053|><|1521|><|1355|><|1274|><|816|><|1398|><|211|><|1218|><|817|><|1472|><|1703|><|686|><|13|><|822|><|445|><|1068|><|code_end|> -remarkable<|t_0.68|><|code_start|><|230|><|1048|><|1705|><|355|><|706|><|1149|><|1535|><|1787|><|1356|><|1396|><|835|><|1583|><|486|><|1249|><|286|><|937|><|1076|><|1150|><|614|><|42|><|1058|><|705|><|681|><|798|><|934|><|490|><|514|><|1399|><|572|><|1446|><|1703|><|1346|><|1040|><|1426|><|1304|><|664|><|171|><|1530|><|625|><|64|><|1708|><|1830|><|1030|><|443|><|1509|><|1063|><|1605|><|1785|><|721|><|1440|><|923|><|code_end|> -sure<|t_0.36|><|code_start|><|792|><|1780|><|923|><|1640|><|265|><|261|><|1525|><|567|><|1491|><|1250|><|1730|><|362|><|919|><|1766|><|543|><|1|><|333|><|113|><|970|><|252|><|1606|><|133|><|302|><|1810|><|1046|><|1190|><|1675|><|code_end|> -i<|t_0.08|><|code_start|><|123|><|439|><|1074|><|705|><|1799|><|637|><|code_end|> -have<|t_0.16|><|code_start|><|1509|><|599|><|518|><|1170|><|552|><|1029|><|1267|><|864|><|419|><|143|><|1061|><|0|><|code_end|> -some<|t_0.16|><|code_start|><|619|><|400|><|1270|><|62|><|1370|><|1832|><|917|><|1661|><|167|><|269|><|1366|><|1508|><|code_end|> -critiques<|t_0.60|><|code_start|><|559|><|584|><|1163|><|1129|><|1313|><|1728|><|721|><|1146|><|1093|><|577|><|928|><|27|><|630|><|1080|><|1346|><|1337|><|320|><|1382|><|1175|><|1682|><|1556|><|990|><|1683|><|860|><|1721|><|110|><|786|><|376|><|1085|><|756|><|1523|><|234|><|1334|><|1506|><|1578|><|659|><|612|><|1108|><|1466|><|1647|><|308|><|1470|><|746|><|556|><|1061|><|code_end|> -about<|t_0.29|><|code_start|><|26|><|1649|><|545|><|1367|><|1263|><|1728|><|450|><|859|><|1434|><|497|><|1220|><|1285|><|179|><|755|><|1154|><|779|><|179|><|1229|><|1213|><|922|><|1774|><|1408|><|code_end|> -some<|t_0.23|><|code_start|><|986|><|28|><|1649|><|778|><|858|><|1519|><|1|><|18|><|26|><|1042|><|1174|><|1309|><|1499|><|1712|><|1692|><|1516|><|1574|><|code_end|> -of<|t_0.07|><|code_start|><|197|><|716|><|1039|><|1662|><|64|><|code_end|> -the<|t_0.08|><|code_start|><|1811|><|1568|><|569|><|886|><|1025|><|1374|><|code_end|> -gameplay<|t_0.48|><|code_start|><|1269|><|1092|><|933|><|1362|><|1762|><|1700|><|1675|><|215|><|781|><|1086|><|461|><|838|><|1022|><|759|><|649|><|1416|><|1004|><|551|><|909|><|787|><|343|><|830|><|1391|><|1040|><|1622|><|1779|><|1360|><|1231|><|1187|><|1317|><|76|><|997|><|989|><|978|><|737|><|189|><|code_end|> -aspects<|t_0.56|><|code_start|><|1423|><|797|><|1316|><|1222|><|147|><|719|><|1347|><|386|><|1390|><|1558|><|154|><|440|><|634|><|592|><|1097|><|1718|><|712|><|763|><|1118|><|1721|><|1311|><|868|><|580|><|362|><|1435|><|868|><|247|><|221|><|886|><|1145|><|1274|><|1284|><|457|><|1043|><|1459|><|1818|><|62|><|599|><|1035|><|62|><|1649|><|778|><|code_end|> -but<|t_0.20|><|code_start|><|780|><|1825|><|1681|><|1007|><|861|><|710|><|702|><|939|><|1669|><|1491|><|613|><|1739|><|823|><|1469|><|648|><|code_end|> -its<|t_0.09|><|code_start|><|92|><|688|><|1623|><|962|><|1670|><|527|><|599|><|code_end|> -still<|t_0.27|><|code_start|><|636|><|10|><|1217|><|344|><|713|><|957|><|823|><|154|><|1649|><|1286|><|508|><|214|><|1760|><|1250|><|456|><|1352|><|1368|><|921|><|615|><|5|><|code_end|> -really<|t_0.36|><|code_start|><|55|><|420|><|1008|><|1659|><|27|><|644|><|1266|><|617|><|761|><|1712|><|109|><|1465|><|1587|><|503|><|1541|><|619|><|197|><|1019|><|817|><|269|><|377|><|362|><|1381|><|507|><|1488|><|4|><|1695|><|code_end|> -enjoyable<|t_0.49|><|code_start|><|678|><|501|><|864|><|319|><|288|><|1472|><|1341|><|686|><|562|><|1463|><|619|><|1563|><|471|><|911|><|730|><|1811|><|1006|><|520|><|861|><|1274|><|125|><|1431|><|638|><|621|><|153|><|876|><|1770|><|437|><|987|><|1653|><|1109|><|898|><|1285|><|80|><|593|><|1709|><|843|><|code_end|> -and<|t_0.15|><|code_start|><|1285|><|987|><|303|><|1037|><|730|><|1164|><|502|><|120|><|1737|><|1655|><|1318|><|code_end|> -it<|t_0.09|><|code_start|><|848|><|1366|><|395|><|1601|><|1513|><|593|><|1302|><|code_end|> -looks<|t_0.27|><|code_start|><|1281|><|1266|><|1755|><|572|><|248|><|1751|><|1257|><|695|><|1380|><|457|><|659|><|585|><|1315|><|1105|><|1776|><|736|><|24|><|736|><|654|><|1027|><|code_end|> -lovely<|t_0.56|><|code_start|><|634|><|596|><|1766|><|1556|><|1306|><|1285|><|1481|><|1721|><|1123|><|438|><|1246|><|1251|><|795|><|659|><|1381|><|1658|><|217|><|1772|><|562|><|952|><|107|><|1129|><|1112|><|467|><|550|><|1079|><|840|><|1615|><|1469|><|1380|><|168|><|917|><|836|><|1827|><|437|><|583|><|67|><|595|><|1087|><|1646|><|1493|><|1677|><|code_end|>)"; - - // audio data for 0.3 version - outetts_version tts_version = get_tts_version(model_ttc); - if (tts_version == OUTETTS_V0_3) { - audio_text = std::regex_replace(audio_text, std::regex(R"(<\|text_sep\|>)"), "<|space|>"); - audio_data = std::regex_replace(audio_data, std::regex(R"(<\|code_start\|>)"), ""); - audio_data = std::regex_replace(audio_data, std::regex(R"(<\|code_end\|>)"), "<|space|>"); + if (mtmd_gen_audio_get_info(mctx.get()).type == MTMD_GEN_AUDIO_TYPE_NONE) { + LOG_ERR("mmproj does not support audio generation\n"); + return 1; } - // load speaker if given - if (!params.vocoder.speaker_file.empty()) { - LOG_INF("%s: loading speaker ..\n", __func__); - json speaker = speaker_from_file(params.vocoder.speaker_file); - if (speaker.empty()) { - LOG_ERR("%s: Failed to load speaker file '%s'\n", __func__, params.vocoder.speaker_file.c_str()); + // + // stage 0: process speaker reference file, if any + // + + mtmd::bitmap_ptr speaker_bitmap; + if (!params.tts_speaker_file.empty()) { + auto wrapper = mtmd_helper_bitmap_init_from_file(mctx.get(), params.tts_speaker_file.c_str(), false); + if (!wrapper.bitmap) { + LOG_ERR("failed to load speaker file %s\n", params.tts_speaker_file.c_str()); return 1; } - audio_text = audio_text_from_speaker(speaker, tts_version); - audio_data = audio_data_from_speaker(speaker, tts_version); + speaker_bitmap.reset(wrapper.bitmap); } - // process prompt and generate voice codes - { - LOG_INF("%s: constructing prompt ..\n", __func__); - - std::vector prompt_inp; - - prompt_init(prompt_inp, vocab); - - prompt_add(prompt_inp, vocab, audio_text, false, true); - - // convert the input text into the necessary format expected by OuteTTS - { - std::string prompt_clean = process_text(params.prompt, tts_version); - if (params.vocoder.use_guide_tokens) { - guide_tokens = prepare_guide_tokens(vocab, prompt_clean, tts_version); - } - - LOG_INF("%s: prompt: '%s'\n", __func__, prompt_clean.c_str()); - - prompt_add(prompt_inp, vocab, prompt_clean, false, true); - } - - prompt_add(prompt_inp, vocab, "<|text_end|>\n", false, true); - - if (!params.vocoder.speaker_file.empty()) { - prompt_add(prompt_inp, vocab, audio_data, false, true); - } else { - // disabled to save time on tokenizing each time -#if 1 - const std::string voice_data = audio_data; - - auto tmp = common_tokenize(vocab, voice_data, false, true); - - std::ostringstream tokens_oss; - for (size_t i = 0; i < tmp.size(); ++i) { - tokens_oss << tmp[i] << ", "; - } - LOG_INF("\n\n%s: llama tokens: %s\n\n", __func__, tokens_oss.str().c_str()); - - prompt_add(prompt_inp, tmp); -#else - prompt_add(prompt_inp, llama_tokens { - 151667, 198, 1782, 155780, 151669, 151929, 152412, 152308, 152585, - 152460, 153375, 151670, 198, 74455, 155808, 151669, 151799, - 151873, 151863, 152446, 152372, 152204, 152728, 152229, 152470, - 151970, 153413, 152419, 153334, 153289, 153374, 153199, 152040, - 153260, 152721, 152680, 153297, 152419, 153248, 152400, 152691, - 153368, 153437, 151670, 198, 1722, 155828, 151669, 152607, - 152256, 152991, 152299, 152688, 153163, 153016, 152789, 153198, - 152712, 151911, 153107, 152623, 152170, 152395, 152852, 152207, - 152461, 153321, 153309, 151750, 152137, 153340, 152573, 152267, - 153347, 151789, 152681, 153339, 151992, 152512, 151751, 152179, - 153434, 153180, 152900, 153440, 152474, 153122, 153129, 151904, - 152311, 151670, 198, 1499, 155791, 151669, 152276, 152454, - 153354, 152544, 153204, 153272, 152708, 153433, 152319, 153226, - 153043, 152325, 153267, 152622, 151670, 198, 4250, 155797, - 151669, 153454, 153342, 151989, 152458, 153420, 152303, 152271, - 152827, 153036, 153196, 151708, 153263, 152561, 153207, 152213, - 152112, 153204, 151722, 152542, 151670, 198, 19789, 155796, - 151669, 153353, 153182, 152345, 152471, 152477, 153014, 152002, - 152191, 151734, 152312, 152810, 152237, 153224, 153169, 153224, - 152244, 153387, 153404, 151670, 198, 16069, 155811, 151669, - 152265, 151946, 151808, 152412, 152363, 152305, 153156, 152733, - 152810, 153157, 152016, 152100, 152069, 153234, 152317, 152589, - 152707, 153121, 153341, 152159, 152114, 153156, 153001, 153504, - 153376, 152272, 152433, 152325, 151941, 151670, 198, 285, - 155788, 151669, 152238, 152255, 153427, 152318, 153009, 152381, - 152474, 152680, 152157, 153255, 152324, 151682, 151670, 198, - 32955, 155804, 151669, 153490, 153419, 152364, 152405, 152682, - 152206, 152078, 153369, 152725, 153193, 153027, 152946, 152488, - 153070, 151883, 152890, 152489, 153144, 153375, 152358, 151685, - 152494, 152117, 152740, 151670, 198, 37448, 480, 155840, 151669, - 151902, 152720, 153377, 152027, 152378, 152821, 153207, 153459, - 153028, 153068, 152507, 153255, 152158, 152921, 151958, 152609, - 152748, 152822, 152286, 151714, 152730, 152377, 152353, 152470, - 152606, 152162, 152186, 153071, 152244, 153118, 153375, 153018, - 152712, 153098, 152976, 152336, 151843, 153202, 152297, 151736, - 153380, 153502, 152702, 152115, 153181, 152735, 153277, 153457, - 152393, 153112, 152595, 151670, 198, 19098, 155808, 151669, - 152464, 153452, 152595, 153312, 151937, 151933, 153197, 152239, - 153163, 152922, 153402, 152034, 152591, 153438, 152215, 151673, - 152005, 151785, 152642, 151924, 153278, 151805, 151974, 153482, - 152718, 152862, 153347, 151670, 198, 72, 155780, 151669, 151795, - 152111, 152746, 152377, 153471, 152309, 151670, 198, 19016, - 155788, 151669, 153181, 152271, 152190, 152842, 152224, 152701, - 152939, 152536, 152091, 151815, 152733, 151672, 151670, 198, - 14689, 155788, 151669, 152291, 152072, 152942, 151734, 153042, - 153504, 152589, 153333, 151839, 151941, 153038, 153180, 151670, - 198, 36996, 8303, 155832, 151669, 152231, 152256, 152835, - 152801, 152985, 153400, 152393, 152818, 152765, 152249, 152600, - 151699, 152302, 152752, 153018, 153009, 151992, 153054, 152847, - 153354, 153228, 152662, 153355, 152532, 153393, 151782, 152458, - 152048, 152757, 152428, 153195, 151906, 153006, 153178, 153250, - 152331, 152284, 152780, 153138, 153319, 151980, 153142, 152418, - 152228, 152733, 151670, 198, 9096, 155801, 151669, 151698, - 153321, 152217, 153039, 152935, 153400, 152122, 152531, 153106, - 152169, 152892, 152957, 151851, 152427, 152826, 152451, 151851, - 152901, 152885, 152594, 153446, 153080, 151670, 198, 14689, - 155795, 151669, 152658, 151700, 153321, 152450, 152530, 153191, - 151673, 151690, 151698, 152714, 152846, 152981, 153171, 153384, - 153364, 153188, 153246, 151670, 198, 1055, 155779, 151669, - 151869, 152388, 152711, 153334, 151736, 151670, 198, 1782, - 155780, 151669, 153483, 153240, 152241, 152558, 152697, 153046, - 151670, 198, 5804, 1363, 155820, 151669, 152941, 152764, 152605, - 153034, 153434, 153372, 153347, 151887, 152453, 152758, 152133, - 152510, 152694, 152431, 152321, 153088, 152676, 152223, 152581, - 152459, 152015, 152502, 153063, 152712, 153294, 153451, 153032, - 152903, 152859, 152989, 151748, 152669, 152661, 152650, 152409, - 151861, 151670, 198, 300, 7973, 155828, 151669, 153095, 152469, - 152988, 152894, 151819, 152391, 153019, 152058, 153062, 153230, - 151826, 152112, 152306, 152264, 152769, 153390, 152384, 152435, - 152790, 153393, 152983, 152540, 152252, 152034, 153107, 152540, - 151919, 151893, 152558, 152817, 152946, 152956, 152129, 152715, - 153131, 153490, 151734, 152271, 152707, 151734, 153321, 152450, - 151670, 198, 8088, 155792, 151669, 152452, 153497, 153353, - 152679, 152533, 152382, 152374, 152611, 153341, 153163, 152285, - 153411, 152495, 153141, 152320, 151670, 198, 1199, 155781, - 151669, 151764, 152360, 153295, 152634, 153342, 152199, 152271, - 151670, 198, 43366, 155799, 151669, 152308, 151682, 152889, - 152016, 152385, 152629, 152495, 151826, 153321, 152958, 152180, - 151886, 153432, 152922, 152128, 153024, 153040, 152593, 152287, - 151677, 151670, 198, 53660, 155808, 151669, 151727, 152092, - 152680, 153331, 151699, 152316, 152938, 152289, 152433, 153384, - 151781, 153137, 153259, 152175, 153213, 152291, 151869, 152691, - 152489, 151941, 152049, 152034, 153053, 152179, 153160, 151676, - 153367, 151670, 198, 268, 4123, 480, 155821, 151669, 152350, - 152173, 152536, 151991, 151960, 153144, 153013, 152358, 152234, - 153135, 152291, 153235, 152143, 152583, 152402, 153483, 152678, - 152192, 152533, 152946, 151797, 153103, 152310, 152293, 151825, - 152548, 153442, 152109, 152659, 153325, 152781, 152570, 152957, - 151752, 152265, 153381, 152515, 151670, 198, 437, 155787, - 151669, 152957, 152659, 151975, 152709, 152402, 152836, 152174, - 151792, 153409, 153327, 152990, 151670, 198, 275, 155781, - 151669, 152520, 153038, 152067, 153273, 153185, 152265, 152974, - 151670, 198, 94273, 155799, 151669, 152953, 152938, 153427, - 152244, 151920, 153423, 152929, 152367, 153052, 152129, 152331, - 152257, 152987, 152777, 153448, 152408, 151696, 152408, 152326, - 152699, 151670, 198, 385, 16239, 155828, 151669, 152306, 152268, - 153438, 153228, 152978, 152957, 153153, 153393, 152795, 152110, - 152918, 152923, 152467, 152331, 153053, 153330, 151889, 153444, - 152234, 152624, 151779, 152801, 152784, 152139, 152222, 152751, - 152512, 153287, 153141, 153052, 151840, 152589, 152508, 153499, - 152109, 152255, 151739, 152267, 152759, 153318, 153165, 153349, - 151670,}); -#endif - } - - // print the prompt token-by-token - - LOG("\n"); - - for (auto id : prompt_inp) { - LOG("%s", common_token_to_piece(ctx_ttc, id).c_str()); - } + mtmd_helper::gen_audio gen(lctx, mctx.get()); + mtmd_helper_gen_audio_inp inp{}; + inp.seq_id = 0; + inp.prompt = params.prompt.c_str(); + inp.prompt_len = params.prompt.size(); + inp.speaker_ref = speaker_bitmap.get(); + inp.lang = params.tts_lang.c_str(); + inp.top_k = params.sampling.top_k; + inp.top_p = params.sampling.top_p; + inp.out_type = MTMD_HELPER_GEN_AUDIO_OUTTYPE_WAV; - LOG_INF("%s: prompt size: %d\n", __func__, (int) prompt_inp.size()); + // + // stage 1: process prompt via backbone model, generate semantic representation + // - LOG("\n"); - - // create a llama_batch - // we use this object to submit token data for decoding - llama_batch batch = llama_batch_init(std::max(prompt_inp.size(), (size_t) n_parallel), 0, n_parallel); - - std::vector seq_ids(n_parallel, 0); - for (int32_t i = 0; i < n_parallel; ++i) { - seq_ids[i] = i; - } - - // evaluate the initial prompt - for (size_t i = 0; i < prompt_inp.size(); ++i) { - common_batch_add(batch, prompt_inp[i], i, seq_ids, false); - } - GGML_ASSERT(batch.n_tokens == (int) prompt_inp.size()); + if (gen.set_input(&inp) != 0) { + LOG_ERR("set_input failed\n"); + return 1; + } - // llama_decode will output logits only for the last token of the prompt - batch.logits[batch.n_tokens - 1] = true; + const int64_t t_prompt_start_us = ggml_time_us(); - if (llama_decode(ctx_ttc, batch) != 0) { - LOG_ERR("%s: llama_decode() failed\n", __func__); + for (;;) { + int32_t ret = gen.step_prompt(params.n_batch); + if (ret < 0) { + LOG_ERR("prompt processing failed\n"); return 1; } - - if (n_parallel > 1) { - LOG_INF("\n\n%s: generating %d sequences ...\n", __func__, n_parallel); - } - - llama_synchronize(ctx_ttc); - - LOG_INF("%s: time for prompt: %.3f ms\n\n", __func__, (ggml_time_us() - t_main_start) / 1000.0f); - - const auto t_dec_start = ggml_time_us(); - - // main loop - - // remember the batch index of the last token for each parallel sequence - // we need this to determine which logits to sample from - std::vector i_batch(n_parallel, batch.n_tokens - 1); - - int n_past = batch.n_tokens; - int n_decode = 0; - - bool next_token_uses_guide_token = true; - - while (n_decode <= n_predict) { - // prepare the next batch - common_batch_clear(batch); - - // sample the next token for each parallel sequence / stream - for (int32_t i = 0; i < n_parallel; ++i) { - if (i_batch[i] < 0) { - // the stream has already finished - continue; - } - - llama_token new_token_id = common_sampler_sample(smpl[i], ctx_ttc, i_batch[i]); - - //guide tokens help prevent hallucinations by forcing the TTS to use the correct word - if (!guide_tokens.empty() && next_token_uses_guide_token && !llama_vocab_is_control(vocab, new_token_id) && !llama_vocab_is_eog(vocab, new_token_id)) { - llama_token guide_token = guide_tokens[0]; - guide_tokens.erase(guide_tokens.begin()); - new_token_id = guide_token; //ensure correct word fragment is used - } - - //this is the token id that always precedes a new word - next_token_uses_guide_token = (new_token_id == 198); - - common_sampler_accept(smpl[i], new_token_id, true); - - codes.push_back(new_token_id); - - const auto * cands = common_sampler_get_candidates(smpl[i], false); - - // is it an end of generation? -> mark the stream as finished - if (llama_vocab_is_eog(vocab, new_token_id) || n_decode == n_predict) { - std::string reason; - if (llama_vocab_is_eog(vocab, new_token_id)) { - reason = "eos"; - } else { - reason = "n_predict"; - } - - i_batch[i] = -1; - - LOG("\n"); - if (n_parallel > 1) { - LOG_CNT("\n"); - LOG_INF("%s: stream %d finished at n_past = %d, reason = '%s'\n", __func__, i, n_past, reason.c_str()); - } - - continue; - } - - { - const float p = cands->data[cands->selected].p; - - const int col = std::max(0, std::min((int) k_colors.size() - 1, (int) ((3*p)*float(k_colors.size())))); - - LOG_CNT("%s%d%s", k_colors[col].c_str(), i, "\033[0m"); - //LOG_CNT("%d", i); - } - - i_batch[i] = batch.n_tokens; - - // push this new token for next evaluation - common_batch_add(batch, new_token_id, n_past, { i }, true); - } - - // all streams are finished - if (batch.n_tokens == 0) { - break; - } - - n_decode += 1; - n_past += 1; - - // evaluate the current batch with the transformer model - if (llama_decode(ctx_ttc, batch)) { - LOG_ERR("%s : failed to eval, return code %d\n", __func__, 1); - return 1; - } + if (ret == 0) { + break; } - - llama_batch_free(batch); - - LOG("\n"); - LOG_INF("%s: time for decoder: %.3f ms\n", __func__, (ggml_time_us() - t_dec_start) / 1000.0f); } - common_perf_print(ctx_ttc, smpl[0]); + const llama_vocab * vocab = llama_model_get_vocab(model); - //std::vector codes = {198, 88225, 155856, 151669, 152205, - // 153064, 152537, 153421, 153209, 152524, 151689, 152993, 152438, 152695, - // 153091, 152945, 152829, 152534, 152934, 153020, 151997, 152263, 153010, - // 153146, 152399, 153208, 152496, 151793, 152848, 152263, 152571, 153286, - // 152227, 153300, 152934, 152263, 153208, 152263, 152965, 152430, 152296, - // 153146, 152920, 152376, 152556, 153363, 151775, 152044, 152972, 152690, - // 153379, 152368, 152233, 153422, 152490, 151996, 152022, 151694, 152061, - // 153238, 152539, 153356, 152640, 153021, 153123, 151962, 153094, 151670, - // 198, 20339, 13189, 155824, 151669, 152070, 152007, 152910, 151683, - // 152000, 152373, 152760, 152046, 151735, 152334, 152394, 153073, 152908, - // 151856, 151953, 153247, 153293, 151903, 153480, 153168, 152478, 153359, - // 153429, 151905, 151678, 152567, 152411, 152165, 152556, 153075, 153424, - // 151993, 152999, 153078, 152151, 152088, 153389, 152484, 151874, 151670, - // 198, 285, 155784, 151669, 152226, 152126, 152638, 153215, 151729, - // 152959, 153479, 153059, 151838, 151670, 198, 1782, 155783, 151669, - // 153288, 153055, 153314, 152497, 152962, 152741, 152076, 153253, 151670, - // 198, 471, 16488, 155825, 151669, 152060, 152916, 151893, 153469, 152501, - // 152080, 152743, 151932, 153161, 152096, 152761, 152698, 153401, 153242, - // 153336, 152441, 152838, 153467, 152706, 153496, 153310, 152422, 153360, - // 153115, 152763, 151998, 152373, 153450, 152554, 151968, 153323, 152055, - // 152468, 153111, 153358, 152813, 152010, 151770, 152823, 152960, 151670, - // 198, 22627, 155823, 151669, 152814, 152366, 153484, 152931, 153441, - // 152164, 152877, 152915, 153463, 151692, 152911, 152747, 152776, 151831, - // 153449, 151882, 152975, 152031, 152513, 153150, 152448, 152667, 153133, - // 153189, 152619, 153466, 152054, 152106, 153119, 152277, 152439, 153109, - // 152997, 152141, 153154, 153256, 153311, 151922, 151670, 198, 1055, - // 155781, 151669, 152633, 151850, 153060, 153270, 152560, 153348, 152729, - // 151670, 198, 25312, 155803, 151669, 152521, 153403, 152561, 153337, - // 153383, 152199, 153493, 153326, 151830, 152254, 152248, 152349, 152153, - // 153007, 151823, 153037, 152575, 152457, 152406, 152592, 153116, 153365, - // 153456, 151670, 198, 88225, 155817, 151669, 153271, 151925, 152218, - // 152418, 152253, 153140, 151903, 153151, 152626, 152338, 152647, 153464, - // 152785, 152768, 151711, 152037, 152033, 151804, 152216, 151701, 151855, - // 152348, 152995, 152955, 152905, 152342, 152340, 153391, 153453, 152418, - // 153415, 151990, 153083, 152884, 151670, 198, 151668, 198, 151645}; + auto sample_semantic_code = [&]() -> llama_token { + llama_token t = common_sampler_sample(smpl, lctx, -1); + common_sampler_accept(smpl, t, true); + return t; + }; - { - const std::string inp_txt = common_detokenize(ctx_ttc, codes, true); + const int max_new = params.n_predict > 0 ? params.n_predict : 512; + int n_frames = 0; + llama_token sampled = sample_semantic_code(); + const float * h_state = llama_get_embeddings_ith(lctx, -1); - LOG("\n"); - LOG_INF("codes: '%s'\n", inp_txt.c_str()); - LOG_INF("%s: codes size: %d\n", __func__, (int) codes.size()); - } - - // remove all non-audio tokens (i.e. < 151672 || > 155772) - codes.erase(std::remove_if(codes.begin(), codes.end(), [](llama_token t) { return t < 151672 || t > 155772; }), codes.end()); + tts_timings timings; + const int64_t t_gen_start_us = ggml_time_us(); - { - const std::string inp_txt = common_detokenize(ctx_ttc, codes, true); - LOG_INF("codes audio: '%s'\n", inp_txt.c_str()); - LOG_INF("%s: codes audio size: %d\n", __func__, (int) codes.size()); - } + for (; n_frames < max_new && !llama_vocab_is_eog(vocab, sampled); n_frames++) { + const float * h_next = nullptr; - for (auto & token : codes) { - token -= 151672; - } - - const auto t_voc_start = ggml_time_us(); - - const int n_codes = codes.size(); - - llama_batch batch = llama_batch_init(n_codes, 0, 1); - - for (size_t i = 0; i < codes.size(); ++i) { - common_batch_add(batch, codes[i], i, { 0 }, true); // TODO: all logits? - } - GGML_ASSERT(batch.n_tokens == n_codes); - - if (llama_encode(ctx_cts, batch) != 0) { - LOG_ERR("%s: llama_encode() failed\n", __func__); - return 1; - } - - llama_synchronize(ctx_cts); - - LOG_INF("%s: time for vocoder: %.3f ms\n", __func__, (ggml_time_us() - t_voc_start) / 1000.0f); - - const auto t_spec_start = ggml_time_us(); - -#if 1 - // spectral operations - const int n_embd = llama_model_n_embd_out(model_cts); - const float * embd = llama_get_embeddings(ctx_cts); - - auto audio = embd_to_audio(embd, n_codes, n_embd, params.cpuparams.n_threads); - -#else - // read the spectrogram from a file for debugging purposes - std::vector audio; - { - std::ifstream fin("out.bin", std::ios::binary); - if (!fin) { - LOG_ERR("%s: failed to open file '%s'\n", __func__, "out.bin"); + // stage 2+3: semantic --> acoustic details --> audio waveform + // step_gen() runs both stages and returns new h_state for next step + if (gen.step_gen(sampled, h_state, &h_next) != 0) { + LOG_ERR("step_gen failed at frame %d\n", n_frames); return 1; } - std::vector embd; - - int n_codes; - int n_embd; - - fin.read(reinterpret_cast(&n_codes), sizeof(int)); - fin.read(reinterpret_cast(&n_embd), sizeof(int)); - - embd.resize(n_codes * n_embd); - fin.read(reinterpret_cast(embd.data()), n_codes * n_embd * sizeof(float)); - fin.close(); - - LOG_INF("%s: n_codes: %d, n_embd: %d\n", __func__, n_codes, n_embd); - - audio = embd_to_audio(embd.data(), n_codes, n_embd, params.cpuparams.n_threads); + h_state = h_next; + sampled = sample_semantic_code(); + timings.report(n_frames + 1); } -#endif - - const int n_sr = 24000; // sampling rate + const double t_gen_s = (ggml_time_us() - t_gen_start_us) / 1e6; - // zero out first 0.25 seconds - for (int i = 0; i < 24000/4; ++i) { - audio[i] = 0.0f; + int32_t sample_rate = 0; + const char * data = nullptr; + size_t data_len = 0; + int64_t n_samples = 0; + if (gen.get_output(&sample_rate, &data, &data_len, &n_samples) != 0) { + LOG_ERR("get_output failed\n"); + return 1; } - LOG_INF("%s: time for spectral ops: %.3f ms\n", __func__, (ggml_time_us() - t_spec_start) / 1000.0f); - LOG_INF("%s: total time: %.3f ms\n", __func__, (ggml_time_us() - t_main_start) / 1000.0f); - - int retval = 0; + LOG_INF("generated %d frames, %zu bytes of WAV audio (%d Hz)\n", n_frames, data_len, sample_rate); - if (save_wav16(params.out_file, audio, n_sr)) { - LOG_INF("%s: audio written to file '%s'\n", __func__, params.out_file.c_str()); - } else { - retval = ENOENT; + const double t_prompt_s = (t_gen_start_us - t_prompt_start_us) / 1e6; + const double t_total_s = t_prompt_s + t_gen_s; + const double audio_s = sample_rate > 0 ? (double) n_samples / sample_rate : 0.0; + LOG_INF("timings: prompt eval %.2fs + generation %.2fs = total %.2fs\n", t_prompt_s, t_gen_s, t_total_s); + LOG_INF(" output audio = %.2fs (audio time = %.2fx process time)\n", audio_s, t_total_s > 0 ? audio_s / t_total_s : 0.0); + FILE * f = fopen(params.out_file.c_str(), "wb"); + if (!f) { + LOG_ERR("failed to open %s\n", params.out_file.c_str()); + return 1; } + fwrite(data, 1, data_len, f); + fclose(f); + LOG_INF("wrote %s\n", params.out_file.c_str()); llama_backend_free(); - - return retval; + return 0; } diff --git a/tools/ui/.storybook/main.ts b/tools/ui/.storybook/main.ts index 4f6945f21080..b02ecc5d5a62 100644 --- a/tools/ui/.storybook/main.ts +++ b/tools/ui/.storybook/main.ts @@ -11,7 +11,8 @@ const config: StorybookConfig = { '@chromatic-com/storybook', '@storybook/addon-vitest', '@storybook/addon-a11y', - '@storybook/addon-docs' + '@storybook/addon-docs', + '@storybook/addon-mcp' ], framework: '@storybook/sveltekit', viteFinal: async (config) => { diff --git a/tools/ui/.storybook/vitest.setup.ts b/tools/ui/.storybook/vitest.setup.ts deleted file mode 100644 index 14715728989b..000000000000 --- a/tools/ui/.storybook/vitest.setup.ts +++ /dev/null @@ -1,12 +0,0 @@ -import * as a11yAddonAnnotations from '@storybook/addon-a11y/preview'; -import { setProjectAnnotations } from '@storybook/sveltekit'; -import * as previewAnnotations from './preview'; -import { beforeAll } from 'vitest'; - -const project = setProjectAnnotations([a11yAddonAnnotations, previewAnnotations]); - -beforeAll(async () => { - if (project.beforeAll) { - await project.beforeAll(); - } -}); diff --git a/tools/ui/CMakeLists.txt b/tools/ui/CMakeLists.txt index 74bca417e372..208b46a5c15a 100644 --- a/tools/ui/CMakeLists.txt +++ b/tools/ui/CMakeLists.txt @@ -61,12 +61,30 @@ if(CMAKE_CROSSCOMPILING) # phony target to tie it into the dependency graph add_custom_target(llama-ui-embed DEPENDS "${LLAMA_UI_EMBED_EXE}") else() + # exclude llama-ui-embed from sanitizer flags, + # it's a build-time-only tool, no need to instrument it + # this is to fix TSan "memory layout is incompatible" error on CI + get_directory_property(_llama_ui_dir_co COMPILE_OPTIONS) + get_directory_property(_llama_ui_dir_ll LINK_LIBRARIES) + set(_llama_ui_embed_co ${_llama_ui_dir_co}) + set(_llama_ui_embed_ll ${_llama_ui_dir_ll}) + list(FILTER _llama_ui_embed_co EXCLUDE REGEX ".*-fsanitize=.*") + list(FILTER _llama_ui_embed_ll EXCLUDE REGEX ".*-fsanitize=.*") + set_directory_properties(PROPERTIES + COMPILE_OPTIONS "${_llama_ui_embed_co}" + LINK_LIBRARIES "${_llama_ui_embed_ll}") + add_executable(llama-ui-embed embed.cpp) target_compile_features(llama-ui-embed PRIVATE cxx_std_17) set_target_properties(llama-ui-embed PROPERTIES RUNTIME_OUTPUT_DIRECTORY "${CMAKE_CURRENT_BINARY_DIR}" ) set(LLAMA_UI_EMBED_EXE "$") + + # restore so the llama-ui library below keeps sanitizer instrumentation + set_directory_properties(PROPERTIES + COMPILE_OPTIONS "${_llama_ui_dir_co}" + LINK_LIBRARIES "${_llama_ui_dir_ll}") endif() # Run the provisioning script every build so source changes in tools/ui/ are diff --git a/tools/ui/README.md b/tools/ui/README.md index 1b99ebbfe806..53b5925e2cee 100644 --- a/tools/ui/README.md +++ b/tools/ui/README.md @@ -89,7 +89,7 @@ Llama UI supports two server operation modes: ```bash cd tools/ui -npm install +npm ci ``` ### 2. Start llama-server diff --git a/tools/ui/package-lock.json b/tools/ui/package-lock.json index 2fe44f4c34f7..976ed050f837 100644 --- a/tools/ui/package-lock.json +++ b/tools/ui/package-lock.json @@ -8,20 +8,21 @@ "name": "llama-ui", "version": "1.0.0", "devDependencies": { - "@chromatic-com/storybook": "5.0.0", + "@chromatic-com/storybook": "5.2.1", "@eslint/compat": "1.4.1", "@eslint/js": "9.39.2", "@internationalized/date": "3.12.2", "@lucide/svelte": "1.25.0", - "@modelcontextprotocol/sdk": "1.26.0", + "@modelcontextprotocol/sdk": "1.30.0", "@playwright/test": "1.56.1", - "@storybook/addon-a11y": "10.2.4", - "@storybook/addon-docs": "10.2.4", - "@storybook/addon-svelte-csf": "5.0.10", - "@storybook/addon-vitest": "10.2.4", - "@storybook/sveltekit": "10.2.4", + "@storybook/addon-a11y": "10.5.6", + "@storybook/addon-docs": "10.5.6", + "@storybook/addon-mcp": "0.7.0", + "@storybook/addon-svelte-csf": "5.1.2", + "@storybook/addon-vitest": "10.5.6", + "@storybook/sveltekit": "10.5.6", "@sveltejs/adapter-static": "3.0.10", - "@sveltejs/kit": "2.60.1", + "@sveltejs/kit": "2.70.2", "@sveltejs/vite-plugin-svelte": "6.2.1", "@tailwindcss/forms": "0.5.10", "@tailwindcss/typography": "0.5.16", @@ -29,16 +30,16 @@ "@types/node": "24.13.0", "@vite-pwa/assets-generator": "1.0.2", "@vite-pwa/sveltekit": "1.1.0", - "@vitest/browser": "4.1.8", - "@vitest/browser-playwright": "4.1.8", - "@vitest/coverage-v8": "4.1.8", + "@vitest/browser": "4.1.10", + "@vitest/browser-playwright": "4.1.10", + "@vitest/coverage-v8": "4.1.10", "bits-ui": "2.18.1", "clsx": "2.1.1", "dexie": "4.4.3", - "dompurify": "3.4.11", + "dompurify": "3.4.13", "eslint": "9.39.4", "eslint-config-prettier": "10.1.8", - "eslint-plugin-storybook": "10.4.2", + "eslint-plugin-storybook": "10.5.6", "eslint-plugin-svelte": "3.19.0", "fflate": "0.8.3", "globals": "16.5.0", @@ -63,7 +64,7 @@ "remark-math": "6.0.0", "remark-rehype": "11.1.2", "sass": "1.100.0", - "storybook": "10.4.2", + "storybook": "10.5.6", "svelte": "5.56.1", "svelte-check": "4.6.0", "svelte-sonner": "1.1.1", @@ -76,9 +77,9 @@ "unified": "11.0.5", "unist-util-visit": "5.1.0", "uuid": "13.0.2", - "vite": "7.3.5", + "vite": "7.3.6", "vite-plugin-devtools-json": "0.2.1", - "vitest": "4.1.8", + "vitest": "4.1.10", "vitest-browser-svelte": "2.1.1", "workbox-window": "7.4.1" } @@ -1776,15 +1777,14 @@ "license": "Apache-2.0" }, "node_modules/@chromatic-com/storybook": { - "version": "5.0.0", - "resolved": "https://registry.npmjs.org/@chromatic-com/storybook/-/storybook-5.0.0.tgz", - "integrity": "sha512-8wUsqL8kg6R5ue8XNE7Jv/iD1SuE4+6EXMIGIuE+T2loBITEACLfC3V8W44NJviCLusZRMWbzICddz0nU0bFaw==", + "version": "5.2.1", + "resolved": "https://registry.npmjs.org/@chromatic-com/storybook/-/storybook-5.2.1.tgz", + "integrity": "sha512-z6I7NJk/0VngA64y5TNYaB4Hc2X8+90n4op6lBt9PvWk5TmIlFLDqdX33rlrwbNRkkYijVgA/wO04rVYXi5Mlg==", "dev": true, "license": "MIT", "dependencies": { "@neoconfetti/react": "^1.0.0", - "chromatic": "^13.3.4", - "filesize": "^10.0.12", + "chromatic": "16.10.0", "jsonfile": "^6.1.0", "strip-ansi": "^7.1.0" }, @@ -1793,7 +1793,7 @@ "yarn": ">=1.22.18" }, "peerDependencies": { - "storybook": "^0.0.0-0 || ^10.1.0 || ^10.1.0-0 || ^10.2.0-0 || ^10.3.0-0" + "storybook": "^0.0.0-0 || ^10.1.0 || ^10.1.0-0 || ^10.2.0-0 || ^10.3.0-0 || ^10.4.0-0 || ^10.5.0-0 || ^10.6.0-0" } }, "node_modules/@emnapi/core": { @@ -1831,9 +1831,9 @@ } }, "node_modules/@esbuild/aix-ppc64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.27.7.tgz", - "integrity": "sha512-EKX3Qwmhz1eMdEJokhALr0YiD0lhQNwDqkPYyPhiSwKrh7/4KRjQc04sZ8db+5DVVnZ1LmbNDI1uAMPEUBnQPg==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/aix-ppc64/-/aix-ppc64-0.28.1.tgz", + "integrity": "sha512-Svl7tq8k/08+p6CXPpRjQ1fKX+1odH/BQbb48fV6fj3CWHhsoIOoY87w1oHXm0qEpkIK3ZfVgp0hed3XBXzXMQ==", "cpu": [ "ppc64" ], @@ -1848,9 +1848,9 @@ } }, "node_modules/@esbuild/android-arm": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.27.7.tgz", - "integrity": "sha512-jbPXvB4Yj2yBV7HUfE2KHe4GJX51QplCN1pGbYjvsyCZbQmies29EoJbkEc+vYuU5o45AfQn37vZlyXy4YJ8RQ==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/android-arm/-/android-arm-0.28.1.tgz", + "integrity": "sha512-0k2F129Xdio1TdJfzJ8sy1Q47vUD2NnwdhiAf7drUN1EBTfPf4hsFCtmMgu/6m8JSzsBrlmVjudMBQqOfG8usQ==", "cpu": [ "arm" ], @@ -1865,9 +1865,9 @@ } }, "node_modules/@esbuild/android-arm64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.27.7.tgz", - "integrity": "sha512-62dPZHpIXzvChfvfLJow3q5dDtiNMkwiRzPylSCfriLvZeq0a1bWChrGx/BbUbPwOrsWKMn8idSllklzBy+dgQ==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/android-arm64/-/android-arm64-0.28.1.tgz", + "integrity": "sha512-34EGEbCIAgosYz6goLcopX6Mo7NyGv9tfwEM2/7Ce2VcVRk568iSvniGWcUXIy7wEDR1wzolcxcriFVrWYcwBg==", "cpu": [ "arm64" ], @@ -1882,9 +1882,9 @@ } }, "node_modules/@esbuild/android-x64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.27.7.tgz", - "integrity": "sha512-x5VpMODneVDb70PYV2VQOmIUUiBtY3D3mPBG8NxVk5CogneYhkR7MmM3yR/uMdITLrC1ml/NV1rj4bMJuy9MCg==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/android-x64/-/android-x64-0.28.1.tgz", + "integrity": "sha512-dbwY7ltSMDWsRatcRpCnES4F+im88OCUgGZjy52shC7GqHRE/cYlxNbB4Z4UpJswpcc4Qxd2oE/ufM0p61IKng==", "cpu": [ "x64" ], @@ -1899,9 +1899,9 @@ } }, "node_modules/@esbuild/darwin-arm64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.27.7.tgz", - "integrity": "sha512-5lckdqeuBPlKUwvoCXIgI2D9/ABmPq3Rdp7IfL70393YgaASt7tbju3Ac+ePVi3KDH6N2RqePfHnXkaDtY9fkw==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/darwin-arm64/-/darwin-arm64-0.28.1.tgz", + "integrity": "sha512-TZbWkQY7kvTAXbXUT7uVACR5cMHsDiSz9z7ZKAX/RTq/WJEk3QyRr0wZpNhBDX+/0CtdqUIJlOiodQcta6tY3Q==", "cpu": [ "arm64" ], @@ -1916,9 +1916,9 @@ } }, "node_modules/@esbuild/darwin-x64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.27.7.tgz", - "integrity": "sha512-rYnXrKcXuT7Z+WL5K980jVFdvVKhCHhUwid+dDYQpH+qu+TefcomiMAJpIiC2EM3Rjtq0sO3StMV/+3w3MyyqQ==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/darwin-x64/-/darwin-x64-0.28.1.tgz", + "integrity": "sha512-zfdzgK9ACBNZLI/CyHTOx81SyNbM6YXn7rxSgX97VjyiPl9W1i4Ka4fgKECEoFCKGpvBj5qArWIGgQjOwkgskQ==", "cpu": [ "x64" ], @@ -1933,9 +1933,9 @@ } }, "node_modules/@esbuild/freebsd-arm64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.27.7.tgz", - "integrity": "sha512-B48PqeCsEgOtzME2GbNM2roU29AMTuOIN91dsMO30t+Ydis3z/3Ngoj5hhnsOSSwNzS+6JppqWsuhTp6E82l2w==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/freebsd-arm64/-/freebsd-arm64-0.28.1.tgz", + "integrity": "sha512-wG2EA8ENdEI0qhkSZMjfqrdY+ziCYCPMmtZjjIwOmXFjmyzEHn+UUxk5of+SYsjtfs3VpnlC7QLzSI5hY/rOAw==", "cpu": [ "arm64" ], @@ -1950,9 +1950,9 @@ } }, "node_modules/@esbuild/freebsd-x64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.27.7.tgz", - "integrity": "sha512-jOBDK5XEjA4m5IJK3bpAQF9/Lelu/Z9ZcdhTRLf4cajlB+8VEhFFRjWgfy3M1O4rO2GQ/b2dLwCUGpiF/eATNQ==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/freebsd-x64/-/freebsd-x64-0.28.1.tgz", + "integrity": "sha512-i7dZ9vQgnvSCzi/rYCXNgtF/U+eKZNJBzu3eTQbRgHnM7tNSizLOkRFAl3qzVc/Op/u5YkHHa4pf/3DOYHthLQ==", "cpu": [ "x64" ], @@ -1967,9 +1967,9 @@ } }, "node_modules/@esbuild/linux-arm": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.27.7.tgz", - "integrity": "sha512-RkT/YXYBTSULo3+af8Ib0ykH8u2MBh57o7q/DAs3lTJlyVQkgQvlrPTnjIzzRPQyavxtPtfg0EopvDyIt0j1rA==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/linux-arm/-/linux-arm-0.28.1.tgz", + "integrity": "sha512-qVXBOHQS+d5Y722GwJzJUtOLlX7km3CraOaGormF1pDtPd2C/l1SHRPgjLunLGe51Sh5YYWKMFDyV4SxgMQYTQ==", "cpu": [ "arm" ], @@ -1984,9 +1984,9 @@ } }, "node_modules/@esbuild/linux-arm64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.27.7.tgz", - "integrity": "sha512-RZPHBoxXuNnPQO9rvjh5jdkRmVizktkT7TCDkDmQ0W2SwHInKCAV95GRuvdSvA7w4VMwfCjUiPwDi0ZO6Nfe9A==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/linux-arm64/-/linux-arm64-0.28.1.tgz", + "integrity": "sha512-yHs+0uc8+nvEAfAfxrWQKK5peSNzBc4PegcMO0EJ2hT71uA7vB8Ihg2e77R2P7SG5uYjPbHlLLmve4LLLRCf0g==", "cpu": [ "arm64" ], @@ -2001,9 +2001,9 @@ } }, "node_modules/@esbuild/linux-ia32": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.27.7.tgz", - "integrity": "sha512-GA48aKNkyQDbd3KtkplYWT102C5sn/EZTY4XROkxONgruHPU72l+gW+FfF8tf2cFjeHaRbWpOYa/uRBz/Xq1Pg==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/linux-ia32/-/linux-ia32-0.28.1.tgz", + "integrity": "sha512-d1z4ZuP0ajrfz/FhGT4vv278rX8KnPPJx8i5+AtK7TYbx9Le9F1hyzurZpkEyjkGa9dUGhQow4C1NmeGvqxN2w==", "cpu": [ "ia32" ], @@ -2018,9 +2018,9 @@ } }, "node_modules/@esbuild/linux-loong64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.27.7.tgz", - "integrity": "sha512-a4POruNM2oWsD4WKvBSEKGIiWQF8fZOAsycHOt6JBpZ+JN2n2JH9WAv56SOyu9X5IqAjqSIPTaJkqN8F7XOQ5Q==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/linux-loong64/-/linux-loong64-0.28.1.tgz", + "integrity": "sha512-M5sRjUVZrkm1OAPR3dlOYzNmN+loZKGVi1VUQGrwuqLcbR6qeAz+famMhjASeH3YVKvZz+zT1jlh/keC3Rj/lg==", "cpu": [ "loong64" ], @@ -2035,9 +2035,9 @@ } }, "node_modules/@esbuild/linux-mips64el": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.27.7.tgz", - "integrity": "sha512-KabT5I6StirGfIz0FMgl1I+R1H73Gp0ofL9A3nG3i/cYFJzKHhouBV5VWK1CSgKvVaG4q1RNpCTR2LuTVB3fIw==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/linux-mips64el/-/linux-mips64el-0.28.1.tgz", + "integrity": "sha512-mRObBZeHh2OxcBFPWE/FjylkRgZdYuiTR3vaTozquCGOH14iP9oN4x4Ge81CoIDYQrXmIxpFumJBu5MtZpnQJQ==", "cpu": [ "mips64el" ], @@ -2052,9 +2052,9 @@ } }, "node_modules/@esbuild/linux-ppc64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.27.7.tgz", - "integrity": "sha512-gRsL4x6wsGHGRqhtI+ifpN/vpOFTQtnbsupUF5R5YTAg+y/lKelYR1hXbnBdzDjGbMYjVJLJTd2OFmMewAgwlQ==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/linux-ppc64/-/linux-ppc64-0.28.1.tgz", + "integrity": "sha512-slScBsMAb3GFDcdrCgLwZtPYRoH2H/youv10QiZyRjmsP48fznoveWytSgCI/R0ZcUgpc0ZhIUEx6LHts8yrfQ==", "cpu": [ "ppc64" ], @@ -2069,9 +2069,9 @@ } }, "node_modules/@esbuild/linux-riscv64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.27.7.tgz", - "integrity": "sha512-hL25LbxO1QOngGzu2U5xeXtxXcW+/GvMN3ejANqXkxZ/opySAZMrc+9LY/WyjAan41unrR3YrmtTsUpwT66InQ==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/linux-riscv64/-/linux-riscv64-0.28.1.tgz", + "integrity": "sha512-kw0owk1o0GFETUJyW0jc0G4Yzs0BHZn0JDZ8JRT088vjJYX777BAs1fDGxAC+q831qOs2DTC96mNsG2opdfyyQ==", "cpu": [ "riscv64" ], @@ -2086,9 +2086,9 @@ } }, "node_modules/@esbuild/linux-s390x": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.27.7.tgz", - "integrity": "sha512-2k8go8Ycu1Kb46vEelhu1vqEP+UeRVj2zY1pSuPdgvbd5ykAw82Lrro28vXUrRmzEsUV0NzCf54yARIK8r0fdw==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/linux-s390x/-/linux-s390x-0.28.1.tgz", + "integrity": "sha512-/lAIjX8aYFRByhh6L5rYtPEDRqa9de/4V/juOXcta5frjvzXO4/sqEtyytse0g3zZFuWu5cDN0MkLz2qRDD2Ag==", "cpu": [ "s390x" ], @@ -2103,9 +2103,9 @@ } }, "node_modules/@esbuild/linux-x64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.27.7.tgz", - "integrity": "sha512-hzznmADPt+OmsYzw1EE33ccA+HPdIqiCRq7cQeL1Jlq2gb1+OyWBkMCrYGBJ+sxVzve2ZJEVeePbLM2iEIZSxA==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/linux-x64/-/linux-x64-0.28.1.tgz", + "integrity": "sha512-u/anNYF2mmVOEDwLtnQ1wOr3EZ9sTNGLWrsYGYwHWzGA3Si84IOkHXlbWTD1NB+9/1lcnweYKO54uhxZydNzfA==", "cpu": [ "x64" ], @@ -2120,9 +2120,9 @@ } }, "node_modules/@esbuild/netbsd-arm64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/netbsd-arm64/-/netbsd-arm64-0.27.7.tgz", - "integrity": "sha512-b6pqtrQdigZBwZxAn1UpazEisvwaIDvdbMbmrly7cDTMFnw/+3lVxxCTGOrkPVnsYIosJJXAsILG9XcQS+Yu6w==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/netbsd-arm64/-/netbsd-arm64-0.28.1.tgz", + "integrity": "sha512-oks0DYbLwWMmaakTsCb+zL4E+aHRVLom9IJZOAthMQEPiQmydXHkziYEsGYRx0uNV/IjEKGAV941JzH02pflqw==", "cpu": [ "arm64" ], @@ -2137,9 +2137,9 @@ } }, "node_modules/@esbuild/netbsd-x64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.27.7.tgz", - "integrity": "sha512-OfatkLojr6U+WN5EDYuoQhtM+1xco+/6FSzJJnuWiUw5eVcicbyK3dq5EeV/QHT1uy6GoDhGbFpprUiHUYggrw==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/netbsd-x64/-/netbsd-x64-0.28.1.tgz", + "integrity": "sha512-aeL6lAnN89Hz43Mlh1G8ARasbuoYvSITDEx0tHh5b7jJnHcssqgjy9Yx430GDpmCa6OyrKoS0aNRjKundRizGg==", "cpu": [ "x64" ], @@ -2154,9 +2154,9 @@ } }, "node_modules/@esbuild/openbsd-arm64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/openbsd-arm64/-/openbsd-arm64-0.27.7.tgz", - "integrity": "sha512-AFuojMQTxAz75Fo8idVcqoQWEHIXFRbOc1TrVcFSgCZtQfSdc1RXgB3tjOn/krRHENUB4j00bfGjyl2mJrU37A==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/openbsd-arm64/-/openbsd-arm64-0.28.1.tgz", + "integrity": "sha512-MEFJe5C3R8pwXdZ5Y21oo6m7ePiS0d9pWucn99O/wvyJZChoIQKrQDxKrGeW8F5+T0okTHesAmDeiHDTIq0V/Q==", "cpu": [ "arm64" ], @@ -2171,9 +2171,9 @@ } }, "node_modules/@esbuild/openbsd-x64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.27.7.tgz", - "integrity": "sha512-+A1NJmfM8WNDv5CLVQYJ5PshuRm/4cI6WMZRg1by1GwPIQPCTs1GLEUHwiiQGT5zDdyLiRM/l1G0Pv54gvtKIg==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/openbsd-x64/-/openbsd-x64-0.28.1.tgz", + "integrity": "sha512-i/ZLIOafE0Z8cI/XANJAixoJL/uRAoS2xOA3rb0xN+KK0K177cMAsQYkzHtBrtMXAKuAc7HGgcWiZ/sRC1Nxgw==", "cpu": [ "x64" ], @@ -2188,9 +2188,9 @@ } }, "node_modules/@esbuild/openharmony-arm64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/openharmony-arm64/-/openharmony-arm64-0.27.7.tgz", - "integrity": "sha512-+KrvYb/C8zA9CU/g0sR6w2RBw7IGc5J2BPnc3dYc5VJxHCSF1yNMxTV5LQ7GuKteQXZtspjFbiuW5/dOj7H4Yw==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/openharmony-arm64/-/openharmony-arm64-0.28.1.tgz", + "integrity": "sha512-ge+Z7EXFNt2BO1oAMsVpiQ8EwndV9i1xXerAeTIK7AtPs3bKFXQM7nlRxDSIUIMeueR1CNXxqztLzdNeReKBJg==", "cpu": [ "arm64" ], @@ -2205,9 +2205,9 @@ } }, "node_modules/@esbuild/sunos-x64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.27.7.tgz", - "integrity": "sha512-ikktIhFBzQNt/QDyOL580ti9+5mL/YZeUPKU2ivGtGjdTYoqz6jObj6nOMfhASpS4GU4Q/Clh1QtxWAvcYKamA==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/sunos-x64/-/sunos-x64-0.28.1.tgz", + "integrity": "sha512-BEjgtECkL3vY+SaSQ6nzVfiALUeFxpawyp8Jmf5PtYhf1Ug40N1h/hxlhts+f1FvSvarEigdxS3BlSMI2PJLcQ==", "cpu": [ "x64" ], @@ -2222,9 +2222,9 @@ } }, "node_modules/@esbuild/win32-arm64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.27.7.tgz", - "integrity": "sha512-7yRhbHvPqSpRUV7Q20VuDwbjW5kIMwTHpptuUzV+AA46kiPze5Z7qgt6CLCK3pWFrHeNfDd1VKgyP4O+ng17CA==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/win32-arm64/-/win32-arm64-0.28.1.tgz", + "integrity": "sha512-lCv9eK/H6ZJWbE7bh2nw54CZ9M2nupBxJcTsdk/QQnWkdSjKGuxmmH8/GWrlT1eMmZfn4dGcCjRte397WqfQXA==", "cpu": [ "arm64" ], @@ -2239,9 +2239,9 @@ } }, "node_modules/@esbuild/win32-ia32": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.27.7.tgz", - "integrity": "sha512-SmwKXe6VHIyZYbBLJrhOoCJRB/Z1tckzmgTLfFYOfpMAx63BJEaL9ExI8x7v0oAO3Zh6D/Oi1gVxEYr5oUCFhw==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.28.1.tgz", + "integrity": "sha512-zvb/mB2bSCoJOpoCBgYKKpX6YM6mJBlBUVUtVj41DlZJVEB6/0CKlRYxP5wWl1C1ILiCoAU5wZZ4q1P3qeS6Eg==", "cpu": [ "ia32" ], @@ -2256,9 +2256,9 @@ } }, "node_modules/@esbuild/win32-x64": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.27.7.tgz", - "integrity": "sha512-56hiAJPhwQ1R4i+21FVF7V8kSD5zZTdHcVuRFMW0hn753vVfQN8xlx4uOPT4xoGH0Z/oVATuR82AiqSTDIpaHg==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/@esbuild/win32-x64/-/win32-x64-0.28.1.tgz", + "integrity": "sha512-bm4Mowrv+GXMlpWX++EcXw/iLyd1o3+bJkC2DkWXYVvgZCqD/bSj9ctZeAMC3cIxgjRVR2Dufaiu4YPxr5gW1A==", "cpu": [ "x64" ], @@ -2503,13 +2503,13 @@ "license": "MIT" }, "node_modules/@hono/node-server": { - "version": "1.19.14", - "resolved": "https://registry.npmjs.org/@hono/node-server/-/node-server-1.19.14.tgz", - "integrity": "sha512-GwtvgtXxnWsucXvbQXkRgqksiH2Qed37H9xHZocE5sA3N8O8O8/8FA3uclQXxXVzc9XBZuEOMK7+r02FmSpHtw==", + "version": "2.1.0", + "resolved": "https://registry.npmjs.org/@hono/node-server/-/node-server-2.1.0.tgz", + "integrity": "sha512-XovyyCCnBzW+zKu+z/zq8hwNs4KOR5rEMAOxo2f40Q5xoOI37IMm6MIg2COOUtUApo0i6850MTBKH2u4QLGIqg==", "dev": true, "license": "MIT", "engines": { - "node": ">=18.14.1" + "node": ">=20" }, "peerDependencies": { "hono": "^4" @@ -2600,10 +2600,20 @@ "import-meta-resolve": "^4.2.0" } }, + "node_modules/@img/colour": { + "version": "1.1.0", + "resolved": "https://registry.npmjs.org/@img/colour/-/colour-1.1.0.tgz", + "integrity": "sha512-Td76q7j57o/tLVdgS746cYARfSyxk8iEfRxewL9h4OMzYhbW4TAcppl0mT4eyqXddh6L/jwoM75mo7ixa/pCeQ==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=18" + } + }, "node_modules/@img/sharp-darwin-arm64": { - "version": "0.33.5", - "resolved": "https://registry.npmjs.org/@img/sharp-darwin-arm64/-/sharp-darwin-arm64-0.33.5.tgz", - "integrity": "sha512-UT4p+iz/2H4twwAoLCqfA9UH5pI6DggwKEGuaPy7nCVQ8ZsiY5PIcrRvD1DzuY3qYL07NtIQcWnBSY/heikIFQ==", + "version": "0.35.3", + "resolved": "https://registry.npmjs.org/@img/sharp-darwin-arm64/-/sharp-darwin-arm64-0.35.3.tgz", + "integrity": "sha512-RMnFX7YQsMoh7lWfcM4NEHHymBX/rLuKNPVM84XE9ONPcaSCDgE7CHIHpSgPcO2xcRthgBy1HfNO319mwhIAkg==", "cpu": [ "arm64" ], @@ -2614,19 +2624,19 @@ "darwin" ], "engines": { - "node": "^18.17.0 || ^20.3.0 || >=21.0.0" + "node": ">=20.9.0" }, "funding": { "url": "https://opencollective.com/libvips" }, "optionalDependencies": { - "@img/sharp-libvips-darwin-arm64": "1.0.4" + "@img/sharp-libvips-darwin-arm64": "1.3.2" } }, "node_modules/@img/sharp-darwin-x64": { - "version": "0.33.5", - "resolved": "https://registry.npmjs.org/@img/sharp-darwin-x64/-/sharp-darwin-x64-0.33.5.tgz", - "integrity": "sha512-fyHac4jIc1ANYGRDxtiqelIbdWkIuQaI84Mv45KvGRRxSAa7o7d1ZKAOBaYbnepLC1WqxfpimdeWfvqqSGwR2Q==", + "version": "0.35.3", + "resolved": "https://registry.npmjs.org/@img/sharp-darwin-x64/-/sharp-darwin-x64-0.35.3.tgz", + "integrity": "sha512-Xo+5uFBtLN0BKqieTxiFzFPQAUlBbbH5iBKyRX/z1JrbnYsHTfKJnUfL8+p2TPXr1pXqao4eeL4Rl144uDpK9w==", "cpu": [ "x64" ], @@ -2637,19 +2647,39 @@ "darwin" ], "engines": { - "node": "^18.17.0 || ^20.3.0 || >=21.0.0" + "node": ">=20.9.0" }, "funding": { "url": "https://opencollective.com/libvips" }, "optionalDependencies": { - "@img/sharp-libvips-darwin-x64": "1.0.4" + "@img/sharp-libvips-darwin-x64": "1.3.2" + } + }, + "node_modules/@img/sharp-freebsd-wasm32": { + "version": "0.35.3", + "resolved": "https://registry.npmjs.org/@img/sharp-freebsd-wasm32/-/sharp-freebsd-wasm32-0.35.3.tgz", + "integrity": "sha512-lUxcqWIj2wMQ9BrwNjngcr1gWUr5xgaGThBRqPPalIC2n67Cqj1uPh8NnA/ZhAg8hUbKl+kVHKwgUIwe6ZYPrg==", + "dev": true, + "license": "Apache-2.0", + "optional": true, + "os": [ + "freebsd" + ], + "dependencies": { + "@img/sharp-wasm32": "0.35.3" + }, + "engines": { + "node": ">=20.9.0" + }, + "funding": { + "url": "https://opencollective.com/libvips" } }, "node_modules/@img/sharp-libvips-darwin-arm64": { - "version": "1.0.4", - "resolved": "https://registry.npmjs.org/@img/sharp-libvips-darwin-arm64/-/sharp-libvips-darwin-arm64-1.0.4.tgz", - "integrity": "sha512-XblONe153h0O2zuFfTAbQYAX2JhYmDHeWikp1LM9Hul9gVPjFY427k6dFEcOL72O01QxQsWi761svJ/ev9xEDg==", + "version": "1.3.2", + "resolved": "https://registry.npmjs.org/@img/sharp-libvips-darwin-arm64/-/sharp-libvips-darwin-arm64-1.3.2.tgz", + "integrity": "sha512-9J6ypZFpQBj4YnePGoq/S38w6nz+vqg5WZLrLGY4YuSemdMq47GMLBPO42MzwdGwpg/agZ7xzZcFHa48xlywfg==", "cpu": [ "arm64" ], @@ -2664,9 +2694,9 @@ } }, "node_modules/@img/sharp-libvips-darwin-x64": { - "version": "1.0.4", - "resolved": "https://registry.npmjs.org/@img/sharp-libvips-darwin-x64/-/sharp-libvips-darwin-x64-1.0.4.tgz", - "integrity": "sha512-xnGR8YuZYfJGmWPvmlunFaWJsb9T/AO2ykoP3Fz/0X5XV2aoYBPkX6xqCQvUTKKiLddarLaxpzNe+b1hjeWHAQ==", + "version": "1.3.2", + "resolved": "https://registry.npmjs.org/@img/sharp-libvips-darwin-x64/-/sharp-libvips-darwin-x64-1.3.2.tgz", + "integrity": "sha512-m2pW1n6cns9VaubNwsZ+c3CRYjxNQWgJ5gPlnL1nbBcpkBvFm6SCFN5o0psFHI8w9n11NKhFkeEDns98tiqbEw==", "cpu": [ "x64" ], @@ -2681,9 +2711,9 @@ } }, "node_modules/@img/sharp-libvips-linux-arm": { - "version": "1.0.5", - "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linux-arm/-/sharp-libvips-linux-arm-1.0.5.tgz", - "integrity": "sha512-gvcC4ACAOPRNATg/ov8/MnbxFDJqf/pDePbBnuBDcjsI8PssmjoKMAz4LtLaVi+OnSb5FK/yIOamqDwGmXW32g==", + "version": "1.3.2", + "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linux-arm/-/sharp-libvips-linux-arm-1.3.2.tgz", + "integrity": "sha512-1eMLzy92I4J6rmi4mAT8yC3HxOtniyGELlzGbNMLLeqe052ahFQ0h6LFq+lh5DsDIdYViIDst08abvSbcEdLXQ==", "cpu": [ "arm" ], @@ -2698,9 +2728,9 @@ } }, "node_modules/@img/sharp-libvips-linux-arm64": { - "version": "1.0.4", - "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linux-arm64/-/sharp-libvips-linux-arm64-1.0.4.tgz", - "integrity": "sha512-9B+taZ8DlyyqzZQnoeIvDVR/2F4EbMepXMc/NdVbkzsJbzkUjhXv/70GQJ7tdLA4YJgNP25zukcxpX2/SueNrA==", + "version": "1.3.2", + "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linux-arm64/-/sharp-libvips-linux-arm64-1.3.2.tgz", + "integrity": "sha512-dqVSFynCox4C/J8kT16V7SIFAns0IjgLwkvYT7p8LQVmJ5OS5b6tI9IGflxTeuBS//zXeFIUbwt5dwxyZ17cnA==", "cpu": [ "arm64" ], @@ -2714,10 +2744,44 @@ "url": "https://opencollective.com/libvips" } }, + "node_modules/@img/sharp-libvips-linux-ppc64": { + "version": "1.3.2", + "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linux-ppc64/-/sharp-libvips-linux-ppc64-1.3.2.tgz", + "integrity": "sha512-3z0NHDxD6n5I9gc05U1eW1AyRm+Gznzq3naMrthPNqE6oYykcogW0l/jfpJdjYnuNl8R7yI9pNbE1XiUeyq0Aw==", + "cpu": [ + "ppc64" + ], + "dev": true, + "license": "LGPL-3.0-or-later", + "optional": true, + "os": [ + "linux" + ], + "funding": { + "url": "https://opencollective.com/libvips" + } + }, + "node_modules/@img/sharp-libvips-linux-riscv64": { + "version": "1.3.2", + "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linux-riscv64/-/sharp-libvips-linux-riscv64-1.3.2.tgz", + "integrity": "sha512-bsb4rI+NldGOsXuej2r8OdSS8+zXDVaCWxyWrcv6kneTOlgAHtZABRzBBCwdsPiD90J4myNJuHpg6kA20ImW/w==", + "cpu": [ + "riscv64" + ], + "dev": true, + "license": "LGPL-3.0-or-later", + "optional": true, + "os": [ + "linux" + ], + "funding": { + "url": "https://opencollective.com/libvips" + } + }, "node_modules/@img/sharp-libvips-linux-s390x": { - "version": "1.0.4", - "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linux-s390x/-/sharp-libvips-linux-s390x-1.0.4.tgz", - "integrity": "sha512-u7Wz6ntiSSgGSGcjZ55im6uvTrOxSIS8/dgoVMoiGE9I6JAfU50yH5BoDlYA1tcuGS7g/QNtetJnxA6QEsCVTA==", + "version": "1.3.2", + "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linux-s390x/-/sharp-libvips-linux-s390x-1.3.2.tgz", + "integrity": "sha512-/ABshyj8gCpyIrNXnHn4LorDJ0HHm1VhXPBlxZ8zAtfVPAaSafXPGn+sUSIRiwaSBy0mmFjSjiXI5mkcwdChKQ==", "cpu": [ "s390x" ], @@ -2732,9 +2796,9 @@ } }, "node_modules/@img/sharp-libvips-linux-x64": { - "version": "1.0.4", - "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linux-x64/-/sharp-libvips-linux-x64-1.0.4.tgz", - "integrity": "sha512-MmWmQ3iPFZr0Iev+BAgVMb3ZyC4KeFc3jFxnNbEPas60e1cIfevbtuyf9nDGIzOaW9PdnDciJm+wFFaTlj5xYw==", + "version": "1.3.2", + "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linux-x64/-/sharp-libvips-linux-x64-1.3.2.tgz", + "integrity": "sha512-ITPEtgffGJ0S6G9dRyw/366tJQqFRcHWPHhC+Stpg3Z8AEMrDrTr2lhdz4f/Y/HMbRh//7Z5mBzEpVdi62Oc3w==", "cpu": [ "x64" ], @@ -2749,9 +2813,9 @@ } }, "node_modules/@img/sharp-libvips-linuxmusl-arm64": { - "version": "1.0.4", - "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linuxmusl-arm64/-/sharp-libvips-linuxmusl-arm64-1.0.4.tgz", - "integrity": "sha512-9Ti+BbTYDcsbp4wfYib8Ctm1ilkugkA/uscUn6UXK1ldpC1JjiXbLfFZtRlBhjPZ5o1NCLiDbg8fhUPKStHoTA==", + "version": "1.3.2", + "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linuxmusl-arm64/-/sharp-libvips-linuxmusl-arm64-1.3.2.tgz", + "integrity": "sha512-zE9EdiUzUmg5mDT5a1rk5fYJ6GWPloTwWBYDS14naqHsL+EaMpDj1AWnpLgh3u0YCORv2Tt50wrcrpYqkP97Kw==", "cpu": [ "arm64" ], @@ -2766,9 +2830,9 @@ } }, "node_modules/@img/sharp-libvips-linuxmusl-x64": { - "version": "1.0.4", - "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linuxmusl-x64/-/sharp-libvips-linuxmusl-x64-1.0.4.tgz", - "integrity": "sha512-viYN1KX9m+/hGkJtvYYp+CCLgnJXwiQB39damAO7WMdKWlIhmYTfHjwSbQeUK/20vY154mwezd9HflVFM1wVSw==", + "version": "1.3.2", + "resolved": "https://registry.npmjs.org/@img/sharp-libvips-linuxmusl-x64/-/sharp-libvips-linuxmusl-x64-1.3.2.tgz", + "integrity": "sha512-m0lrLiUt+lBYnCFr8qV/65yMR4E/c7/wf78I5eKTdkEakFAlZ9QlzEM3QIhhAwVeUhLAHLcCq7a7Vszq/oFNZQ==", "cpu": [ "x64" ], @@ -2783,9 +2847,9 @@ } }, "node_modules/@img/sharp-linux-arm": { - "version": "0.33.5", - "resolved": "https://registry.npmjs.org/@img/sharp-linux-arm/-/sharp-linux-arm-0.33.5.tgz", - "integrity": "sha512-JTS1eldqZbJxjvKaAkxhZmBqPRGmxgu+qFKSInv8moZ2AmT5Yib3EQ1c6gp493HvrvV8QgdOXdyaIBrhvFhBMQ==", + "version": "0.35.3", + "resolved": "https://registry.npmjs.org/@img/sharp-linux-arm/-/sharp-linux-arm-0.35.3.tgz", + "integrity": "sha512-affVWCTLooy8TSxbDx2qkzuDeaWLNVBA+P//FNBirHsXpP2fuBhk5AuboYUnrDnzoXes8GFjpTx0SBFOCRg+FA==", "cpu": [ "arm" ], @@ -2796,19 +2860,19 @@ "linux" ], "engines": { - "node": "^18.17.0 || ^20.3.0 || >=21.0.0" + "node": ">=20.9.0" }, "funding": { "url": "https://opencollective.com/libvips" }, "optionalDependencies": { - "@img/sharp-libvips-linux-arm": "1.0.5" + "@img/sharp-libvips-linux-arm": "1.3.2" } }, "node_modules/@img/sharp-linux-arm64": { - "version": "0.33.5", - "resolved": "https://registry.npmjs.org/@img/sharp-linux-arm64/-/sharp-linux-arm64-0.33.5.tgz", - "integrity": "sha512-JMVv+AMRyGOHtO1RFBiJy/MBsgz0x4AWrT6QoEVVTyh1E39TrCUpTRI7mx9VksGX4awWASxqCYLCV4wBZHAYxA==", + "version": "0.35.3", + "resolved": "https://registry.npmjs.org/@img/sharp-linux-arm64/-/sharp-linux-arm64-0.35.3.tgz", + "integrity": "sha512-QgKDspHPnrU+GQ55XPhGwyhC8acLVOOSyAvo1oVfFmrIXLkDNmGWzAfDZ4xK8oSA1qBQrALcHX0G5UZni/SuFQ==", "cpu": [ "arm64" ], @@ -2819,19 +2883,65 @@ "linux" ], "engines": { - "node": "^18.17.0 || ^20.3.0 || >=21.0.0" + "node": ">=20.9.0" }, "funding": { "url": "https://opencollective.com/libvips" }, "optionalDependencies": { - "@img/sharp-libvips-linux-arm64": "1.0.4" + "@img/sharp-libvips-linux-arm64": "1.3.2" + } + }, + "node_modules/@img/sharp-linux-ppc64": { + "version": "0.35.3", + "resolved": "https://registry.npmjs.org/@img/sharp-linux-ppc64/-/sharp-linux-ppc64-0.35.3.tgz", + "integrity": "sha512-sMd8rDxmpLOwv/7N44klFjOD5DUO7FLdjiXDI0hoxYaf7Ar262dQIEkosE98bps+5HPLtp/EvNqeqQtOycP/IA==", + "cpu": [ + "ppc64" + ], + "dev": true, + "license": "Apache-2.0", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=20.9.0" + }, + "funding": { + "url": "https://opencollective.com/libvips" + }, + "optionalDependencies": { + "@img/sharp-libvips-linux-ppc64": "1.3.2" + } + }, + "node_modules/@img/sharp-linux-riscv64": { + "version": "0.35.3", + "resolved": "https://registry.npmjs.org/@img/sharp-linux-riscv64/-/sharp-linux-riscv64-0.35.3.tgz", + "integrity": "sha512-0Eob78yjlYPfL5vMNWAW55l3R9Y6BQS/gOfe0ZcP9mEz9ohhKSt4im1hayiknXgf8AWrFqMvJcKIdmLmEe7yeQ==", + "cpu": [ + "riscv64" + ], + "dev": true, + "license": "Apache-2.0", + "optional": true, + "os": [ + "linux" + ], + "engines": { + "node": ">=20.9.0" + }, + "funding": { + "url": "https://opencollective.com/libvips" + }, + "optionalDependencies": { + "@img/sharp-libvips-linux-riscv64": "1.3.2" } }, "node_modules/@img/sharp-linux-s390x": { - "version": "0.33.5", - "resolved": "https://registry.npmjs.org/@img/sharp-linux-s390x/-/sharp-linux-s390x-0.33.5.tgz", - "integrity": "sha512-y/5PCd+mP4CA/sPDKl2961b+C9d+vPAveS33s6Z3zfASk2j5upL6fXVPZi7ztePZ5CuH+1kW8JtvxgbuXHRa4Q==", + "version": "0.35.3", + "resolved": "https://registry.npmjs.org/@img/sharp-linux-s390x/-/sharp-linux-s390x-0.35.3.tgz", + "integrity": "sha512-KgAxQ0DxpNOq1rG2t5cgTgShJFGSuU7XO45cqC+1NVOuZnP6tlgZRuSYOfNupGkHID0o3cJOsw4DVeJpMovcGw==", "cpu": [ "s390x" ], @@ -2842,19 +2952,19 @@ "linux" ], "engines": { - "node": "^18.17.0 || ^20.3.0 || >=21.0.0" + "node": ">=20.9.0" }, "funding": { "url": "https://opencollective.com/libvips" }, "optionalDependencies": { - "@img/sharp-libvips-linux-s390x": "1.0.4" + "@img/sharp-libvips-linux-s390x": "1.3.2" } }, "node_modules/@img/sharp-linux-x64": { - "version": "0.33.5", - "resolved": "https://registry.npmjs.org/@img/sharp-linux-x64/-/sharp-linux-x64-0.33.5.tgz", - "integrity": "sha512-opC+Ok5pRNAzuvq1AG0ar+1owsu842/Ab+4qvU879ippJBHvyY5n2mxF1izXqkPYlGuP/M556uh53jRLJmzTWA==", + "version": "0.35.3", + "resolved": "https://registry.npmjs.org/@img/sharp-linux-x64/-/sharp-linux-x64-0.35.3.tgz", + "integrity": "sha512-8pqvxubL2PGdhlPy6GLqzDYMUjyRmKAwKHYKixpdJYBUK7PJ0C029XdsnpFIdgRZG68fZiGdHVWcKPvtiPB4cA==", "cpu": [ "x64" ], @@ -2865,19 +2975,19 @@ "linux" ], "engines": { - "node": "^18.17.0 || ^20.3.0 || >=21.0.0" + "node": ">=20.9.0" }, "funding": { "url": "https://opencollective.com/libvips" }, "optionalDependencies": { - "@img/sharp-libvips-linux-x64": "1.0.4" + "@img/sharp-libvips-linux-x64": "1.3.2" } }, "node_modules/@img/sharp-linuxmusl-arm64": { - "version": "0.33.5", - "resolved": "https://registry.npmjs.org/@img/sharp-linuxmusl-arm64/-/sharp-linuxmusl-arm64-0.33.5.tgz", - "integrity": "sha512-XrHMZwGQGvJg2V/oRSUfSAfjfPxO+4DkiRh6p2AFjLQztWUuY/o8Mq0eMQVIY7HJ1CDQUJlxGGZRw1a5bqmd1g==", + "version": "0.35.3", + "resolved": "https://registry.npmjs.org/@img/sharp-linuxmusl-arm64/-/sharp-linuxmusl-arm64-0.35.3.tgz", + "integrity": "sha512-Vz0iQjzzcSX3HCbfwFfCSG/9SCIqyO0mH2sXyiHaAYfBk0cRsCWXRyQYX0ovCK/PAQBbTzQ0dsPQHh5MAFL59w==", "cpu": [ "arm64" ], @@ -2888,19 +2998,19 @@ "linux" ], "engines": { - "node": "^18.17.0 || ^20.3.0 || >=21.0.0" + "node": ">=20.9.0" }, "funding": { "url": "https://opencollective.com/libvips" }, "optionalDependencies": { - "@img/sharp-libvips-linuxmusl-arm64": "1.0.4" + "@img/sharp-libvips-linuxmusl-arm64": "1.3.2" } }, "node_modules/@img/sharp-linuxmusl-x64": { - "version": "0.33.5", - "resolved": "https://registry.npmjs.org/@img/sharp-linuxmusl-x64/-/sharp-linuxmusl-x64-0.33.5.tgz", - "integrity": "sha512-WT+d/cgqKkkKySYmqoZ8y3pxx7lx9vVejxW/W4DOFMYVSkErR+w7mf2u8m/y4+xHe7yY9DAXQMWQhpnMuFfScw==", + "version": "0.35.3", + "resolved": "https://registry.npmjs.org/@img/sharp-linuxmusl-x64/-/sharp-linuxmusl-x64-0.35.3.tgz", + "integrity": "sha512-6O1NPKcDVj9QEdg7Hx549EX8U0rp6yXQERqru6yRN7fGBn32UvIRJUlWnk+8xDCiG76hXVBbX82NZ/ZKr0euIg==", "cpu": [ "x64" ], @@ -2911,39 +3021,87 @@ "linux" ], "engines": { - "node": "^18.17.0 || ^20.3.0 || >=21.0.0" + "node": ">=20.9.0" }, "funding": { "url": "https://opencollective.com/libvips" }, "optionalDependencies": { - "@img/sharp-libvips-linuxmusl-x64": "1.0.4" + "@img/sharp-libvips-linuxmusl-x64": "1.3.2" } }, "node_modules/@img/sharp-wasm32": { - "version": "0.33.5", - "resolved": "https://registry.npmjs.org/@img/sharp-wasm32/-/sharp-wasm32-0.33.5.tgz", - "integrity": "sha512-ykUW4LVGaMcU9lu9thv85CbRMAwfeadCJHRsg2GmeRa/cJxsVY9Rbd57JcMxBkKHag5U/x7TSBpScF4U8ElVzg==", + "version": "0.35.3", + "resolved": "https://registry.npmjs.org/@img/sharp-wasm32/-/sharp-wasm32-0.35.3.tgz", + "integrity": "sha512-cZ0XkcYGpHZkqW6iCkqTcmUC0CD9DhD5d/qeZlZkfRBn6GnHniZXLUo5+9xw8Iv76YE6LQFN9YNBlKREcCG76w==", + "dev": true, + "license": "Apache-2.0 AND LGPL-3.0-or-later AND MIT", + "optional": true, + "dependencies": { + "@emnapi/runtime": "^1.11.1" + }, + "engines": { + "node": ">=20.9.0" + }, + "funding": { + "url": "https://opencollective.com/libvips" + } + }, + "node_modules/@img/sharp-wasm32/node_modules/@emnapi/runtime": { + "version": "1.11.3", + "resolved": "https://registry.npmjs.org/@emnapi/runtime/-/runtime-1.11.3.tgz", + "integrity": "sha512-Xz4Tpyki7XyrpbUK1jR1AhdAdaXyhhY4lZ3neLodmhpuWfy2PAQN5B46sAiU4liOXGLkHypn/qU+jvfWSCYYLA==", + "dev": true, + "license": "MIT", + "optional": true, + "dependencies": { + "tslib": "^2.4.0" + } + }, + "node_modules/@img/sharp-webcontainers-wasm32": { + "version": "0.35.3", + "resolved": "https://registry.npmjs.org/@img/sharp-webcontainers-wasm32/-/sharp-webcontainers-wasm32-0.35.3.tgz", + "integrity": "sha512-2rnq7bX3NzeR2T4YWgz8qiG4h3TSdMe+vN1iQXpJleSJ3SM5zQ8Fy2SyyXAWlbxpEZ2Y+Z4u1BePgJEYbSy80Q==", "cpu": [ "wasm32" ], "dev": true, - "license": "Apache-2.0 AND LGPL-3.0-or-later AND MIT", + "license": "Apache-2.0", "optional": true, "dependencies": { - "@emnapi/runtime": "^1.2.0" + "@img/sharp-wasm32": "0.35.3" }, "engines": { - "node": "^18.17.0 || ^20.3.0 || >=21.0.0" + "node": ">=20.9.0" + }, + "funding": { + "url": "https://opencollective.com/libvips" + } + }, + "node_modules/@img/sharp-win32-arm64": { + "version": "0.35.3", + "resolved": "https://registry.npmjs.org/@img/sharp-win32-arm64/-/sharp-win32-arm64-0.35.3.tgz", + "integrity": "sha512-4bPwFdMbeC4JQ8L8LOyWp6nsHcboP5fxkp6iPOXz2Vg49R42TuMs2whkJ5OAP4/Ul035qOzy0AecOF9VOscn4w==", + "cpu": [ + "arm64" + ], + "dev": true, + "license": "Apache-2.0 AND LGPL-3.0-or-later", + "optional": true, + "os": [ + "win32" + ], + "engines": { + "node": ">=20.9.0" }, "funding": { "url": "https://opencollective.com/libvips" } }, "node_modules/@img/sharp-win32-ia32": { - "version": "0.33.5", - "resolved": "https://registry.npmjs.org/@img/sharp-win32-ia32/-/sharp-win32-ia32-0.33.5.tgz", - "integrity": "sha512-T36PblLaTwuVJ/zw/LaH0PdZkRz5rd3SmMHX8GSmR7vtNSP5Z6bQkExdSK7xGWyxLw4sUknBuugTelgw2faBbQ==", + "version": "0.35.3", + "resolved": "https://registry.npmjs.org/@img/sharp-win32-ia32/-/sharp-win32-ia32-0.35.3.tgz", + "integrity": "sha512-r53mXsBN6lFUDiST764SvgwUdHAqM4rPAiDzAmf4fLoB6X/rkfyTrLCg6+g17wJJiCmB3JYgHuUldCWUIRFSXw==", "cpu": [ "ia32" ], @@ -2954,16 +3112,16 @@ "win32" ], "engines": { - "node": "^18.17.0 || ^20.3.0 || >=21.0.0" + "node": "^20.9.0" }, "funding": { "url": "https://opencollective.com/libvips" } }, "node_modules/@img/sharp-win32-x64": { - "version": "0.33.5", - "resolved": "https://registry.npmjs.org/@img/sharp-win32-x64/-/sharp-win32-x64-0.33.5.tgz", - "integrity": "sha512-MpY/o8/8kj+EcnxwvrP4aTJSWw/aZ7JIGR4aBeZkZw5B7/Jn+tY9/VNwtcoGmdT7GfggGIU4kygOMSbYnOrAbg==", + "version": "0.35.3", + "resolved": "https://registry.npmjs.org/@img/sharp-win32-x64/-/sharp-win32-x64-0.35.3.tgz", + "integrity": "sha512-D4y1vNeZrIIJCN+uHaWVtH86B+aCrdMYYjicy9pXHvbGZeGYLLSd3wdVuC37FxVXlU1ARsk84eKWfWMXGYEqvA==", "cpu": [ "x64" ], @@ -2974,7 +3132,7 @@ "win32" ], "engines": { - "node": "^18.17.0 || ^20.3.0 || >=21.0.0" + "node": ">=20.9.0" }, "funding": { "url": "https://opencollective.com/libvips" @@ -3103,13 +3261,13 @@ } }, "node_modules/@modelcontextprotocol/sdk": { - "version": "1.26.0", - "resolved": "https://registry.npmjs.org/@modelcontextprotocol/sdk/-/sdk-1.26.0.tgz", - "integrity": "sha512-Y5RmPncpiDtTXDbLKswIJzTqu2hyBKxTNsgKqKclDbhIgg1wgtf1fRuvxgTnRfcnxtvvgbIEcqUOzZrJ6iSReg==", + "version": "1.30.0", + "resolved": "https://registry.npmjs.org/@modelcontextprotocol/sdk/-/sdk-1.30.0.tgz", + "integrity": "sha512-xKd8OIzlqNzcqcNumGAa6g+PW2kjD5vrpcKOnfldAUPP3j7lnqMPwlTXQm8gF+UwH72z0lqaRbjr9hqGz0eITA==", "dev": true, "license": "MIT", "dependencies": { - "@hono/node-server": "^1.19.9", + "@hono/node-server": "^1.19.9 || ^2.0.5", "ajv": "^8.17.1", "ajv-formats": "^3.0.1", "content-type": "^1.0.5", @@ -4908,9 +5066,9 @@ "license": "MIT" }, "node_modules/@storybook/addon-a11y": { - "version": "10.2.4", - "resolved": "https://registry.npmjs.org/@storybook/addon-a11y/-/addon-a11y-10.2.4.tgz", - "integrity": "sha512-VGhdZ+iP2l/CSulIKV2kt3SMWVHntOigqWqGkNYf6YNYofynUYEKdsNqBvHx4ySuNEl/eXJ8LRO8FKYnU7LxZQ==", + "version": "10.5.6", + "resolved": "https://registry.npmjs.org/@storybook/addon-a11y/-/addon-a11y-10.5.6.tgz", + "integrity": "sha512-pMqbmtvkIgb7/kVE2BTNovGhSerRXWsVag62zpwQe0SwYYkgN+1Q9h4TYuIe2+npGkxgwALCjwtqkcnpOoND+A==", "dev": true, "license": "MIT", "dependencies": { @@ -4922,20 +5080,20 @@ "url": "https://opencollective.com/storybook" }, "peerDependencies": { - "storybook": "^10.2.4" + "storybook": "^10.5.6" } }, "node_modules/@storybook/addon-docs": { - "version": "10.2.4", - "resolved": "https://registry.npmjs.org/@storybook/addon-docs/-/addon-docs-10.2.4.tgz", - "integrity": "sha512-FzscAmdBiOGnGrxiEM+8eTg43kjqgjLfObg+lbJVRR/a0DmZ3xfAPNB0+VKYQbN0FacNcWLM9LZ/7U0hRBPBnQ==", + "version": "10.5.6", + "resolved": "https://registry.npmjs.org/@storybook/addon-docs/-/addon-docs-10.5.6.tgz", + "integrity": "sha512-zyUJBrrpC9NTrmsREaVFNr+9WW6pikJtmRvo7GgZGqthEyhjQKSarHrW0aNWkwae2ep3jp1CZi8vIUVG1Dnp0w==", "dev": true, "license": "MIT", "dependencies": { "@mdx-js/react": "^3.0.0", - "@storybook/csf-plugin": "10.2.4", - "@storybook/icons": "^2.0.1", - "@storybook/react-dom-shim": "10.2.4", + "@storybook/csf-plugin": "10.5.6", + "@storybook/icons": "^2.0.2", + "@storybook/react-dom-shim": "10.5.6", "react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0", "react-dom": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0", "ts-dedent": "^2.0.0" @@ -4945,13 +5103,43 @@ "url": "https://opencollective.com/storybook" }, "peerDependencies": { - "storybook": "^10.2.4" + "@types/react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0", + "storybook": "^10.5.6" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + } + } + }, + "node_modules/@storybook/addon-mcp": { + "version": "0.7.0", + "resolved": "https://registry.npmjs.org/@storybook/addon-mcp/-/addon-mcp-0.7.0.tgz", + "integrity": "sha512-f/IWGRMzWynBg5kDJ3DYvvnafuSX88kykGNFzzLOlkLVpfxEZoAmQF6AS47tw25GuH6EFIqSo6ZDBLHLVyZ/IQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "@storybook/mcp": "0.8.0", + "@tmcp/adapter-valibot": "^0.1.5", + "@tmcp/transport-http": "^0.8.5", + "picoquery": "^2.5.0", + "tmcp": "^1.19.4", + "valibot": "1.2.0" + }, + "peerDependencies": { + "@storybook/addon-vitest": "^0.0.0-0 || ^9.1.16 || ^10.0.0 || ^10.1.0-0 || ^10.2.0-0 || ^10.3.0-0 || ^10.4.0-0 || ^10.5.0-0", + "storybook": "^0.0.0-0 || ^9.1.16 || ^10.0.0 || ^10.1.0-0 || ^10.2.0-0 || ^10.3.0-0 || ^10.4.0-0 || ^10.5.0-0" + }, + "peerDependenciesMeta": { + "@storybook/addon-vitest": { + "optional": true + } } }, "node_modules/@storybook/addon-svelte-csf": { - "version": "5.0.10", - "resolved": "https://registry.npmjs.org/@storybook/addon-svelte-csf/-/addon-svelte-csf-5.0.10.tgz", - "integrity": "sha512-poSvTS7VdaQ42ZoqW5e4+2Hv1iLO0mekH9fwn/QuBNse48R4WlTyR8XFbHRTfatl9gdc9ZYC4uWzazrmV6zGIA==", + "version": "5.1.2", + "resolved": "https://registry.npmjs.org/@storybook/addon-svelte-csf/-/addon-svelte-csf-5.1.2.tgz", + "integrity": "sha512-NpImknEb48J7yr/ArTYpvhDSvGUrgm5Nuybu9PCicjSKTACsXX7cln2R19572ORtns399RTE+t20BBOKxSPm2g==", "dev": true, "license": "MIT", "dependencies": { @@ -4964,22 +5152,22 @@ "zimmerframe": "^1.1.2" }, "peerDependencies": { - "@storybook/svelte": "^0.0.0-0 || ^8.2.0 || ^9.0.0 || ^9.1.0-0 || ^10.0.0-0", - "@sveltejs/vite-plugin-svelte": "^4.0.0 || ^5.0.0 || ^6.0.0", - "storybook": "^0.0.0-0 || ^8.2.0 || ^9.0.0 || ^9.1.0-0 || ^10.0.0-0", + "@storybook/svelte": "^0.0.0-0 || ^8.2.0 || ^9.0.0 || ^9.1.0-0 || ^10.0.0-0 || ^10.1.0-0 || ^10.2.0-0 || ^10.3.0-0 || ^10.4.0-0", + "@sveltejs/vite-plugin-svelte": "^4.0.0 || ^5.0.0 || ^6.0.0 || ^7.0.0", + "storybook": "^0.0.0-0 || ^8.2.0 || ^9.0.0 || ^9.1.0-0 || ^10.0.0-0 || ^10.1.0-0 || ^10.2.0-0 || ^10.3.0-0 || ^10.4.0-0", "svelte": "^5.0.0", - "vite": "^5.0.0 || ^6.0.0 || ^7.0.0" + "vite": "^5.0.0 || ^6.0.0 || ^7.0.0 || ^8.0.0" } }, "node_modules/@storybook/addon-vitest": { - "version": "10.2.4", - "resolved": "https://registry.npmjs.org/@storybook/addon-vitest/-/addon-vitest-10.2.4.tgz", - "integrity": "sha512-BT1iP89U4wcbpzTURU8WYTAeUcdNh4WIt0BqsnATmMwR/jKNJW6QgXCVqGQTSpRjWj40hX5e2JkQYCNXdjKsPw==", + "version": "10.5.6", + "resolved": "https://registry.npmjs.org/@storybook/addon-vitest/-/addon-vitest-10.5.6.tgz", + "integrity": "sha512-oxq7Qi4Vujc8Etoi1TZBurMs4RiKoGnvAOCXePOLglXSJMpy95gEb7iu/hvj8E21lV+vVtQYmFvj9Z7gJeMtdg==", "dev": true, "license": "MIT", "dependencies": { "@storybook/global": "^5.0.0", - "@storybook/icons": "^2.0.1" + "@storybook/icons": "^2.0.2" }, "funding": { "type": "opencollective", @@ -4989,7 +5177,7 @@ "@vitest/browser": "^3.0.0 || ^4.0.0", "@vitest/browser-playwright": "^4.0.0", "@vitest/runner": "^3.0.0 || ^4.0.0", - "storybook": "^10.2.4", + "storybook": "^10.5.6", "vitest": "^3.0.0 || ^4.0.0" }, "peerDependenciesMeta": { @@ -5008,13 +5196,13 @@ } }, "node_modules/@storybook/builder-vite": { - "version": "10.2.4", - "resolved": "https://registry.npmjs.org/@storybook/builder-vite/-/builder-vite-10.2.4.tgz", - "integrity": "sha512-/hcT1xj3CL5GkJ5v5/EguZdttDwNE6weNXK7vKzp034tnGcLycOossDsTiUQkBowSL+Ylc8aKj+ZgvddPNfOig==", + "version": "10.5.6", + "resolved": "https://registry.npmjs.org/@storybook/builder-vite/-/builder-vite-10.5.6.tgz", + "integrity": "sha512-Ts8EohKPj8okDPCkueeKVN+IRGNpI3LuddsFGupqraRvK6aRWawDKA28uc0PlsLCLWbMkMsGVw+IpFXfmoLJgQ==", "dev": true, "license": "MIT", "dependencies": { - "@storybook/csf-plugin": "10.2.4", + "@storybook/csf-plugin": "10.5.6", "ts-dedent": "^2.0.0" }, "funding": { @@ -5022,8 +5210,8 @@ "url": "https://opencollective.com/storybook" }, "peerDependencies": { - "storybook": "^10.2.4", - "vite": "^5.0.0 || ^6.0.0 || ^7.0.0" + "storybook": "^10.5.6", + "vite": "^5.0.0 || ^6.0.0 || ^7.0.0 || ^8.0.0" } }, "node_modules/@storybook/csf": { @@ -5037,9 +5225,9 @@ } }, "node_modules/@storybook/csf-plugin": { - "version": "10.2.4", - "resolved": "https://registry.npmjs.org/@storybook/csf-plugin/-/csf-plugin-10.2.4.tgz", - "integrity": "sha512-kupPQEV+4N9mzsZHYaokvhO/KHBjYdWda9PNmPQwy0TR7r2mzthgaNH72TjmgN1L6DIbsuyOG1wtczcPJn4+Jg==", + "version": "10.5.6", + "resolved": "https://registry.npmjs.org/@storybook/csf-plugin/-/csf-plugin-10.5.6.tgz", + "integrity": "sha512-PJLyOmcKe1OZDBw7RaGX/gjuiJuVfS5pVgc4W2RnHYOFpU6F5Bv9+9MqQwp0i7tWZBWc4fsCJudgVqwgjuTROA==", "dev": true, "license": "MIT", "dependencies": { @@ -5052,7 +5240,7 @@ "peerDependencies": { "esbuild": "*", "rollup": "*", - "storybook": "^10.2.4", + "storybook": "^10.5.6", "vite": "*", "webpack": "*" }, @@ -5089,10 +5277,23 @@ "react-dom": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0" } }, + "node_modules/@storybook/mcp": { + "version": "0.8.0", + "resolved": "https://registry.npmjs.org/@storybook/mcp/-/mcp-0.8.0.tgz", + "integrity": "sha512-G+XDgoWGrE98moXqKSee8fQyMQxoIWxRAbPG8r/HQ95pKodratevDqNyOgW+t6ZigM6AAVN1WHiFc5MI+hc8sg==", + "dev": true, + "license": "MIT", + "dependencies": { + "@tmcp/adapter-valibot": "^0.1.5", + "@tmcp/transport-http": "^0.8.5", + "tmcp": "^1.19.4", + "valibot": "1.2.0" + } + }, "node_modules/@storybook/react-dom-shim": { - "version": "10.2.4", - "resolved": "https://registry.npmjs.org/@storybook/react-dom-shim/-/react-dom-shim-10.2.4.tgz", - "integrity": "sha512-i22OtrZ7GeZPt/odLf0vqyDhRSKyaLsHkkKSBcANQfzRRnBZmiz2FchOtWm9uvoDWybQsTruZq7kTdtpEhwyGw==", + "version": "10.5.6", + "resolved": "https://registry.npmjs.org/@storybook/react-dom-shim/-/react-dom-shim-10.5.6.tgz", + "integrity": "sha512-dV3oOHc5ImggxEqeIiUj4vvnQO5SKScFtqAkxgIWLju1wiSZSIqQ5Q4Mp12Rhs9hQrjF039DueH7f2xJJZfvSw==", "dev": true, "license": "MIT", "funding": { @@ -5100,73 +5301,99 @@ "url": "https://opencollective.com/storybook" }, "peerDependencies": { + "@types/react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0", + "@types/react-dom": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0", "react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0", "react-dom": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0", - "storybook": "^10.2.4" + "storybook": "^10.5.6" + }, + "peerDependenciesMeta": { + "@types/react": { + "optional": true + }, + "@types/react-dom": { + "optional": true + } } }, "node_modules/@storybook/svelte": { - "version": "10.2.4", - "resolved": "https://registry.npmjs.org/@storybook/svelte/-/svelte-10.2.4.tgz", - "integrity": "sha512-W9R51zUCd2iHOQBg/D93+bdpYv6kbtFx+kft5X8lPKQl6yEu0aKs9i5N5GyCASOhIApgx/tkqZIJ7vgM4cqrHA==", + "version": "10.5.6", + "resolved": "https://registry.npmjs.org/@storybook/svelte/-/svelte-10.5.6.tgz", + "integrity": "sha512-dx95/i86Lvif3wJZvMIWa/FnnyRljdIbDYicdBitbqS3SBldX6EE9DhYEY/e3ELEbRHMhsIANKoP2rzxs5xjVw==", "dev": true, "license": "MIT", "dependencies": { "ts-dedent": "^2.0.0", - "type-fest": "~2.19" + "type-fest": "^5.6.0" }, "funding": { "type": "opencollective", "url": "https://opencollective.com/storybook" }, "peerDependencies": { - "storybook": "^10.2.4", + "storybook": "^10.5.6", "svelte": "^5.0.0" } }, - "node_modules/@storybook/svelte-vite": { - "version": "10.2.4", - "resolved": "https://registry.npmjs.org/@storybook/svelte-vite/-/svelte-vite-10.2.4.tgz", - "integrity": "sha512-FMgKMRdoZFDwPD6eIDMldcgp6d6NtIGuXyUJjb29qLias/gE5TI6hg+cWmmWXQRTrXwdyepeMBmIfRcZbB6REQ==", + "node_modules/@storybook/svelte/node_modules/type-fest": { + "version": "5.8.0", + "resolved": "https://registry.npmjs.org/type-fest/-/type-fest-5.8.0.tgz", + "integrity": "sha512-YGYEVz3Fm5iy/AybuA0oyNFq7H4CgQNfRp/qfe8nurE1kuCeNm3/vfm9X4Mtl+qLyaKJUh5xrFZwogr41SMjYA==", + "dev": true, + "license": "(MIT OR CC0-1.0)", + "dependencies": { + "tagged-tag": "^1.0.0" + }, + "engines": { + "node": ">=20" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, + "node_modules/@storybook/sveltekit": { + "version": "10.5.6", + "resolved": "https://registry.npmjs.org/@storybook/sveltekit/-/sveltekit-10.5.6.tgz", + "integrity": "sha512-dwQb4B4zLitoQvQUpuudEjbnHAVc3/a0ZzvounwloJINGAmFvTp/fz4F5wHvh5a0vXFK/QT6VSpF3+CcKFqYDw==", "dev": true, "license": "MIT", "dependencies": { - "@storybook/builder-vite": "10.2.4", - "@storybook/svelte": "10.2.4", - "magic-string": "^0.30.0", - "svelte2tsx": "^0.7.44", - "typescript": "^4.9.4 || ^5.0.0" + "@storybook/builder-vite": "10.5.6", + "@storybook/svelte": "10.5.6", + "@storybook/svelte-vite": "10.5.6" }, "funding": { "type": "opencollective", "url": "https://opencollective.com/storybook" }, "peerDependencies": { - "@sveltejs/vite-plugin-svelte": "^2.0.0 || ^3.0.0 || ^4.0.0 || ^5.0.0 || ^6.0.0", - "storybook": "^10.2.4", + "storybook": "^10.5.6", "svelte": "^5.0.0", - "vite": "^5.0.0 || ^6.0.0 || ^7.0.0" + "vite": "^5.0.0 || ^6.0.0 || ^7.0.0 || ^8.0.0" } }, - "node_modules/@storybook/sveltekit": { - "version": "10.2.4", - "resolved": "https://registry.npmjs.org/@storybook/sveltekit/-/sveltekit-10.2.4.tgz", - "integrity": "sha512-1qDX35iSJHWo1AOd7HMzJtCHBfgahXqTWNiyZa/JMEKJ3qC1otaU8XMmTjsZ6fCRF99piNdgqtWM8+s1TJOldg==", + "node_modules/@storybook/sveltekit/node_modules/@storybook/svelte-vite": { + "version": "10.5.6", + "resolved": "https://registry.npmjs.org/@storybook/svelte-vite/-/svelte-vite-10.5.6.tgz", + "integrity": "sha512-jMmCOvOJ3VL7ee0258nbqrnRBT7e0kFjimnwe7MGUz1HnmOHvH7gUlcZXGh79kb8kkFjJJ6x4ZPHNK689IndNQ==", "dev": true, "license": "MIT", "dependencies": { - "@storybook/builder-vite": "10.2.4", - "@storybook/svelte": "10.2.4", - "@storybook/svelte-vite": "10.2.4" + "@storybook/builder-vite": "10.5.6", + "@storybook/svelte": "10.5.6", + "magic-string": "^0.30.0", + "svelte2tsx": "^0.7.55", + "typescript": "^4.9.4 || ^5.0.0" }, "funding": { "type": "opencollective", "url": "https://opencollective.com/storybook" }, "peerDependencies": { - "storybook": "^10.2.4", + "@sveltejs/vite-plugin-svelte": "^2.0.0 || ^3.0.0 || ^4.0.0 || ^5.0.0 || ^6.0.0 || ^7.0.0", + "storybook": "^10.5.6", "svelte": "^5.0.0", - "vite": "^5.0.0 || ^6.0.0 || ^7.0.0" + "vite": "^5.0.0 || ^6.0.0 || ^7.0.0 || ^8.0.0" } }, "node_modules/@sveltejs/acorn-typescript": { @@ -5190,16 +5417,16 @@ } }, "node_modules/@sveltejs/kit": { - "version": "2.60.1", - "resolved": "https://registry.npmjs.org/@sveltejs/kit/-/kit-2.60.1.tgz", - "integrity": "sha512-mQjlkNo+rJvpln7V2IGY2j99BqhcFbS4UN0AQNKNYfhBAFZTuCDAdW3a1sgf330mvtNvsBXn3HpAhcmvdJTcIQ==", + "version": "2.70.2", + "resolved": "https://registry.npmjs.org/@sveltejs/kit/-/kit-2.70.2.tgz", + "integrity": "sha512-RzRoRpuR2KXqc5yMO0akQHDZeT4AslOlznGITURsqHaVbtyYP4Wn3eE3gxj9JcDyNYO0crkxhdwFHc+2vkVm6w==", "dev": true, "license": "MIT", "dependencies": { "@standard-schema/spec": "^1.0.0", - "@sveltejs/acorn-typescript": "^1.0.5", + "@sveltejs/acorn-typescript": "^1.0.9", "@types/cookie": "^0.6.0", - "acorn": "^8.14.1", + "acorn": "^8.16.0", "cookie": "^0.6.0", "devalue": "^5.8.1", "esm-env": "^1.2.2", @@ -5616,7 +5843,6 @@ "integrity": "sha512-o4PXJQidqJl82ckFaXUeoAW+XysPLauYI43Abki5hABd853iMhitooc6znOnczgbTYmEP6U6/y1ZyKAIsvMKGg==", "dev": true, "license": "MIT", - "peer": true, "dependencies": { "@babel/code-frame": "^7.10.4", "@babel/runtime": "^7.12.5", @@ -5685,6 +5911,62 @@ "@testing-library/dom": ">=7.21.4" } }, + "node_modules/@tmcp/adapter-valibot": { + "version": "0.1.6", + "resolved": "https://registry.npmjs.org/@tmcp/adapter-valibot/-/adapter-valibot-0.1.6.tgz", + "integrity": "sha512-drirZeNinhYLiRSMksN+m//u0ImFxtGRk1Vp425Xp/7CbBXFQdjAG+f7grssyHAukbVTGzmWsMMP6ejrGVErUA==", + "dev": true, + "license": "MIT", + "dependencies": { + "@standard-schema/spec": "^1.0.0", + "@valibot/to-json-schema": "^1.3.0", + "valibot": "^1.1.0" + }, + "peerDependencies": { + "tmcp": "^1.17.0", + "valibot": "^1.1.0" + } + }, + "node_modules/@tmcp/adapter-valibot/node_modules/@valibot/to-json-schema": { + "version": "1.7.1", + "resolved": "https://registry.npmjs.org/@valibot/to-json-schema/-/to-json-schema-1.7.1.tgz", + "integrity": "sha512-3qkmU6KXWh8GIThEAW3kuRHPQBMjWkKy+Ppz3WkUucx53DTpOa6siMn4xDGSOhlVyMrDaJTCTMLYPZVAIk1P0A==", + "dev": true, + "license": "MIT", + "peerDependencies": { + "valibot": "^1.4.0" + } + }, + "node_modules/@tmcp/session-manager": { + "version": "0.2.2", + "resolved": "https://registry.npmjs.org/@tmcp/session-manager/-/session-manager-0.2.2.tgz", + "integrity": "sha512-UrCRpTsxh5XnMbplspvftEYboiZWgAiXqqAUbyFTHoHMJ0LoNDy8bQd0+7qtxtT4S5Qsnv650gvs/Nbec5NTCQ==", + "dev": true, + "license": "MIT", + "peerDependencies": { + "tmcp": "^1.16.3" + } + }, + "node_modules/@tmcp/transport-http": { + "version": "0.8.6", + "resolved": "https://registry.npmjs.org/@tmcp/transport-http/-/transport-http-0.8.6.tgz", + "integrity": "sha512-iLcxu+tEMbkVHbhFfyXQhxfPDDTfm+F0kEw8Xg/a1rm29s4cBg1vwcpbtk02XTxsdDh8RJ1AZkQwF9WDGeb/IA==", + "dev": true, + "license": "MIT", + "dependencies": { + "@tmcp/session-manager": "^0.2.2", + "esm-env": "^1.2.2" + }, + "peerDependencies": { + "@tmcp/auth": "^0.3.3 || ^0.4.0", + "tmcp": "^1.18.0" + }, + "peerDependenciesMeta": { + "@tmcp/auth": { + "optional": true + } + } + }, "node_modules/@trickfilm400/rollup-plugin-off-main-thread": { "version": "3.0.0-pre1", "resolved": "https://registry.npmjs.org/@trickfilm400/rollup-plugin-off-main-thread/-/rollup-plugin-off-main-thread-3.0.0-pre1.tgz", @@ -5717,8 +5999,7 @@ "resolved": "https://registry.npmjs.org/@types/aria-query/-/aria-query-5.0.4.tgz", "integrity": "sha512-rfT93uj5s0PRL7EzccGMs3brplhcrghnDoV26NqKhCAS1hVo+WdNsPvE/yb6ilfr5hi2MEk6d5EWJTKdxg8jVw==", "dev": true, - "license": "MIT", - "peer": true + "license": "MIT" }, "node_modules/@types/chai": { "version": "5.2.3", @@ -6342,16 +6623,16 @@ } }, "node_modules/@typescript-eslint/typescript-estree/node_modules/brace-expansion": { - "version": "5.0.6", - "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.6.tgz", - "integrity": "sha512-kLpxurY4Z4r9sgMsyG0Z9uzsBlgiU/EFKhj/h91/8yHu0edo7XuixOIH3VcJ8kkxs6/jPzoI6U9Vj3WqbMQ94g==", + "version": "5.0.9", + "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.9.tgz", + "integrity": "sha512-ScQ4IuvIEF1TMlP7Zt+vjJ//9zlPb2SDcxWxM3bk8s6t6GGdJ7KO1dCcTidOPJKePW30LE/2cT7wCyPho9/Wxg==", "dev": true, "license": "MIT", "dependencies": { "balanced-match": "^4.0.2" }, "engines": { - "node": "18 || 20 || >=22" + "node": "20 || >=22" } }, "node_modules/@typescript-eslint/typescript-estree/node_modules/minimatch": { @@ -6495,15 +6776,15 @@ } }, "node_modules/@vitest/browser": { - "version": "4.1.8", - "resolved": "https://registry.npmjs.org/@vitest/browser/-/browser-4.1.8.tgz", - "integrity": "sha512-u21VzX07HzlJYpFgkxmjEXar/tG2UqWGgyGG/46SrrPc7rSdCTPw5vuowopO9CIqF8UCUQzDFdbVnNpw6N0BfQ==", + "version": "4.1.10", + "resolved": "https://registry.npmjs.org/@vitest/browser/-/browser-4.1.10.tgz", + "integrity": "sha512-UDwuWGwXj646CBx/bQHOaJSX7np0I8JL/UKQYa1e4QrVHH8VdWtx8eaOuf8sy0ShwDgR6NjJAsp5eF6vjF6qng==", "dev": true, "license": "MIT", "dependencies": { "@blazediff/core": "1.9.1", - "@vitest/mocker": "4.1.8", - "@vitest/utils": "4.1.8", + "@vitest/mocker": "4.1.10", + "@vitest/utils": "4.1.10", "magic-string": "^0.30.21", "pngjs": "^7.0.0", "sirv": "^3.0.2", @@ -6514,18 +6795,18 @@ "url": "https://opencollective.com/vitest" }, "peerDependencies": { - "vitest": "4.1.8" + "vitest": "4.1.10" } }, "node_modules/@vitest/browser-playwright": { - "version": "4.1.8", - "resolved": "https://registry.npmjs.org/@vitest/browser-playwright/-/browser-playwright-4.1.8.tgz", - "integrity": "sha512-SR7FqgegaexEg73xvf3ArtygXegagMdXnL0EZMpxrWvvhQxvicD/E8p0ib0J91riPRtQUViyh67Xjw3NqvyhVg==", + "version": "4.1.10", + "resolved": "https://registry.npmjs.org/@vitest/browser-playwright/-/browser-playwright-4.1.10.tgz", + "integrity": "sha512-nMoXGEiRpT7m3W7NsbvrM2aKNwiNHZf+zEpUCvMteGjZFvfT96Q9fh7QyB98dvDWXiKvrLxA7bJ1mCOOv+JQPw==", "dev": true, "license": "MIT", "dependencies": { - "@vitest/browser": "4.1.8", - "@vitest/mocker": "4.1.8", + "@vitest/browser": "4.1.10", + "@vitest/mocker": "4.1.10", "tinyrainbow": "^3.1.0" }, "funding": { @@ -6533,7 +6814,7 @@ }, "peerDependencies": { "playwright": "*", - "vitest": "4.1.8" + "vitest": "4.1.10" }, "peerDependenciesMeta": { "playwright": { @@ -6541,35 +6822,15 @@ } } }, - "node_modules/@vitest/browser-playwright/node_modules/tinyrainbow": { - "version": "3.1.0", - "resolved": "https://registry.npmjs.org/tinyrainbow/-/tinyrainbow-3.1.0.tgz", - "integrity": "sha512-Bf+ILmBgretUrdJxzXM0SgXLZ3XfiaUuOj/IKQHuTXip+05Xn+uyEYdVg0kYDipTBcLrCVyUzAPz7QmArb0mmw==", - "dev": true, - "license": "MIT", - "engines": { - "node": ">=14.0.0" - } - }, - "node_modules/@vitest/browser/node_modules/tinyrainbow": { - "version": "3.1.0", - "resolved": "https://registry.npmjs.org/tinyrainbow/-/tinyrainbow-3.1.0.tgz", - "integrity": "sha512-Bf+ILmBgretUrdJxzXM0SgXLZ3XfiaUuOj/IKQHuTXip+05Xn+uyEYdVg0kYDipTBcLrCVyUzAPz7QmArb0mmw==", - "dev": true, - "license": "MIT", - "engines": { - "node": ">=14.0.0" - } - }, "node_modules/@vitest/coverage-v8": { - "version": "4.1.8", - "resolved": "https://registry.npmjs.org/@vitest/coverage-v8/-/coverage-v8-4.1.8.tgz", - "integrity": "sha512-lt3kovsyHwYe00wq4D1ti0Z974fWj4NLp6siqiyEufUpyFwK9Yhi7rBhac9JL5aA0zoMrJqc4vYPZRUnI7l7nw==", + "version": "4.1.10", + "resolved": "https://registry.npmjs.org/@vitest/coverage-v8/-/coverage-v8-4.1.10.tgz", + "integrity": "sha512-IM49HmthevbgAO4anp1hwtoT9wYe59w0LR00gr+eagHE+ZJ5lK4sLPeO0ubgoJcwLk6dehU3R24N+FbEEKDc8g==", "dev": true, "license": "MIT", "dependencies": { "@bcoe/v8-coverage": "^1.0.2", - "@vitest/utils": "4.1.8", + "@vitest/utils": "4.1.10", "ast-v8-to-istanbul": "^1.0.0", "istanbul-lib-coverage": "^3.2.2", "istanbul-lib-report": "^3.0.1", @@ -6583,8 +6844,8 @@ "url": "https://opencollective.com/vitest" }, "peerDependencies": { - "@vitest/browser": "4.1.8", - "vitest": "4.1.8" + "@vitest/browser": "4.1.10", + "vitest": "4.1.10" }, "peerDependenciesMeta": { "@vitest/browser": { @@ -6592,16 +6853,6 @@ } } }, - "node_modules/@vitest/coverage-v8/node_modules/tinyrainbow": { - "version": "3.1.0", - "resolved": "https://registry.npmjs.org/tinyrainbow/-/tinyrainbow-3.1.0.tgz", - "integrity": "sha512-Bf+ILmBgretUrdJxzXM0SgXLZ3XfiaUuOj/IKQHuTXip+05Xn+uyEYdVg0kYDipTBcLrCVyUzAPz7QmArb0mmw==", - "dev": true, - "license": "MIT", - "engines": { - "node": ">=14.0.0" - } - }, "node_modules/@vitest/expect": { "version": "3.2.4", "resolved": "https://registry.npmjs.org/@vitest/expect/-/expect-3.2.4.tgz", @@ -6660,14 +6911,24 @@ "url": "https://opencollective.com/vitest" } }, + "node_modules/@vitest/expect/node_modules/tinyrainbow": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/tinyrainbow/-/tinyrainbow-2.0.0.tgz", + "integrity": "sha512-op4nsTR47R6p0vMUUoYl/a+ljLFVtlfaXkLQmqfLR1qHma1h/ysYk4hEXZ880bf2CYgTskvTa/e196Vd5dDQXw==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=14.0.0" + } + }, "node_modules/@vitest/mocker": { - "version": "4.1.8", - "resolved": "https://registry.npmjs.org/@vitest/mocker/-/mocker-4.1.8.tgz", - "integrity": "sha512-LEiN/xe4OSIbKe9HQIp5OC24agGD9J5CnmMgsLohVVoOPWL9a2sBoR6VBx43jQZb7Kr1l4RCuyCJzcAa0+dojw==", + "version": "4.1.10", + "resolved": "https://registry.npmjs.org/@vitest/mocker/-/mocker-4.1.10.tgz", + "integrity": "sha512-v0xaezt+DKEmKfaxg133ldzADrwLGd7Ze1MfQQTYfvs8OqZIwbxyxaYURivwV7sWy5fqn3rH5uOrSp07bp44Ow==", "dev": true, "license": "MIT", "dependencies": { - "@vitest/spy": "4.1.8", + "@vitest/spy": "4.1.10", "estree-walker": "^3.0.3", "magic-string": "^0.30.21" }, @@ -6688,9 +6949,9 @@ } }, "node_modules/@vitest/pretty-format": { - "version": "4.1.8", - "resolved": "https://registry.npmjs.org/@vitest/pretty-format/-/pretty-format-4.1.8.tgz", - "integrity": "sha512-9GasEBxpZ1VYIpqHf/0+YGg121uSNwCKOJqIrTwWP/TB7DmFCiaBpNl3aPZzoLWfWkuqhbH8vJIVobZkvdo2cA==", + "version": "4.1.10", + "resolved": "https://registry.npmjs.org/@vitest/pretty-format/-/pretty-format-4.1.10.tgz", + "integrity": "sha512-W1HsjSH4MXQ9YfmmhLAoIYf1HRfekQCGngeIgcei6MP5QQGWUe0gkopdZQaVCFO+JDJMrAJGwa5pRpNpvy4P8Q==", "dev": true, "license": "MIT", "dependencies": { @@ -6700,24 +6961,14 @@ "url": "https://opencollective.com/vitest" } }, - "node_modules/@vitest/pretty-format/node_modules/tinyrainbow": { - "version": "3.1.0", - "resolved": "https://registry.npmjs.org/tinyrainbow/-/tinyrainbow-3.1.0.tgz", - "integrity": "sha512-Bf+ILmBgretUrdJxzXM0SgXLZ3XfiaUuOj/IKQHuTXip+05Xn+uyEYdVg0kYDipTBcLrCVyUzAPz7QmArb0mmw==", - "dev": true, - "license": "MIT", - "engines": { - "node": ">=14.0.0" - } - }, "node_modules/@vitest/runner": { - "version": "4.1.8", - "resolved": "https://registry.npmjs.org/@vitest/runner/-/runner-4.1.8.tgz", - "integrity": "sha512-EmVxeBAfMJvycdjd6Hm+RbFBbA9fKvo0Kx37hNpBYoYeavH3RNsBXWDooR1mgD52dCrxIIuP7UotpfiwOikvcg==", + "version": "4.1.10", + "resolved": "https://registry.npmjs.org/@vitest/runner/-/runner-4.1.10.tgz", + "integrity": "sha512-IKI6kpIH+LmpROplyLwBBaCfMgOZOMsygVa6BARD6ahA04VRuJSa6OaVG7kRvSEMD870Vd91rSSw0eegtWyLGg==", "dev": true, "license": "MIT", "dependencies": { - "@vitest/utils": "4.1.8", + "@vitest/utils": "4.1.10", "pathe": "^2.0.3" }, "funding": { @@ -6725,14 +6976,14 @@ } }, "node_modules/@vitest/snapshot": { - "version": "4.1.8", - "resolved": "https://registry.npmjs.org/@vitest/snapshot/-/snapshot-4.1.8.tgz", - "integrity": "sha512-acfZboRmAIf05DEKcBQy33VXojFJjtUdLyo7oOmV9kebb2xdU01UknNiPuPZoJZQyO7DF0gZdTGTpeAzET9QPQ==", + "version": "4.1.10", + "resolved": "https://registry.npmjs.org/@vitest/snapshot/-/snapshot-4.1.10.tgz", + "integrity": "sha512-xRkfOT1qpTAi/Ti4Y1LtfRc3kEuqxGw59eN2jN9pRWMtS/XDevekhcFSqvQqjUNGksfjMJu3Y+oJ+4Ypn2OaJw==", "dev": true, "license": "MIT", "dependencies": { - "@vitest/pretty-format": "4.1.8", - "@vitest/utils": "4.1.8", + "@vitest/pretty-format": "4.1.10", + "@vitest/utils": "4.1.10", "magic-string": "^0.30.21", "pathe": "^2.0.3" }, @@ -6741,9 +6992,9 @@ } }, "node_modules/@vitest/spy": { - "version": "4.1.8", - "resolved": "https://registry.npmjs.org/@vitest/spy/-/spy-4.1.8.tgz", - "integrity": "sha512-6EevtBp6OZOPF7bmz36HrGMeP3txgVSrgebWxHOafDXGkhIzfXK14f8KF6MuFfgXXUeHxmpD3BQxkV00/3s5mA==", + "version": "4.1.10", + "resolved": "https://registry.npmjs.org/@vitest/spy/-/spy-4.1.10.tgz", + "integrity": "sha512-PLf/Ugvoq5wO/b4rwYCR1h2PSIdXz7wnkQFMiUpLdtM7l6pqVFcQIBEHyT1+l+cj7mNwAfZHzqXqDyjvOuwbDw==", "dev": true, "license": "MIT", "funding": { @@ -6751,13 +7002,13 @@ } }, "node_modules/@vitest/utils": { - "version": "4.1.8", - "resolved": "https://registry.npmjs.org/@vitest/utils/-/utils-4.1.8.tgz", - "integrity": "sha512-uOJamYALNhfJ6iolExyQM40yIQwDqYnkKtQ5VCiSe17E33H0aQ/u+1GlRuz4LZBk6Mm3sg90G9hEbmEt37C1Zg==", + "version": "4.1.10", + "resolved": "https://registry.npmjs.org/@vitest/utils/-/utils-4.1.10.tgz", + "integrity": "sha512-fy9am/HWxbaGt/Sawrp90vt6Y6jQwf1RX77cz3uwoJwJVMli/e1IEwRPnMNJ7vKfPTwo0diXifkpPvwH9v7nGA==", "dev": true, "license": "MIT", "dependencies": { - "@vitest/pretty-format": "4.1.8", + "@vitest/pretty-format": "4.1.10", "convert-source-map": "^2.0.0", "tinyrainbow": "^3.1.0" }, @@ -6765,16 +7016,6 @@ "url": "https://opencollective.com/vitest" } }, - "node_modules/@vitest/utils/node_modules/tinyrainbow": { - "version": "3.1.0", - "resolved": "https://registry.npmjs.org/tinyrainbow/-/tinyrainbow-3.1.0.tgz", - "integrity": "sha512-Bf+ILmBgretUrdJxzXM0SgXLZ3XfiaUuOj/IKQHuTXip+05Xn+uyEYdVg0kYDipTBcLrCVyUzAPz7QmArb0mmw==", - "dev": true, - "license": "MIT", - "engines": { - "node": ">=14.0.0" - } - }, "node_modules/@webcontainer/env": { "version": "1.1.1", "resolved": "https://registry.npmjs.org/@webcontainer/env/-/env-1.1.1.tgz", @@ -6860,7 +7101,6 @@ "integrity": "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ==", "dev": true, "license": "MIT", - "peer": true, "engines": { "node": ">=8" } @@ -7164,21 +7404,21 @@ } }, "node_modules/body-parser": { - "version": "2.2.2", - "resolved": "https://registry.npmjs.org/body-parser/-/body-parser-2.2.2.tgz", - "integrity": "sha512-oP5VkATKlNwcgvxi0vM0p/D3n2C3EReYVX+DNYs5TjZFn/oQt2j+4sVJtSMr18pdRr8wjTcBl6LoV+FUwzPmNA==", + "version": "2.3.0", + "resolved": "https://registry.npmjs.org/body-parser/-/body-parser-2.3.0.tgz", + "integrity": "sha512-2cGmJupaNgg+QUwVLAucDuWuoMZ6EX9iHDRswZ5lsNYEmwPaRknMPCLZz07yTzVq/83p4o/wzbDZbBrTvGGTIw==", "dev": true, "license": "MIT", "dependencies": { "bytes": "^3.1.2", - "content-type": "^1.0.5", + "content-type": "^2.0.0", "debug": "^4.4.3", - "http-errors": "^2.0.0", - "iconv-lite": "^0.7.0", + "http-errors": "^2.0.1", + "iconv-lite": "^0.7.2", "on-finished": "^2.4.1", - "qs": "^6.14.1", - "raw-body": "^3.0.1", - "type-is": "^2.0.1" + "qs": "^6.15.2", + "raw-body": "^3.0.2", + "type-is": "^2.1.0" }, "engines": { "node": ">=18" @@ -7188,10 +7428,24 @@ "url": "https://opencollective.com/express" } }, + "node_modules/body-parser/node_modules/content-type": { + "version": "2.0.0", + "resolved": "https://registry.npmjs.org/content-type/-/content-type-2.0.0.tgz", + "integrity": "sha512-j/O/d7GcZCyNl7/hwZAb606rzqkyvaDctLmckbxLzHvFBzTJHuGEdodATcP3yIRoDrLHkIATJuvzbFlp/ki2cQ==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=18" + }, + "funding": { + "type": "opencollective", + "url": "https://opencollective.com/express" + } + }, "node_modules/brace-expansion": { - "version": "1.1.15", - "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.15.tgz", - "integrity": "sha512-EwOCDEex4quD37XhqM3omwtMoJjr//isUZz1JopUNWms+4Z2ViyM/k1YIRePpoVNnQhENnxtFjLaxNHrT7xIUg==", + "version": "1.1.18", + "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.18.tgz", + "integrity": "sha512-Edep/X9fGqVNmzKBVsDYIOtD+z1tuezV70LBjdCst9Tqu76lsnvRiZ6oTic1n+/BIwX6QDGAO94PN4N2SADvtw==", "dev": true, "license": "MIT", "dependencies": { @@ -7472,19 +7726,23 @@ } }, "node_modules/chromatic": { - "version": "13.3.5", - "resolved": "https://registry.npmjs.org/chromatic/-/chromatic-13.3.5.tgz", - "integrity": "sha512-MzPhxpl838qJUo0A55osCF2ifwPbjcIPeElr1d4SHcjnHoIcg7l1syJDrAYK/a+PcCBrOGi06jPNpQAln5hWgw==", + "version": "16.10.0", + "resolved": "https://registry.npmjs.org/chromatic/-/chromatic-16.10.0.tgz", + "integrity": "sha512-nFsztmnu7rFiGafUJgXvLUNpqmRylz92eNvzBoJNTKKQj4EQUyxznwnfpf1dTs7hXtWD8JwcH92jADydaHA1sw==", "dev": true, "license": "MIT", + "dependencies": { + "semver": "^7.3.5" + }, "bin": { - "chroma": "dist/bin.js", - "chromatic": "dist/bin.js", - "chromatic-cli": "dist/bin.js" + "chroma": "dist/bin.cjs", + "chromatic": "dist/bin.cjs", + "chromatic-cli": "dist/bin.cjs" }, "peerDependencies": { "@chromatic-com/cypress": "^0.*.* || ^1.0.0", - "@chromatic-com/playwright": "^0.*.* || ^1.0.0" + "@chromatic-com/playwright": "^0.*.* || ^1.0.0", + "@chromatic-com/vitest": "^0.*.* || ^1.0.0" }, "peerDependenciesMeta": { "@chromatic-com/cypress": { @@ -7492,6 +7750,9 @@ }, "@chromatic-com/playwright": { "optional": true + }, + "@chromatic-com/vitest": { + "optional": true } } }, @@ -7505,20 +7766,6 @@ "node": ">=6" } }, - "node_modules/color": { - "version": "4.2.3", - "resolved": "https://registry.npmjs.org/color/-/color-4.2.3.tgz", - "integrity": "sha512-1rXeuUUiGGrykh+CeBdu5Ie7OJwinCgQY0bc7GCRxy5xVHy+moaqkpL/jqQq0MtQOeYcrqEz4abc5f0KtU7W4A==", - "dev": true, - "license": "MIT", - "dependencies": { - "color-convert": "^2.0.1", - "color-string": "^1.9.0" - }, - "engines": { - "node": ">=12.5.0" - } - }, "node_modules/color-convert": { "version": "2.0.1", "resolved": "https://registry.npmjs.org/color-convert/-/color-convert-2.0.1.tgz", @@ -7539,17 +7786,6 @@ "dev": true, "license": "MIT" }, - "node_modules/color-string": { - "version": "1.9.1", - "resolved": "https://registry.npmjs.org/color-string/-/color-string-1.9.1.tgz", - "integrity": "sha512-shrVawQFojnZv6xM40anx4CkoDP+fZsw/ZerEMsW/pyzsRbElpsL/DBVW7q3ExxwusdNXI3lXpuhEZkzs8p5Eg==", - "dev": true, - "license": "MIT", - "dependencies": { - "color-name": "^1.0.0", - "simple-swizzle": "^0.2.2" - } - }, "node_modules/colorette": { "version": "2.0.20", "resolved": "https://registry.npmjs.org/colorette/-/colorette-2.0.20.tgz", @@ -8649,13 +8885,12 @@ "resolved": "https://registry.npmjs.org/dom-accessibility-api/-/dom-accessibility-api-0.5.16.tgz", "integrity": "sha512-X7BJ2yElsnOJ30pZF4uIIDfBEVgF4XEBxL9Bxhy6dnrm5hkzqmsWHGTiHqRiITNhMyFLyAiWndIJP7Z1NTteDg==", "dev": true, - "license": "MIT", - "peer": true + "license": "MIT" }, "node_modules/dompurify": { - "version": "3.4.11", - "resolved": "https://registry.npmjs.org/dompurify/-/dompurify-3.4.11.tgz", - "integrity": "sha512-zhlUV12GsaRzMsf9q5M254YhA4+VuF0fG+QFqu6aYpoGlKtz+w8//jBcGVYBgQkR5GHjUomejY84AV+/uPbWdw==", + "version": "3.4.13", + "resolved": "https://registry.npmjs.org/dompurify/-/dompurify-3.4.13.tgz", + "integrity": "sha512-2vmYIoqjze2d+kakP8S/nS5shfsl587kzwEjcGlTdiksUVgFHnFCsLYDVj/JNqJVOQZGSYBTmuycv0PodwmnMQ==", "dev": true, "license": "(MPL-2.0 OR Apache-2.0)", "optionalDependencies": { @@ -8899,9 +9134,9 @@ ] }, "node_modules/esbuild": { - "version": "0.27.7", - "resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.27.7.tgz", - "integrity": "sha512-IxpibTjyVnmrIQo5aqNpCgoACA/dTKLTlhMHihVHhdkxKyPO1uBBthumT0rdHmcsk9uMonIWS0m4FljWzILh3w==", + "version": "0.28.1", + "resolved": "https://registry.npmjs.org/esbuild/-/esbuild-0.28.1.tgz", + "integrity": "sha512-HrJrvZv5ayxBzPfwphOoNzkzOIIlifzk0KJrGK2c8R4+LKpMtpYLQeUdjnwjWv/LZlkH2laZk+4w78pi99D4Vw==", "dev": true, "hasInstallScript": true, "license": "MIT", @@ -8912,32 +9147,32 @@ "node": ">=18" }, "optionalDependencies": { - "@esbuild/aix-ppc64": "0.27.7", - "@esbuild/android-arm": "0.27.7", - "@esbuild/android-arm64": "0.27.7", - "@esbuild/android-x64": "0.27.7", - "@esbuild/darwin-arm64": "0.27.7", - "@esbuild/darwin-x64": "0.27.7", - "@esbuild/freebsd-arm64": "0.27.7", - "@esbuild/freebsd-x64": "0.27.7", - "@esbuild/linux-arm": "0.27.7", - "@esbuild/linux-arm64": "0.27.7", - "@esbuild/linux-ia32": "0.27.7", - "@esbuild/linux-loong64": "0.27.7", - "@esbuild/linux-mips64el": "0.27.7", - "@esbuild/linux-ppc64": "0.27.7", - "@esbuild/linux-riscv64": "0.27.7", - "@esbuild/linux-s390x": "0.27.7", - "@esbuild/linux-x64": "0.27.7", - "@esbuild/netbsd-arm64": "0.27.7", - "@esbuild/netbsd-x64": "0.27.7", - "@esbuild/openbsd-arm64": "0.27.7", - "@esbuild/openbsd-x64": "0.27.7", - "@esbuild/openharmony-arm64": "0.27.7", - "@esbuild/sunos-x64": "0.27.7", - "@esbuild/win32-arm64": "0.27.7", - "@esbuild/win32-ia32": "0.27.7", - "@esbuild/win32-x64": "0.27.7" + "@esbuild/aix-ppc64": "0.28.1", + "@esbuild/android-arm": "0.28.1", + "@esbuild/android-arm64": "0.28.1", + "@esbuild/android-x64": "0.28.1", + "@esbuild/darwin-arm64": "0.28.1", + "@esbuild/darwin-x64": "0.28.1", + "@esbuild/freebsd-arm64": "0.28.1", + "@esbuild/freebsd-x64": "0.28.1", + "@esbuild/linux-arm": "0.28.1", + "@esbuild/linux-arm64": "0.28.1", + "@esbuild/linux-ia32": "0.28.1", + "@esbuild/linux-loong64": "0.28.1", + "@esbuild/linux-mips64el": "0.28.1", + "@esbuild/linux-ppc64": "0.28.1", + "@esbuild/linux-riscv64": "0.28.1", + "@esbuild/linux-s390x": "0.28.1", + "@esbuild/linux-x64": "0.28.1", + "@esbuild/netbsd-arm64": "0.28.1", + "@esbuild/netbsd-x64": "0.28.1", + "@esbuild/openbsd-arm64": "0.28.1", + "@esbuild/openbsd-x64": "0.28.1", + "@esbuild/openharmony-arm64": "0.28.1", + "@esbuild/sunos-x64": "0.28.1", + "@esbuild/win32-arm64": "0.28.1", + "@esbuild/win32-ia32": "0.28.1", + "@esbuild/win32-x64": "0.28.1" } }, "node_modules/escalade": { @@ -9047,17 +9282,18 @@ } }, "node_modules/eslint-plugin-storybook": { - "version": "10.4.2", - "resolved": "https://registry.npmjs.org/eslint-plugin-storybook/-/eslint-plugin-storybook-10.4.2.tgz", - "integrity": "sha512-l3/vzLRmb8VSi3X1Bo6/Pa+64naw1jFsZE5jPPA4izvVdNhH1rF4rGuOC3kDTU926qKVBQtKua8D24XWQtvcGg==", + "version": "10.5.6", + "resolved": "https://registry.npmjs.org/eslint-plugin-storybook/-/eslint-plugin-storybook-10.5.6.tgz", + "integrity": "sha512-uOXhNkIH+iTdyViSmWnCrwtapasL57M3nq5yfST1H7y9djRLyuAIfNcf9cPBedc2G1oqI8jn3up/VHdN3y3Btw==", "dev": true, "license": "MIT", "dependencies": { - "@typescript-eslint/utils": "^8.48.0" + "@typescript-eslint/types": "^8.60.0", + "@typescript-eslint/utils": "^8.60.0" }, "peerDependencies": { "eslint": ">=8", - "storybook": "^10.4.2" + "storybook": "^10.5.6" } }, "node_modules/eslint-plugin-svelte": { @@ -9421,9 +9657,9 @@ "license": "MIT" }, "node_modules/fast-uri": { - "version": "3.1.2", - "resolved": "https://registry.npmjs.org/fast-uri/-/fast-uri-3.1.2.tgz", - "integrity": "sha512-rVjf7ArG3LTk+FS6Yw81V1DLuZl1bRbNrev6Tmd/9RaroeeRRJhAt7jg/6YFxbvAQXUCavSoZhPPj6oOx+5KjQ==", + "version": "3.1.5", + "resolved": "https://registry.npmjs.org/fast-uri/-/fast-uri-3.1.5.tgz", + "integrity": "sha512-gHwA1O9LDIcKunMKhObS/HimwtehO1nPUECKAu5TpKgaO19fcWEl4bliWe1jWxVFvIXztJjjQ4L8XQ1EU9f7Jw==", "dev": true, "funding": [ { @@ -9486,9 +9722,9 @@ } }, "node_modules/filelist/node_modules/brace-expansion": { - "version": "2.1.1", - "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.1.1.tgz", - "integrity": "sha512-WR1cURNjuvBLMZBMbqM0UoE+WAfdUcEV1ccD8PVBVOI+Z3ND4+SZbN8RsfT2bMuG1qwz5RFvPukSZm5fF2D5eA==", + "version": "2.1.4", + "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.1.4.tgz", + "integrity": "sha512-hGfVzPxthbf3+2yjg/RBs60cB0FhqBS/zvdV/4wn4/BmN0bNMMHPc4V/BbFieqf1TKAGGAHnY4eSjajCl0f2Xg==", "dev": true, "license": "MIT", "dependencies": { @@ -9508,16 +9744,6 @@ "node": ">=10" } }, - "node_modules/filesize": { - "version": "10.1.6", - "resolved": "https://registry.npmjs.org/filesize/-/filesize-10.1.6.tgz", - "integrity": "sha512-sJslQKU2uM33qH5nqewAwVB2QgR6w1aMNsYUp3aN5rMRyXEwJGmZvaWzeJFNTOXWlHQyBFCWrdj3fV/fsTOX8w==", - "dev": true, - "license": "BSD-3-Clause", - "engines": { - "node": ">= 10.4.0" - } - }, "node_modules/finalhandler": { "version": "2.1.1", "resolved": "https://registry.npmjs.org/finalhandler/-/finalhandler-2.1.1.tgz", @@ -10226,9 +10452,9 @@ } }, "node_modules/hono": { - "version": "4.12.26", - "resolved": "https://registry.npmjs.org/hono/-/hono-4.12.26.tgz", - "integrity": "sha512-uyZtpnYxM9CmQ7QsQknM4zN8EftNqhON1qYeIKM0Se67CCEe2c44xyGURwB0axX2fBDu1dqHrHAc1hmNT8ITkw==", + "version": "4.13.0", + "resolved": "https://registry.npmjs.org/hono/-/hono-4.13.0.tgz", + "integrity": "sha512-jhunvfHWxd7J5EFfSgH4xsYJzSe/lfqbUCxiyyeaQasUsXeEHXtzVid+7EOGByc5JnFa23SSFL3Y2RV/z1T+eQ==", "dev": true, "license": "MIT", "engines": { @@ -10372,9 +10598,9 @@ } }, "node_modules/immutable": { - "version": "5.1.6", - "resolved": "https://registry.npmjs.org/immutable/-/immutable-5.1.6.tgz", - "integrity": "sha512-q1swsS8K7L8usSHuOqF2TAoCCkonYz0SG38wLAggaa4Wml70zixIvt2ql4coQ2C2B3hTjltJry4r6bULwgAXLQ==", + "version": "5.1.9", + "resolved": "https://registry.npmjs.org/immutable/-/immutable-5.1.9.tgz", + "integrity": "sha512-m8nVez3rwrgmWxtLMt1ZYXB2Lv7OKYn/disyxAlSDYAlKSlFoPPfIAmAM/M5xqL4m4C/wAPw7S2/CNaUii1Hxg==", "dev": true, "license": "MIT" }, @@ -10466,9 +10692,9 @@ } }, "node_modules/ip-address": { - "version": "10.2.0", - "resolved": "https://registry.npmjs.org/ip-address/-/ip-address-10.2.0.tgz", - "integrity": "sha512-/+S6j4E9AHvW9SWMSEY9Xfy66O5PWvVEJ08O0y5JGyEKQpojb0K0GKpz/v5HJ/G0vi3D2sjGK78119oXZeE0qA==", + "version": "10.4.0", + "resolved": "https://registry.npmjs.org/ip-address/-/ip-address-10.4.0.tgz", + "integrity": "sha512-oSK96Grm3aP6OrS263xVxbNDGVL7rzBtYdpGqlDG8iQdoenDoTs/nkki+DflYbAEE8Xl6o5YxhxlrKvI3nqKXQ==", "dev": true, "license": "MIT", "engines": { @@ -10503,13 +10729,6 @@ "url": "https://github.com/sponsors/ljharb" } }, - "node_modules/is-arrayish": { - "version": "0.3.4", - "resolved": "https://registry.npmjs.org/is-arrayish/-/is-arrayish-0.3.4.tgz", - "integrity": "sha512-m6UrgzFVUYawGBh1dUsWR5M2Clqic9RVXC/9f8ceNlv2IcO9j9J/z8UoCLPqtsPBFNzEpfR3xftohbfqDx8EQA==", - "dev": true, - "license": "MIT" - }, "node_modules/is-async-function": { "version": "2.1.1", "resolved": "https://registry.npmjs.org/is-async-function/-/is-async-function-2.1.1.tgz", @@ -11094,9 +11313,9 @@ "license": "MIT" }, "node_modules/js-yaml": { - "version": "4.2.0", - "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-4.2.0.tgz", - "integrity": "sha512-ePWsvanv0DWuDRsW8dnt+R4jQ31SCRCQ7hhNcPXZPsoBZiemuZNYGf7adZdqX2D86j6rvKp3RpCxVTSb8WQlOw==", + "version": "4.3.1", + "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-4.3.1.tgz", + "integrity": "sha512-CY6crGq313MX8GkwvB7tzgp99vjQxY1++5y10/BKN/GUfHqWaOGQMNZkBvqSzsZKWk/ijwHlWzzkLulsGHhjWQ==", "dev": true, "funding": [ { @@ -11136,6 +11355,13 @@ "dev": true, "license": "MIT" }, + "node_modules/json-rpc-2.0": { + "version": "1.7.1", + "resolved": "https://registry.npmjs.org/json-rpc-2.0/-/json-rpc-2.0-1.7.1.tgz", + "integrity": "sha512-JqZjhjAanbpkXIzFE7u8mE/iFblawwlXtONaCvRqI+pyABVz7B4M1EUNpyVW+dZjqgQ2L5HFmZCmOCgUKm00hg==", + "dev": true, + "license": "MIT" + }, "node_modules/json-schema-traverse": { "version": "1.0.0", "resolved": "https://registry.npmjs.org/json-schema-traverse/-/json-schema-traverse-1.0.0.tgz", @@ -11170,6 +11396,13 @@ "node": ">=6" } }, + "node_modules/jsonc-parser": { + "version": "3.3.1", + "resolved": "https://registry.npmjs.org/jsonc-parser/-/jsonc-parser-3.3.1.tgz", + "integrity": "sha512-HUgH65KyejrUFPvHFPbqOY0rsFip3Bo5wb4ngvdi1EpCYWUQDC5V+Y7mZws+DLkr4M//zQJoanu1SP+87Dv1oQ==", + "dev": true, + "license": "MIT" + }, "node_modules/jsonfile": { "version": "6.2.1", "resolved": "https://registry.npmjs.org/jsonfile/-/jsonfile-6.2.1.tgz", @@ -12938,9 +13171,9 @@ "license": "MIT" }, "node_modules/nanoid": { - "version": "3.3.12", - "resolved": "https://registry.npmjs.org/nanoid/-/nanoid-3.3.12.tgz", - "integrity": "sha512-ZB9RH/39qpq5Vu6Y+NmUaFhQR6pp+M2Xt76XBnEwDaGcVAqhlvxrl3B2bKS5D3NH3QR76v3aSrKaF/Kiy7lEtQ==", + "version": "3.3.17", + "resolved": "https://registry.npmjs.org/nanoid/-/nanoid-3.3.17.tgz", + "integrity": "sha512-xQLf0A3HOMlgHq0n247/LRuAOYmB7dXJ/DvAxGvsSBij45XtBSmQycu+F8ODbHwns/XyFZagyL1+J0Offw1E0g==", "dev": true, "funding": [ { @@ -13393,6 +13626,13 @@ "url": "https://github.com/sponsors/jonschlinkert" } }, + "node_modules/picoquery": { + "version": "2.5.0", + "resolved": "https://registry.npmjs.org/picoquery/-/picoquery-2.5.0.tgz", + "integrity": "sha512-j1kgOFxtaCyoFCkpoYG2Oj3OdGakadO7HZ7o5CqyRazlmBekKhbDoUnNnXASE07xSY4nDImWZkrZv7toSxMi/g==", + "dev": true, + "license": "MIT" + }, "node_modules/pkce-challenge": { "version": "5.0.1", "resolved": "https://registry.npmjs.org/pkce-challenge/-/pkce-challenge-5.0.1.tgz", @@ -13488,9 +13728,9 @@ } }, "node_modules/postcss": { - "version": "8.5.15", - "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.15.tgz", - "integrity": "sha512-FfR8sjd4em2T6fb3I2MwAJU7HWVMr9zba+enmQeeWFfCbm+UOC/0X4DS8XtpUTMwWMGbjKYP7xjfNekzyGmB3A==", + "version": "8.5.25", + "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.25.tgz", + "integrity": "sha512-DTPx3RWSSnWyzLxQnlH0rJP+EW5ekl16ZU4/psbIhA0e53kJfdgaN5vKM+xP7yJtXVu+nfdVFmlgFDEKAe4Pyw==", "dev": true, "funding": [ { @@ -13508,7 +13748,7 @@ ], "license": "MIT", "dependencies": { - "nanoid": "^3.3.12", + "nanoid": "^3.3.16", "picocolors": "^1.1.1", "source-map-js": "^1.2.1" }, @@ -13762,7 +14002,6 @@ "integrity": "sha512-Qb1gy5OrP5+zDf2Bvnzdl3jsTf1qXVMazbvCoKhtKqVs4/YK4ozX4gKQJJVyNe+cajNPn0KoC0MC3FUmaHWEmQ==", "dev": true, "license": "MIT", - "peer": true, "dependencies": { "ansi-regex": "^5.0.1", "ansi-styles": "^5.0.0", @@ -13778,7 +14017,6 @@ "integrity": "sha512-Cxwpt2SfTzTtXcfOlzGEee8O+c+MmUgGrNiBcXnuWxuFJHe6a5Hz7qwhwe5OgaSYI0IJvkLqWX1ASG+cJOkEiA==", "dev": true, "license": "MIT", - "peer": true, "engines": { "node": ">=10" }, @@ -13925,8 +14163,7 @@ "resolved": "https://registry.npmjs.org/react-is/-/react-is-17.0.2.tgz", "integrity": "sha512-w2GsyukL62IJnlaff/nRegPQR94C/XXamvMWmSHRJ4y7Ts/4ocGRmTHvOs8PSE6pB3dWOrD/nueuU5sduBsQ4w==", "dev": true, - "license": "MIT", - "peer": true + "license": "MIT" }, "node_modules/readdirp": { "version": "5.0.0", @@ -14568,9 +14805,9 @@ "license": "MIT" }, "node_modules/semver": { - "version": "7.8.1", - "resolved": "https://registry.npmjs.org/semver/-/semver-7.8.1.tgz", - "integrity": "sha512-rkVq3IXh+4FDGch+KwzX3aV9W3kO54GyEgpvBzSyctDA6Xtd7RJQV1xmXbeQp5v7+VzLOfVqiutSE6GICgPFvg==", + "version": "7.8.5", + "resolved": "https://registry.npmjs.org/semver/-/semver-7.8.5.tgz", + "integrity": "sha512-Y7/KDsb8LjooZpwaqGyulO6DQlksgCncchHGk+sZIY4SBvUocMBEFH5Ur1fI4dV+Jvl0w6cjvucaIi40puRioA==", "dev": true, "license": "ISC", "bin": { @@ -14701,43 +14938,53 @@ "license": "ISC" }, "node_modules/sharp": { - "version": "0.33.5", - "resolved": "https://registry.npmjs.org/sharp/-/sharp-0.33.5.tgz", - "integrity": "sha512-haPVm1EkS9pgvHrQ/F3Xy+hgcuMV0Wm9vfIBSiwZ05k+xgb0PkBQpGsAA/oWdDobNaZTH5ppvHtzCFbnSEwHVw==", + "version": "0.35.3", + "resolved": "https://registry.npmjs.org/sharp/-/sharp-0.35.3.tgz", + "integrity": "sha512-ej0zVHuZGHCiABXcNxeYhpRnPNPAcvbG8RMdBAhDAxLKkCRVSpK3Iyu7qbqw3JMzoj0REeM6f3tJLtVwl0023Q==", "dev": true, - "hasInstallScript": true, "license": "Apache-2.0", "dependencies": { - "color": "^4.2.3", - "detect-libc": "^2.0.3", - "semver": "^7.6.3" + "@img/colour": "^1.1.0", + "detect-libc": "^2.1.2", + "semver": "^7.8.5" }, "engines": { - "node": "^18.17.0 || ^20.3.0 || >=21.0.0" + "node": ">=20.9.0" }, "funding": { "url": "https://opencollective.com/libvips" }, "optionalDependencies": { - "@img/sharp-darwin-arm64": "0.33.5", - "@img/sharp-darwin-x64": "0.33.5", - "@img/sharp-libvips-darwin-arm64": "1.0.4", - "@img/sharp-libvips-darwin-x64": "1.0.4", - "@img/sharp-libvips-linux-arm": "1.0.5", - "@img/sharp-libvips-linux-arm64": "1.0.4", - "@img/sharp-libvips-linux-s390x": "1.0.4", - "@img/sharp-libvips-linux-x64": "1.0.4", - "@img/sharp-libvips-linuxmusl-arm64": "1.0.4", - "@img/sharp-libvips-linuxmusl-x64": "1.0.4", - "@img/sharp-linux-arm": "0.33.5", - "@img/sharp-linux-arm64": "0.33.5", - "@img/sharp-linux-s390x": "0.33.5", - "@img/sharp-linux-x64": "0.33.5", - "@img/sharp-linuxmusl-arm64": "0.33.5", - "@img/sharp-linuxmusl-x64": "0.33.5", - "@img/sharp-wasm32": "0.33.5", - "@img/sharp-win32-ia32": "0.33.5", - "@img/sharp-win32-x64": "0.33.5" + "@img/sharp-darwin-arm64": "0.35.3", + "@img/sharp-darwin-x64": "0.35.3", + "@img/sharp-freebsd-wasm32": "0.35.3", + "@img/sharp-libvips-darwin-arm64": "1.3.2", + "@img/sharp-libvips-darwin-x64": "1.3.2", + "@img/sharp-libvips-linux-arm": "1.3.2", + "@img/sharp-libvips-linux-arm64": "1.3.2", + "@img/sharp-libvips-linux-ppc64": "1.3.2", + "@img/sharp-libvips-linux-riscv64": "1.3.2", + "@img/sharp-libvips-linux-s390x": "1.3.2", + "@img/sharp-libvips-linux-x64": "1.3.2", + "@img/sharp-libvips-linuxmusl-arm64": "1.3.2", + "@img/sharp-libvips-linuxmusl-x64": "1.3.2", + "@img/sharp-linux-arm": "0.35.3", + "@img/sharp-linux-arm64": "0.35.3", + "@img/sharp-linux-ppc64": "0.35.3", + "@img/sharp-linux-riscv64": "0.35.3", + "@img/sharp-linux-s390x": "0.35.3", + "@img/sharp-linux-x64": "0.35.3", + "@img/sharp-linuxmusl-arm64": "0.35.3", + "@img/sharp-linuxmusl-x64": "0.35.3", + "@img/sharp-webcontainers-wasm32": "0.35.3", + "@img/sharp-win32-arm64": "0.35.3", + "@img/sharp-win32-ia32": "0.35.3", + "@img/sharp-win32-x64": "0.35.3" + }, + "peerDependenciesMeta": { + "@types/node": { + "optional": true + } } }, "node_modules/sharp-ico": { @@ -14871,16 +15118,6 @@ "url": "https://github.com/sponsors/isaacs" } }, - "node_modules/simple-swizzle": { - "version": "0.2.4", - "resolved": "https://registry.npmjs.org/simple-swizzle/-/simple-swizzle-0.2.4.tgz", - "integrity": "sha512-nAu1WFPQSMNr2Zn9PGSZK9AGn4t/y97lEm+MXTtUDwfP0ksAIX4nO+6ruD9Jwut4C49SB1Ws+fbXsm/yScWOHw==", - "dev": true, - "license": "MIT", - "dependencies": { - "is-arrayish": "^0.3.1" - } - }, "node_modules/sirv": { "version": "3.0.2", "resolved": "https://registry.npmjs.org/sirv/-/sirv-3.0.2.tgz", @@ -14948,6 +15185,13 @@ "url": "https://github.com/sponsors/wooorm" } }, + "node_modules/sqids": { + "version": "0.3.0", + "resolved": "https://registry.npmjs.org/sqids/-/sqids-0.3.0.tgz", + "integrity": "sha512-lOQK1ucVg+W6n3FhRwwSeUijxe93b51Bfz5PMRMihVf1iVkl82ePQG7V5vwrhzB11v0NtsR25PSZRGiSomJaJw==", + "dev": true, + "license": "MIT" + }, "node_modules/stackback": { "version": "0.0.2", "resolved": "https://registry.npmjs.org/stackback/-/stackback-0.0.2.tgz", @@ -14987,27 +15231,29 @@ } }, "node_modules/storybook": { - "version": "10.4.2", - "resolved": "https://registry.npmjs.org/storybook/-/storybook-10.4.2.tgz", - "integrity": "sha512-5Ax5vbHxFgMBGGhQDm75Rrumm/HZC4ICFhMcJaM0UlqnC/4FKj/IaZtImZFupknyiiyUEcWHPQFA2kX3/VSv1A==", + "version": "10.5.6", + "resolved": "https://registry.npmjs.org/storybook/-/storybook-10.5.6.tgz", + "integrity": "sha512-VhYwqxPySa24CVXKoWD6gCZXx9//DTmo43YpusGuAoHDYj5Osjt8wuBRQVeGoaLUWnHiPWv8S+GYHrJEaBM6Rg==", "dev": true, "license": "MIT", "dependencies": { "@storybook/global": "^5.0.0", "@storybook/icons": "^2.0.2", - "@testing-library/jest-dom": "^6.9.1", + "@testing-library/dom": "^10.4.1", + "@testing-library/jest-dom": "6.9.1", "@testing-library/user-event": "^14.6.1", "@vitest/expect": "3.2.4", "@vitest/spy": "3.2.4", "@webcontainer/env": "^1.1.1", - "esbuild": "^0.18.0 || ^0.19.0 || ^0.20.0 || ^0.21.0 || ^0.22.0 || ^0.23.0 || ^0.24.0 || ^0.25.0 || ^0.26.0 || ^0.27.0", + "esbuild": "^0.18.0 || ^0.19.0 || ^0.20.0 || ^0.21.0 || ^0.22.0 || ^0.23.0 || ^0.24.0 || ^0.25.0 || ^0.26.0 || ^0.27.0 || ^0.28.0", + "jsonc-parser": "^3.3.1", "open": "^10.2.0", "oxc-parser": "^0.127.0", "oxc-resolver": "^11.19.1", "recast": "^0.23.5", "semver": "^7.7.3", "use-sync-external-store": "^1.5.0", - "ws": "^8.18.0" + "ws": "^8.21.1" }, "bin": { "storybook": "dist/bin/dispatcher.js" @@ -15019,7 +15265,7 @@ "peerDependencies": { "@types/react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0", "prettier": "^2 || ^3", - "vite-plus": "^0.1.15" + "vite-plus": "^0.1.15 || ^0.2.0" }, "peerDependenciesMeta": { "@types/react": { @@ -15524,9 +15770,9 @@ } }, "node_modules/svelte2tsx": { - "version": "0.7.56", - "resolved": "https://registry.npmjs.org/svelte2tsx/-/svelte2tsx-0.7.56.tgz", - "integrity": "sha512-NTvqqL+goYlW8gWNajk81L07+uu7jw5V2m1Az5MZbYm3GEydcHXh+uTrLHM9SuGuaqCtF90vlMXkOVBotfH94g==", + "version": "0.7.59", + "resolved": "https://registry.npmjs.org/svelte2tsx/-/svelte2tsx-0.7.59.tgz", + "integrity": "sha512-Itj7Wz9WIiGFl/uJa58+rf43ajezaljKK/KTOHq5abUjto56xe+o5SOzLwSoeJ5hma9NZEstpZiazFW2q1nZPQ==", "dev": true, "license": "MIT", "dependencies": { @@ -15545,6 +15791,19 @@ "dev": true, "license": "MIT" }, + "node_modules/tagged-tag": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/tagged-tag/-/tagged-tag-1.0.0.tgz", + "integrity": "sha512-yEFYrVhod+hdNyx7g5Bnkkb0G6si8HJurOoOEgC8B/O0uXLHlaey/65KRv6cuWBNhBgHKAROVpc7QyYqE5gFng==", + "dev": true, + "license": "MIT", + "engines": { + "node": ">=20" + }, + "funding": { + "url": "https://github.com/sponsors/sindresorhus" + } + }, "node_modules/tailwind-merge": { "version": "3.6.0", "resolved": "https://registry.npmjs.org/tailwind-merge/-/tailwind-merge-3.6.0.tgz", @@ -15598,9 +15857,9 @@ } }, "node_modules/tar": { - "version": "7.5.16", - "resolved": "https://registry.npmjs.org/tar/-/tar-7.5.16.tgz", - "integrity": "sha512-56adEpPMouktRlBLXiaYFFzZ/3+JXa8P9n7WbR+ibIjtviN55mEaOkiysCnPnWm+7kkui1Dn8J9l+g6zV8731w==", + "version": "7.5.22", + "resolved": "https://registry.npmjs.org/tar/-/tar-7.5.22.tgz", + "integrity": "sha512-MFO/QzvtAOmJbkhOaCTvbGcFN9L9b+JunIsDwaKljSOdcLMea3NJ1k9Usz/rjdfSXTq4dfzfeS7W4p4YOAAHeA==", "dev": true, "license": "BlueOak-1.0.0", "dependencies": { @@ -15734,9 +15993,9 @@ } }, "node_modules/tinyrainbow": { - "version": "2.0.0", - "resolved": "https://registry.npmjs.org/tinyrainbow/-/tinyrainbow-2.0.0.tgz", - "integrity": "sha512-op4nsTR47R6p0vMUUoYl/a+ljLFVtlfaXkLQmqfLR1qHma1h/ysYk4hEXZ880bf2CYgTskvTa/e196Vd5dDQXw==", + "version": "3.1.1", + "resolved": "https://registry.npmjs.org/tinyrainbow/-/tinyrainbow-3.1.1.tgz", + "integrity": "sha512-yau8yJdTt989Mm0Bd/236QnzEiPf2xLLTqUZRUJOo/3CB078LSwzei343DgtJVmfJKJE3TMINY1u42SQsP6mXw==", "dev": true, "license": "MIT", "engines": { @@ -15753,6 +16012,20 @@ "node": ">=14.0.0" } }, + "node_modules/tmcp": { + "version": "1.19.4", + "resolved": "https://registry.npmjs.org/tmcp/-/tmcp-1.19.4.tgz", + "integrity": "sha512-fMoUJ3Gef9iA0yKZNeW2SQCCKTluCwghUyOz/qxPS8XxrQk6Jlw4lgql3S+s6L//FteLeSJ7erKxMWl727mZoQ==", + "dev": true, + "license": "MIT", + "dependencies": { + "@standard-schema/spec": "^1.0.0", + "json-rpc-2.0": "^1.7.1", + "sqids": "^0.3.0", + "uri-template-matcher": "^1.1.1", + "valibot": "^1.1.0" + } + }, "node_modules/to-data-view": { "version": "1.1.0", "resolved": "https://registry.npmjs.org/to-data-view/-/to-data-view-1.1.0.tgz", @@ -16420,6 +16693,13 @@ "punycode": "^2.1.0" } }, + "node_modules/uri-template-matcher": { + "version": "1.1.2", + "resolved": "https://registry.npmjs.org/uri-template-matcher/-/uri-template-matcher-1.1.2.tgz", + "integrity": "sha512-uZc1h12jdO3m/R77SfTEOuo6VbMhgWznaawKpBjRGSJb7i91x5PgI37NQJtG+Cerxkk0yr1pylBY2qG1kQ+aEQ==", + "dev": true, + "license": "ISC" + }, "node_modules/url-join": { "version": "4.0.1", "resolved": "https://registry.npmjs.org/url-join/-/url-join-4.0.1.tgz", @@ -16458,6 +16738,21 @@ "uuid": "dist-node/bin/uuid" } }, + "node_modules/valibot": { + "version": "1.4.2", + "resolved": "https://registry.npmjs.org/valibot/-/valibot-1.4.2.tgz", + "integrity": "sha512-gjdCvJ6d3RyHAneqxMYMW9QMCwYMb3jpOO0IyHZV1bnRHFBHrX3VkIILt5XYR0WhwHiH7Mty8ovuPZ/O3gamrg==", + "dev": true, + "license": "MIT", + "peerDependencies": { + "typescript": ">=5" + }, + "peerDependenciesMeta": { + "typescript": { + "optional": true + } + } + }, "node_modules/vary": { "version": "1.1.2", "resolved": "https://registry.npmjs.org/vary/-/vary-1.1.2.tgz", @@ -16557,13 +16852,13 @@ } }, "node_modules/vite": { - "version": "7.3.5", - "resolved": "https://registry.npmjs.org/vite/-/vite-7.3.5.tgz", - "integrity": "sha512-KuOaNhcnGFN2zIPGA7wRmzF+lJA1sea7rHq17aiJ++9lzY1WWG6Jpwqwe1KNbRVPIqHmr8GLYx7jbrQcN/7/ww==", + "version": "7.3.6", + "resolved": "https://registry.npmjs.org/vite/-/vite-7.3.6.tgz", + "integrity": "sha512-4XP60spRGjSZFf1qYH+dJIkK2znL3zQfl9KkOV9MkkRR/3Dls0dxaBsQPTloEc5BLXWPL9vsOxopxyKoMmDueg==", "dev": true, "license": "MIT", "dependencies": { - "esbuild": "^0.27.0", + "esbuild": "^0.27.0 || ^0.28.0", "fdir": "^6.5.0", "picomatch": "^4.0.3", "postcss": "^8.5.6", @@ -16725,19 +17020,19 @@ } }, "node_modules/vitest": { - "version": "4.1.8", - "resolved": "https://registry.npmjs.org/vitest/-/vitest-4.1.8.tgz", - "integrity": "sha512-flY6ScbCIt9HThs+C5HS7jvGOB560DJtk/Z15IQROTA6zEy49Nh8T/dofWTQL+n3vswqn87sbJNiuqw1SDp5Ig==", + "version": "4.1.10", + "resolved": "https://registry.npmjs.org/vitest/-/vitest-4.1.10.tgz", + "integrity": "sha512-R9jUTe5S4Qb0HCd4TNqpC7oGcrMssMRGXLW80ubjWsW9VH5GF8y1Y0SFLY9AbqSk6nt0PnOx4H4WNJYZ13GUPw==", "dev": true, "license": "MIT", "dependencies": { - "@vitest/expect": "4.1.8", - "@vitest/mocker": "4.1.8", - "@vitest/pretty-format": "4.1.8", - "@vitest/runner": "4.1.8", - "@vitest/snapshot": "4.1.8", - "@vitest/spy": "4.1.8", - "@vitest/utils": "4.1.8", + "@vitest/expect": "4.1.10", + "@vitest/mocker": "4.1.10", + "@vitest/pretty-format": "4.1.10", + "@vitest/runner": "4.1.10", + "@vitest/snapshot": "4.1.10", + "@vitest/spy": "4.1.10", + "@vitest/utils": "4.1.10", "es-module-lexer": "^2.0.0", "expect-type": "^1.3.0", "magic-string": "^0.30.21", @@ -16765,12 +17060,12 @@ "@edge-runtime/vm": "*", "@opentelemetry/api": "^1.9.0", "@types/node": "^20.0.0 || ^22.0.0 || >=24.0.0", - "@vitest/browser-playwright": "4.1.8", - "@vitest/browser-preview": "4.1.8", - "@vitest/browser-webdriverio": "4.1.8", - "@vitest/coverage-istanbul": "4.1.8", - "@vitest/coverage-v8": "4.1.8", - "@vitest/ui": "4.1.8", + "@vitest/browser-playwright": "4.1.10", + "@vitest/browser-preview": "4.1.10", + "@vitest/browser-webdriverio": "4.1.10", + "@vitest/coverage-istanbul": "4.1.10", + "@vitest/coverage-v8": "4.1.10", + "@vitest/ui": "4.1.10", "happy-dom": "*", "jsdom": "*", "vite": "^6.0.0 || ^7.0.0 || ^8.0.0" @@ -16832,16 +17127,16 @@ } }, "node_modules/vitest/node_modules/@vitest/expect": { - "version": "4.1.8", - "resolved": "https://registry.npmjs.org/@vitest/expect/-/expect-4.1.8.tgz", - "integrity": "sha512-h3nDO677RDLEGlBxyQ5CW8RlMThSKSRLUePLOx09gNIWRL40edgA1GCZSZgf1W55MFAG6/Sw14KeaAnqv0NKdQ==", + "version": "4.1.10", + "resolved": "https://registry.npmjs.org/@vitest/expect/-/expect-4.1.10.tgz", + "integrity": "sha512-YsCn+qAk1GWjQOWFEsEcL2gNQ0zmVmQu3T03qP6UyjhtmdtwtbuI+DASn/7iQB3HGTXkdBwGddzxPlmiql5vlA==", "dev": true, "license": "MIT", "dependencies": { "@standard-schema/spec": "^1.1.0", "@types/chai": "^5.2.2", - "@vitest/spy": "4.1.8", - "@vitest/utils": "4.1.8", + "@vitest/spy": "4.1.10", + "@vitest/utils": "4.1.10", "chai": "^6.2.2", "tinyrainbow": "^3.1.0" }, @@ -16859,16 +17154,6 @@ "node": ">=18" } }, - "node_modules/vitest/node_modules/tinyrainbow": { - "version": "3.1.0", - "resolved": "https://registry.npmjs.org/tinyrainbow/-/tinyrainbow-3.1.0.tgz", - "integrity": "sha512-Bf+ILmBgretUrdJxzXM0SgXLZ3XfiaUuOj/IKQHuTXip+05Xn+uyEYdVg0kYDipTBcLrCVyUzAPz7QmArb0mmw==", - "dev": true, - "license": "MIT", - "engines": { - "node": ">=14.0.0" - } - }, "node_modules/web-namespaces": { "version": "2.0.1", "resolved": "https://registry.npmjs.org/web-namespaces/-/web-namespaces-2.0.1.tgz", @@ -17156,16 +17441,16 @@ } }, "node_modules/workbox-build/node_modules/brace-expansion": { - "version": "5.0.6", - "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.6.tgz", - "integrity": "sha512-kLpxurY4Z4r9sgMsyG0Z9uzsBlgiU/EFKhj/h91/8yHu0edo7XuixOIH3VcJ8kkxs6/jPzoI6U9Vj3WqbMQ94g==", + "version": "5.0.9", + "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-5.0.9.tgz", + "integrity": "sha512-ScQ4IuvIEF1TMlP7Zt+vjJ//9zlPb2SDcxWxM3bk8s6t6GGdJ7KO1dCcTidOPJKePW30LE/2cT7wCyPho9/Wxg==", "dev": true, "license": "MIT", "dependencies": { "balanced-match": "^4.0.2" }, "engines": { - "node": "18 || 20 || >=22" + "node": "20 || >=22" } }, "node_modules/workbox-build/node_modules/glob": { @@ -17424,9 +17709,9 @@ "license": "ISC" }, "node_modules/ws": { - "version": "8.21.0", - "resolved": "https://registry.npmjs.org/ws/-/ws-8.21.0.tgz", - "integrity": "sha512-Vsp28b7DRcimFQvrqu2Wek3z1iYxDCWqHYB8Qsnk/S4RfaCQzPGPyBNuVjJV3cd6UiKtUtp6sNM77gWvzcCH+g==", + "version": "8.21.2", + "resolved": "https://registry.npmjs.org/ws/-/ws-8.21.2.tgz", + "integrity": "sha512-54dMVAo4WIe6SKy3vBgN+9bJZqqQ8IMRevAkOLQALhi49qkkQDQfWdAZ8KQlXiEabw88ARXXdUrlvtbKQX+aKw==", "dev": true, "license": "MIT", "engines": { diff --git a/tools/ui/package.json b/tools/ui/package.json index 4ea2bf703c35..7f042f415ae8 100644 --- a/tools/ui/package.json +++ b/tools/ui/package.json @@ -27,20 +27,20 @@ "cleanup": "rm -rf .svelte-kit build node_modules test-results dist dev-dist debug-storybook.log static/pwa-*.png static/maskable-icon-*.png static/apple-touch-icon-*.png static/apple-splash-*.png static/favicon*.ico" }, "devDependencies": { - "@chromatic-com/storybook": "5.0.0", + "@chromatic-com/storybook": "5.2.1", "@eslint/compat": "1.4.1", "@eslint/js": "9.39.2", "@internationalized/date": "3.12.2", "@lucide/svelte": "1.25.0", - "@modelcontextprotocol/sdk": "1.26.0", + "@modelcontextprotocol/sdk": "1.30.0", "@playwright/test": "1.56.1", - "@storybook/addon-a11y": "10.2.4", - "@storybook/addon-docs": "10.2.4", - "@storybook/addon-svelte-csf": "5.0.10", - "@storybook/addon-vitest": "10.2.4", - "@storybook/sveltekit": "10.2.4", + "@storybook/addon-a11y": "10.5.6", + "@storybook/addon-docs": "10.5.6", + "@storybook/addon-svelte-csf": "5.1.2", + "@storybook/addon-vitest": "10.5.6", + "@storybook/sveltekit": "10.5.6", "@sveltejs/adapter-static": "3.0.10", - "@sveltejs/kit": "2.60.1", + "@sveltejs/kit": "2.70.2", "@sveltejs/vite-plugin-svelte": "6.2.1", "@tailwindcss/forms": "0.5.10", "@tailwindcss/typography": "0.5.16", @@ -48,16 +48,16 @@ "@types/node": "24.13.0", "@vite-pwa/assets-generator": "1.0.2", "@vite-pwa/sveltekit": "1.1.0", - "@vitest/browser": "4.1.8", - "@vitest/browser-playwright": "4.1.8", - "@vitest/coverage-v8": "4.1.8", + "@vitest/browser": "4.1.10", + "@vitest/browser-playwright": "4.1.10", + "@vitest/coverage-v8": "4.1.10", "bits-ui": "2.18.1", "clsx": "2.1.1", "dexie": "4.4.3", - "dompurify": "3.4.11", + "dompurify": "3.4.13", "eslint": "9.39.4", "eslint-config-prettier": "10.1.8", - "eslint-plugin-storybook": "10.4.2", + "eslint-plugin-storybook": "10.5.6", "eslint-plugin-svelte": "3.19.0", "fflate": "0.8.3", "globals": "16.5.0", @@ -82,7 +82,7 @@ "remark-math": "6.0.0", "remark-rehype": "11.1.2", "sass": "1.100.0", - "storybook": "10.4.2", + "storybook": "10.5.6", "svelte": "5.56.1", "svelte-check": "4.6.0", "svelte-sonner": "1.1.1", @@ -95,13 +95,16 @@ "unified": "11.0.5", "unist-util-visit": "5.1.0", "uuid": "13.0.2", - "vite": "7.3.5", + "vite": "7.3.6", "vite-plugin-devtools-json": "0.2.1", - "vitest": "4.1.8", + "vitest": "4.1.10", "vitest-browser-svelte": "2.1.1", - "workbox-window": "7.4.1" + "workbox-window": "7.4.1", + "@storybook/addon-mcp": "0.7.0" }, "overrides": { - "cookie": "1.1.1" + "cookie": "1.1.1", + "sharp": "0.35.3", + "valibot": "1.4.2" } } diff --git a/tools/ui/scripts/dev.sh b/tools/ui/scripts/dev.sh index 7e1d3c15e5bb..d14186630d96 100644 --- a/tools/ui/scripts/dev.sh +++ b/tools/ui/scripts/dev.sh @@ -14,7 +14,7 @@ cd ../../ # Ensure node_modules are installed if [ ! -d "tools/ui/node_modules" ]; then echo "📦 Installing npm dependencies..." - cd tools/ui && npm install && cd ../../ + cd tools/ui && npm ci && cd ../../ fi # Check and install git hooks if missing diff --git a/tools/ui/scripts/git-hooks/pre-commit.sh b/tools/ui/scripts/git-hooks/pre-commit.sh index 208ef56fcd53..31c23ed51878 100755 --- a/tools/ui/scripts/git-hooks/pre-commit.sh +++ b/tools/ui/scripts/git-hooks/pre-commit.sh @@ -14,7 +14,7 @@ cd "$REPO_ROOT/tools/ui" # Check that node_modules exists if [ ! -d "node_modules" ]; then - echo "❌ node_modules not found. Run 'npm install' first." + echo "❌ node_modules not found. Run 'npm ci' first." exit 1 fi diff --git a/tools/ui/scripts/git-hooks/pre-push.sh b/tools/ui/scripts/git-hooks/pre-push.sh index 66d79b950a36..d5598fb17a9a 100755 --- a/tools/ui/scripts/git-hooks/pre-push.sh +++ b/tools/ui/scripts/git-hooks/pre-push.sh @@ -30,7 +30,7 @@ cd "$REPO_ROOT/tools/ui" # Check that node_modules exists if [ ! -d "node_modules" ]; then - echo "❌ node_modules not found. Run 'npm install' first." + echo "❌ node_modules not found. Run 'npm ci' first." exit 1 fi diff --git a/tools/ui/src/app.d.ts b/tools/ui/src/app.d.ts index 5264e5cc4d72..73944fc3d975 100644 --- a/tools/ui/src/app.d.ts +++ b/tools/ui/src/app.d.ts @@ -51,6 +51,8 @@ import type { DatabaseMessageExtraTextFile, DatabaseMessageExtraPdfFile, DatabaseMessageExtraLegacyContext, + DatabaseMessageExtraEncrypted, + EncryptionMeta, ExportedConversation, ExportedConversations, // Model types @@ -120,6 +122,8 @@ declare global { DatabaseMessageExtraTextFile, DatabaseMessageExtraPdfFile, DatabaseMessageExtraLegacyContext, + DatabaseMessageExtraEncrypted, + EncryptionMeta, ExportedConversation, ExportedConversations, // Enum types @@ -142,5 +146,14 @@ declare global { interface Window { idxThemeStyle?: number; idxCodeBlock?: number; + + // File System Access API - missing from older DOM lib versions. + // Used by ChatFormWorkingDirectory's native folder picker. Feature availability + // is gated at runtime via `typeof window.showDirectoryPicker === 'function'`. + showDirectoryPicker: (options?: { + id?: string; + mode?: 'read' | 'readwrite'; + startIn?: FileSystemHandle | string; + }) => Promise; } } diff --git a/tools/ui/src/lib/components/app/chat/ChatForm/ChatForm.svelte b/tools/ui/src/lib/components/app/chat/ChatForm/ChatForm.svelte index 85683908cc71..105e414fe78f 100644 --- a/tools/ui/src/lib/components/app/chat/ChatForm/ChatForm.svelte +++ b/tools/ui/src/lib/components/app/chat/ChatForm/ChatForm.svelte @@ -6,6 +6,7 @@ ChatFormMcpResourcesList, ChatFormPickers, ChatFormTextarea, + ChatFormWorkingDirectory, DialogMcpResourcesBrowser } from '$lib/components/app'; import { @@ -31,7 +32,13 @@ import { chatStore } from '$lib/stores/chat.svelte'; import { mcpStore } from '$lib/stores/mcp.svelte'; import { mcpHasResourceAttachments } from '$lib/stores/mcp-resources.svelte'; - import { conversationsStore, activeMessages } from '$lib/stores/conversations.svelte'; + import { toolsStore } from '$lib/stores/tools.svelte'; + import { + conversationsStore, + activeMessages, + activeConversation, + pendingCwd + } from '$lib/stores/conversations.svelte'; import type { GetPromptResult, MCPPromptInfo, MCPResourceInfo, PromptMessage } from '$lib/types'; import { isIMEComposing, parseClipboardContent, uuid } from '$lib/utils'; import { @@ -107,6 +114,15 @@ let isInlineResourcePickerOpen = $state(false); let resourceSearchQuery = $state(''); + let cwd = $derived(activeConversation()?.cwd ?? pendingCwd()); + + async function handleWorkingDirectoryChange(value: string | null) { + await conversationsStore.setCwd(value); + if (conversationsStore.activeConversation) { + await chatStore.recordCwdChange(value?.trim() || null); + } + } + // Resource Dialog State let isResourceDialogOpen = $state(false); let preSelectedResourceUri = $state(undefined); @@ -155,6 +171,12 @@ audioRecorder = new AudioRecorder(); }); + // Defer so the closing popover's focus scope tears down first - bits-ui + // yanks a synchronous focus() back into the still-mounted popover. + function refocusInput() { + queueMicrotask(() => textareaRef?.focus()); + } + export function focus() { textareaRef?.focus(); } @@ -470,7 +492,7 @@
{ event.preventDefault(); @@ -559,6 +581,15 @@ + + {#if toolsStore.builtinTools.length > 0} + + {/if} + import { FolderOpen } from '@lucide/svelte'; + import { untrack } from 'svelte'; + import { SvelteMap } from 'svelte/reactivity'; + import { ToolsService } from '$lib/services/tools.service'; + import { toolsStore } from '$lib/stores/tools.svelte'; + import { BuiltInTool, GlobSearchType, KeyboardKey } from '$lib/enums'; + import { + abbreviateHome, + buildCaseInsensitiveGlob, + joinPath, + lastPathSegment, + rankEntries, + splitPathQuery, + type GlobEntry + } from '$lib/utils'; + import { debounce } from '$lib/utils/debounce'; + import * as Popover from '$lib/components/ui/popover'; + import SearchInput from '$lib/components/app/forms/SearchInput.svelte'; + import ChatFormWorkingDirectoryChip from './ChatFormWorkingDirectoryChip.svelte'; + import ChatFormWorkingDirectoryResultsList from './ChatFormWorkingDirectoryResultsList.svelte'; + import { + DEFAULT_MOBILE_BREAKPOINT, + GLOB_WILDCARD, + HOME_TILDE, + MAX_RESULTS_SHOWN, + NATIVE_LIMIT, + NATIVE_MAX_DEPTH, + PATH_NAV_MAX_DEPTH, + SEARCH_DEBOUNCE_MS, + SEARCH_LIMIT, + SEARCH_MAX_DEPTH + } from '$lib/constants'; + + // Microtask delay so the popover's focus scope tears down first. + const FOCUS_DELAY_MS = 0; + + interface Props { + class?: string; + disabled?: boolean; + directory?: string | null; + onChange?: (directory: string | null) => void; + /** + * Lets the host refocus the chat input so typing can resume without + * an extra click after the popover closes. + */ + onClose?: () => void; + } + + let { + class: className = '', + disabled = false, + directory = $bindable(null), + onChange, + onClose + }: Props = $props(); + + // File System Access API is opt-in: when available (Chrome / Edge / Opera) the popover + // exposes a "Browse" button that opens the native folder picker. When unavailable the + // popover still works via the text input - no alerts, no upload semantics. + const pickerSupported = + typeof window !== 'undefined' && typeof window.showDirectoryPicker === 'function'; + + // Popover open state; the element handles outside-click and Escape. + let isOpen = $state(false); + let inputValue = $state(''); + let searchInputRef: HTMLInputElement | null = $state(null); + + let queryResults = $state([]); + let isSearching = $state(false); + let searchError = $state(null); + let hoveredIndex = $state(-1); + // Bumped only by ArrowUp/ArrowDown handlers; the list scrolls the + // highlighted row into view only via this trigger, never on hover. + let scrollTrigger = $state(0); + let listContainer = $state(null); + + // Absolute home directory on the server, resolved once per session by + // the tools store. Anchors both the search scope and the chip's `~` + // abbreviation. + let homeBase = $derived(toolsStore.serverHome); + + // AbortController + sequence counter to discard stale responses when the user + // keeps typing; a newer call aborts the previous one. The sequence counter + // also covers the gap between abort and the catch handler. + let searchController: AbortController | null = null; + let searchSeq = 0; + + // Cache of the last file_glob_search result per (parent, include, max_depth), + // so repeated queries in the same directory don't re-walk the tree. Entries + // expire after a short TTL. + const SEARCH_CACHE_TTL_MS = 2000; + const searchCache = new SvelteMap(); + + const runSearch = debounce((query: string) => { + void doSearch(query); + }, SEARCH_DEBOUNCE_MS); + + // Resolve home eagerly on mount so the chip can abbreviate before the + // user opens the picker. resolveServerHome() is cached, so repeat calls + // (e.g. from handleOpenChange) are no-ops. + $effect(() => { + if (typeof window === 'undefined') return; + void toolsStore.resolveServerHome(); + }); + + // Auto-focus the search input when the popover opens. + // HTML `autofocus` is unreliable on dynamically shown elements, so we + // use a microtask (0ms setTimeout) after the effect flushes. + $effect(() => { + if (!isOpen) return; + setTimeout(() => searchInputRef?.focus(), FOCUS_DELAY_MS); + }); + + let lastScrollTrigger: number | null = null; + + // hoveredIndex/queryResults are untracked so hover and result replacement + // never re-fire the scroll; keyboard nav is the only path that bumps the trigger + $effect(() => { + if (scrollTrigger === lastScrollTrigger) return; + lastScrollTrigger = scrollTrigger; + untrack(() => { + if (!listContainer) return; + if (hoveredIndex < 0 || hoveredIndex >= queryResults.length) return; + const selectedElement = listContainer.querySelector( + `[data-result-index="${hoveredIndex}"]` + ) as HTMLElement | null; + selectedElement?.scrollIntoView({ block: 'nearest', inline: 'nearest' }); + }); + }); + + function cancelSearch() { + searchController?.abort(); + searchSeq++; + isSearching = false; + } + + // Effective directory the current search runs against (shown in the + // footer); updated by doSearch, including when an exactly-typed + // directory is "entered". + let searchScope = $state(HOME_TILDE); + + // Runs a directory listing through the cache, so a repeated query in the + // same directory does not re-walk the tree on the server. + async function searchDirs( + path: string, + include: string, + maxDepth: number, + signal: AbortSignal + ): Promise<{ base: string; entries: GlobEntry[]; error?: string }> { + const key = `${path}\u0000${include}\u0000${maxDepth}`; + const cached = searchCache.get(key); + if (cached && Date.now() - cached.at < SEARCH_CACHE_TTL_MS) { + return { base: cached.base, entries: cached.results }; + } + const res = await ToolsService.executeToolRaw( + BuiltInTool.FILE_GLOB_SEARCH, + { path, type: GlobSearchType.DIR, include, max_depth: maxDepth, limit: SEARCH_LIMIT }, + signal + ); + if (typeof res.error === 'string') return { base: '', entries: [], error: res.error }; + const base = typeof res.base === 'string' ? res.base : ''; + const entries = Array.isArray(res.entries) ? (res.entries as GlobEntry[]) : []; + searchCache.set(key, { results: entries, base, at: Date.now() }); + return { base, entries }; + } + + async function doSearch(query: string) { + const trimmed = query.trim(); + if (!trimmed) { + queryResults = []; + searchError = null; + isSearching = false; + hoveredIndex = -1; + searchScope = homeBase ?? HOME_TILDE; + return; + } + + cancelSearch(); + const controller = new AbortController(); + searchController = controller; + const mySeq = ++searchSeq; + + const pathQuery = splitPathQuery(trimmed); + + isSearching = true; + try { + // A generous limit is requested because ranking happens + // client-side; only the top 20 are shown. + const searchPath = pathQuery ? pathQuery.parent : (homeBase ?? HOME_TILDE); + const include = pathQuery + ? pathQuery.last + ? buildCaseInsensitiveGlob(pathQuery.last) + : GLOB_WILDCARD + : buildCaseInsensitiveGlob(trimmed); + const maxDepth = pathQuery ? PATH_NAV_MAX_DEPTH : SEARCH_MAX_DEPTH; + const res = await searchDirs(searchPath, include, maxDepth, controller.signal); + if (mySeq !== searchSeq) return; + if (res.error) { + queryResults = []; + hoveredIndex = -1; + searchError = res.error; + return; + } + const { base, entries } = res; + const ranked = rankEntries(entries, pathQuery?.last ?? trimmed); + let results = ranked.map((e) => joinPath(base, e.path)); + searchScope = pathQuery ? pathQuery.parent : (homeBase ?? HOME_TILDE); + + // An exactly-typed directory is "entered": list its children too, + // so path navigation doesn't require a trailing slash. + const last = pathQuery?.last; + const exact = last + ? ranked.find((e) => lastPathSegment(e.path).toLowerCase() === last.toLowerCase()) + : undefined; + if (exact) { + const exactDir = joinPath(base, exact.path); + const childRes = await searchDirs( + exactDir, + GLOB_WILDCARD, + PATH_NAV_MAX_DEPTH, + controller.signal + ); + if (mySeq !== searchSeq) return; + if (!childRes.error) { + const children = childRes.entries + .map((e) => joinPath(childRes.base, e.path)) + .sort((a, b) => a.localeCompare(b)); + results = [...results, ...children]; + searchScope = exactDir; + } + } + + queryResults = results.slice(0, MAX_RESULTS_SHOWN); + hoveredIndex = queryResults.length > 0 ? 0 : -1; + // new results: scroll the list back to the top (first item is hovered) + if (hoveredIndex === 0) scrollTrigger++; + searchError = null; + } catch (err) { + if (mySeq !== searchSeq) return; + queryResults = []; + hoveredIndex = -1; + if (controller.signal.aborted) return; + searchError = err instanceof Error ? err.message : String(err); + } finally { + if (mySeq === searchSeq) isSearching = false; + } + } + + // Single funnel for every local close so the host refocus fires + // regardless of which commit/dismiss path ended the interaction. + function closePicker() { + isOpen = false; + onClose?.(); + } + + function commit(path: string) { + directory = path; + onChange?.(path); + closePicker(); + } + + function setDirectory(value: string) { + const trimmed = value.trim(); + if (!trimmed) return; + directory = trimmed; + onChange?.(trimmed); + } + + // Resolve a folder name picked via the browser-native picker (which exposes + // only the leaf name) to a server-side absolute path. Returns null when the + // server cannot locate a matching directory, so the caller can fail visibly + // instead of committing a bare leaf name that would resolve against the + // server process working directory. + async function resolveNativeName(name: string): Promise { + try { + const res = await ToolsService.executeToolRaw(BuiltInTool.FILE_GLOB_SEARCH, { + path: homeBase ?? HOME_TILDE, + type: GlobSearchType.DIR, + include: buildCaseInsensitiveGlob(name), + max_depth: NATIVE_MAX_DEPTH, + limit: NATIVE_LIMIT + }); + const base = typeof res.base === 'string' ? res.base : ''; + const entries = Array.isArray(res.entries) ? (res.entries as GlobEntry[]) : []; + const match = entries.find( + (e) => lastPathSegment(e.path).toLowerCase() === name.toLowerCase() + ); + return match ? joinPath(base, match.path) : null; + } catch { + return null; + } + } + + async function browseNative() { + if (disabled || !window.showDirectoryPicker) return; + try { + const handle = await window.showDirectoryPicker(); + const path = await resolveNativeName(handle.name); + if (path) { + setDirectory(path); + closePicker(); + } else { + // keep the previous cwd and fail visibly instead of committing a + // bare leaf name that would resolve against the server cwd + searchError = `Could not resolve "${handle.name}" to a server path`; + } + } catch (err) { + // user cancelled - silently ignore; other errors are logged + if (err instanceof DOMException && err.name === 'AbortError') return; + console.error('[ChatFormWorkingDirectory] showDirectoryPicker failed:', err); + } + } + + function handleSubmit() { + const value = inputValue.trim(); + if (!value) { + closePicker(); + return; + } + setDirectory(value); + closePicker(); + } + + function handleKeydown(event: KeyboardEvent) { + if (event.key === KeyboardKey.ENTER) { + event.preventDefault(); + // Commit the highlighted result, falling back to the raw input + // only when the query returned no matches. + if (hoveredIndex >= 0 && queryResults[hoveredIndex]) { + commit(queryResults[hoveredIndex]); + } else if (queryResults.length === 0) { + handleSubmit(); + } + } else if (event.key === KeyboardKey.ARROW_DOWN) { + if (queryResults.length > 0) { + event.preventDefault(); + hoveredIndex = (hoveredIndex + 1) % queryResults.length; + scrollTrigger++; + } + } else if (event.key === KeyboardKey.ARROW_UP) { + if (queryResults.length > 0) { + event.preventDefault(); + hoveredIndex = hoveredIndex <= 0 ? queryResults.length - 1 : hoveredIndex - 1; + scrollTrigger++; + } + } + } + + function handleInputInput(value: string) { + hoveredIndex = -1; + if (value.trim().length > 0) { + runSearch(value); + } + } + + function clearDirectory(event?: MouseEvent) { + // Stop the click from bubbling into the popover trigger and re-opening + // the picker on top of the now-cleared state. + event?.stopPropagation(); + event?.preventDefault(); + directory = null; + onChange?.(null); + closePicker(); + } + + // The chip is always visible; the X clears the directory (no-op when + // already empty). + function handleDismiss(event?: MouseEvent) { + event?.stopPropagation(); + event?.preventDefault(); + if (directory) { + clearDirectory(event); + } + } + + function handleOpenChange(open: boolean) { + isOpen = open; + if (open) { + // Seed the search field with the current path so the user can refine it + // (or hit Enter to confirm / clear via the X icon). + inputValue = directory ?? ''; + hoveredIndex = -1; + queryResults = []; + searchError = null; + void toolsStore.resolveServerHome(); + searchScope = homeBase ?? HOME_TILDE; + if (inputValue.trim()) runSearch(inputValue); + } else { + cancelSearch(); + // bits-ui-initiated close (Escape on the content, outside-click, + // trigger toggle) - the only path that bypasses closePicker(). + onClose?.(); + } + } + + // Tooltips only on wider viewports - hover surfaces get in the way on + // touch / narrow layouts. Mirrors the gate used in ActionIcon. + let innerWidth = $state(0); + const showTooltip = $derived(innerWidth > DEFAULT_MOBILE_BREAKPOINT); + + +
+ + + + + + event.preventDefault()} + > +
+ + + {#if inputValue.trim() && (isSearching || queryResults.length > 0 || searchError)} + (hoveredIndex = index)} + /> + {/if} + + {#if pickerSupported} + + {/if} + + {#if homeBase} + + + + Searching in: + + {abbreviateHome(searchScope, homeBase)} + + {/if} +
+ + +
+ + diff --git a/tools/ui/src/lib/components/app/chat/ChatForm/ChatFormWorkingDirectoryChip.svelte b/tools/ui/src/lib/components/app/chat/ChatForm/ChatFormWorkingDirectoryChip.svelte new file mode 100644 index 000000000000..4f8d0f7f7d77 --- /dev/null +++ b/tools/ui/src/lib/components/app/chat/ChatForm/ChatFormWorkingDirectoryChip.svelte @@ -0,0 +1,69 @@ + + + +
+ + + {#if showTooltip && displayLabelTitle} + + + {#snippet child({ props })} + {displayLabel} + {/snippet} + + +

{displayLabelTitle}

+ + + {:else} + {displayLabel} + {/if} +
+ + {#if directory} +
+ +
+ {/if} + diff --git a/tools/ui/src/lib/components/app/chat/ChatForm/ChatFormWorkingDirectoryResultsList.svelte b/tools/ui/src/lib/components/app/chat/ChatForm/ChatFormWorkingDirectoryResultsList.svelte new file mode 100644 index 000000000000..d62eb88242db --- /dev/null +++ b/tools/ui/src/lib/components/app/chat/ChatForm/ChatFormWorkingDirectoryResultsList.svelte @@ -0,0 +1,72 @@ + + +
+ {#if isSearching && results.length === 0} +
Searching...
+ {:else if error} +
{error}
+ {:else if results.length === 0} +
No matching folders
+ {:else} + {#each results as path, index (path)} + + {/each} + {/if} +
diff --git a/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessage.svelte b/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessage.svelte index b8068f790734..afe90f66fe25 100644 --- a/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessage.svelte +++ b/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessage.svelte @@ -12,6 +12,7 @@ ChatMessageAssistant, ChatMessageUser, ChatMessageSystem, + ChatMessageSynthetic, ChatMessageMcpPrompt } from '$lib/components/app/chat'; import { parseFilesToMessageExtras } from '$lib/utils/browser-only'; @@ -56,6 +57,10 @@ : message.content ); + // Synthetic cwd-change messages render with the folder-row UI instead + // of a user bubble. The persisted flag is the single source of truth. + let isSynthetic = $derived(Boolean(message.isSynthetic)); + let rawEditContent = $derived.by(() => { if (message.role !== MessageRole.ASSISTANT) return undefined; @@ -344,7 +349,7 @@ } -
+
{#if message.role === MessageRole.SYSTEM} + {:else if isSynthetic} + {:else if message.role === MessageRole.USER} diff --git a/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageCwdChange.svelte b/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageCwdChange.svelte new file mode 100644 index 000000000000..0b0133060fda --- /dev/null +++ b/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageCwdChange.svelte @@ -0,0 +1,31 @@ + + +{#if info} +
+ {#if info.path === null} + + Working directory cleared + {:else} + + Set working directory to  + + {info.display} + + {/if} +
+{/if} diff --git a/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageSynthetic.svelte b/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageSynthetic.svelte new file mode 100644 index 000000000000..1597df2ab147 --- /dev/null +++ b/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageSynthetic.svelte @@ -0,0 +1,23 @@ + + +{#if isCwdChange} + +{:else} + {message.content} +{/if} diff --git a/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageToolCall/ChatMessageToolCallBlock.svelte b/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageToolCall/ChatMessageToolCallBlock.svelte index b1daedfc818c..1d6cccc9f3ca 100644 --- a/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageToolCall/ChatMessageToolCallBlock.svelte +++ b/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageToolCall/ChatMessageToolCallBlock.svelte @@ -12,6 +12,7 @@ import ChatMessageToolCallBlockExecShellCommand from './ChatMessageToolCallBlockExecShellCommand.svelte'; import ChatMessageToolCallBlockFileGlobSearch from './ChatMessageToolCallBlockFileGlobSearch.svelte'; import ChatMessageToolCallBlockGetDatetime from './ChatMessageToolCallBlockGetDatetime.svelte'; + import ChatMessageToolCallBlockGetInfo from './ChatMessageToolCallBlockGetInfo.svelte'; import ChatMessageToolCallBlockGrepSearch from './ChatMessageToolCallBlockGrepSearch.svelte'; import ChatMessageToolCallBlockReadFile from './ChatMessageToolCallBlockReadFile.svelte'; import ChatMessageToolCallBlockRunJavascript from './ChatMessageToolCallBlockRunJavascript.svelte'; @@ -40,6 +41,8 @@ {:else if section.toolName === BuiltInTool.GET_DATETIME} +{:else if section.toolName === BuiltInTool.GET_INFO} + {:else if section.toolName === BuiltInTool.READ_FILE} {:else if section.toolName === BuiltInTool.EDIT_FILE} diff --git a/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageToolCall/ChatMessageToolCallBlockEditFile.svelte b/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageToolCall/ChatMessageToolCallBlockEditFile.svelte index b990c3898b23..f8618864c953 100644 --- a/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageToolCall/ChatMessageToolCallBlockEditFile.svelte +++ b/tools/ui/src/lib/components/app/chat/ChatMessages/ChatMessage/ChatMessageToolCall/ChatMessageToolCallBlockEditFile.svelte @@ -1,7 +1,8 @@ {#snippet execShellTitle()} + {#if cwd} + {wdDisplay} + $ + {/if} + {#if highlightedCommandHtml} {@html highlightedCommandHtml} {:else} @@ -232,6 +247,23 @@