diff --git a/benchmarks/single_node/agentic/kimik3_fp4_mi355x_mtp.sh b/benchmarks/single_node/agentic/kimik3_fp4_mi355x_mtp.sh new file mode 100755 index 0000000000..4dad02c02a --- /dev/null +++ b/benchmarks/single_node/agentic/kimik3_fp4_mi355x_mtp.sh @@ -0,0 +1,21 @@ +#!/usr/bin/env bash +set -euo pipefail + +# DSpark variant of kimik3_fp4_mi355x.sh. The MI355X launcher routes +# spec-decoding=mtp rows to this suffix, while the shared base recipe owns the +# model, AgentX replay, and eval plumbing. +# +# Keep this wrapper aligned with the upstream AMD Kimi-K3 DSpark reproducer. +# The first AgentX validation is deliberately GPU-only at c1 so a server or +# kernel failure has nowhere else to hide. +export SPEC_DECODE=true +export KV_CACHE_DTYPE="${KV_CACHE_DTYPE:-auto}" +export GPU_MEM_UTIL="${GPU_MEM_UTIL:-0.95}" +export MAX_NUM_SEQS="${MAX_NUM_SEQS:-16}" +export EVAL_MAX_NUM_SEQS="${EVAL_MAX_NUM_SEQS:-128}" +export MAX_NUM_BATCHED_TOKENS="${MAX_NUM_BATCHED_TOKENS:-4096}" +export LANGUAGE_MODEL_ONLY="${LANGUAGE_MODEL_ONLY:-false}" +export PREFIX_CACHING="${PREFIX_CACHING:-auto}" +export ENFORCE_EAGER="${ENFORCE_EAGER:-false}" + +exec "$(dirname "$0")/kimik3_fp4_mi355x.sh" "$@"