-
Notifications
You must be signed in to change notification settings - Fork 487
Pull requests: google/XNNPACK
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Fully enable fusion of elementwise and other ops with reductions in YNNPACK
#10200
opened May 8, 2026 by
copybara-service
Bot
Loading…
Use safe tail loads for inputs in maxpool kernels
#10199
opened May 8, 2026 by
wangw-1991
Contributor
Loading…
Make reference int2/int4 convert work with unaligned n.
#10195
opened May 7, 2026 by
copybara-service
Bot
Loading…
[gn] Add pthreadpool for the Chromium config
#10192
opened May 7, 2026 by
copybara-service
Bot
Loading…
Compute the converts that have static input during the optimization pass.
#10184
opened May 6, 2026 by
copybara-service
Bot
Loading…
Prepare static_reduce test for upcoming fp16 to fp32 rewrite.
#10183
opened May 6, 2026 by
copybara-service
Bot
Loading…
Don't call optimize in fp16 rewrite tests.
#10182
opened May 6, 2026 by
copybara-service
Bot
Loading…
Fix CMake build error caused by FXdiv binary directory collision
#10178
opened May 6, 2026 by
copybara-service
Bot
Loading…
Map Cortex-A320 to A510 kernel selection path
#10173
opened May 5, 2026 by
npitre
Contributor
Loading…
Update cpuinfo commit hash and sha256 checksum in XNNPACK and TFLite
#10158
opened May 4, 2026 by
copybara-service
Bot
Loading…
Port f16-dwconv2d-chw NEON microkernel templates to AVX512FP16
#10130
opened Apr 30, 2026 by
copybara-service
Bot
Loading…
Address review feedback: Add proper fp16 activation support in TFLite XNNPACK delegate without polluting CPU kernels
#10127
opened Apr 30, 2026 by
copybara-service
Bot
Loading…
Move xnn_get_rounded_size and related helpers to be private to runtime.c
#10112
opened Apr 28, 2026 by
copybara-service
Bot
Loading…
Speed up AMX/AVX512 tests by using NextPrime(nr >> 1) step for loop_n
#10075
opened Apr 25, 2026 by
copybara-service
Bot
Loading…
Unify 32-bit and 64-bit ARM benchmark sizes by aligning hardcoded cache constants.
#10044
opened Apr 23, 2026 by
copybara-service
Bot
Loading…
Add bf16-qd8 convert operator support
#10022
opened Apr 21, 2026 by
GregoryComer
Contributor
Loading…
sme dot: size kc for L2 stripe reuse, not L1 per-call stripe
#10005
opened Apr 19, 2026 by
kasper0406
Loading…
fix: dot/schedule_bench A_stride_m for transpose_a kernels
#10004
opened Apr 18, 2026 by
kasper0406
Loading…
1 task done
Previous Next
ProTip!
Exclude everything labeled
bug with -label:bug.