Skip to content

Pull requests: google/XNNPACK

New pull request New
225 Open 9,609 Closed
225 Open 9,609 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Optimize xnn_round_f32 for Hexagon HVX.
#10146 opened May 3, 2026 by copybara-service Bot Loading…
Added convert from qint8 to qcint8.
#10145 opened May 2, 2026 by copybara-service Bot Loading…
Disable subgraph_matcher_test when use_ynnpack is enabled.
#10139 opened May 1, 2026 by copybara-service Bot Loading…
Refactor extent handling in YNNPACK subgraph.
#10138 opened May 1, 2026 by copybara-service Bot Loading…
Split dots on k
#10134 opened May 1, 2026 by copybara-service Bot Loading…
Rewrite reduce(static_transpose(x)) into reduce(x)
#10133 opened Apr 30, 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…
Copybara import of the project:
#10122 opened Apr 29, 2026 by copybara-service Bot Loading…
Copybara import of the project:
#10115 opened Apr 29, 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…
Roll cpuinfo into XNNPACK and TFLite
#10036 opened Apr 22, 2026 by copybara-service Bot Loading…
Add bf16-qd8 convert operator support
#10022 opened Apr 21, 2026 by GregoryComer Contributor Loading…
1
sme dot: size kc for L2 stripe reuse, not L1 per-call stripe
#10005 opened Apr 19, 2026 by kasper0406 Loading…
4
fix: dot/schedule_bench A_stride_m for transpose_a kernels
#10004 opened Apr 18, 2026 by kasper0406 Loading…
1 task done
2
Fix xnn_get_rounded_size to always guarantee XNN_EXTRA_BYTES padding
#10001 opened Apr 17, 2026 by ssam18 Loading…
1
2
Add overflow checks to reduce-nd workspace sizing
#9988 opened Apr 17, 2026 by TristanInSec Loading…
3 tasks done
1
Add overflow detection to shape multiplication functions
#9987 opened Apr 17, 2026 by TristanInSec Loading…
3 tasks done
2
Refactor LUT fusion
#9973 opened Apr 14, 2026 by copybara-service Bot Loading…
[RVV] add rvv support for f16-vcmul
#9971 opened Apr 14, 2026 by ken-unger Contributor Loading…
6
[RVV] add rvv f32 kernel for ibilinear
#9964 opened Apr 14, 2026 by velonica0 Contributor Loading…
[RVV] add rvv f32 kernel for ppmm
#9962 opened Apr 14, 2026 by velonica0 Contributor Loading…
5
Add qd8-qb4w-bf16 scalar kernels
#9960 opened Apr 13, 2026 by GregoryComer Contributor Loading…
2
ProTip! Exclude everything labeled bug with -label:bug.