Skip to content

Pull requests: google/XNNPACK

New pull request New
261 Open 10,030 Closed
261 Open 10,030 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

Fully Connected: guard packed weights size calculation against overflow
#10606 opened Jun 27, 2026 by Alearner12 Loading…
1
Include arithmetic.h in dot_base.py
#10605 opened Jun 26, 2026 by copybara-service Bot Loading…
Update XNNPACK and its dependencies.
#10603 opened Jun 26, 2026 by copybara-service Bot Loading…
Add support for neon dot qd8_bf16_qb4w
#10602 opened Jun 26, 2026 by JakeStevens Loading…
2
fix off-by-one heap write in zephyr log output path
#10600 opened Jun 26, 2026 by aizu-m Contributor Loading…
Add fp32 dot kernels for Hexagon
#10598 opened Jun 26, 2026 by copybara-service Bot Loading…
Skip extent=1 loops in consumer nest during fusion.
#10596 opened Jun 25, 2026 by copybara-service Bot Loading…
guard partial-block bias and ksum writes in x64c4 avx256vnni packw
#10589 opened Jun 25, 2026 by aizu-m Contributor Loading…
Introduce XNN_NO_SANITIZE_INTEGER_OVERFLOW macro
#10587 opened Jun 25, 2026 by wangw-1991 Contributor Loading…
1
Pass quantized weights in MLD and fix Gemma 3 inference on WebGPU.
#10577 opened Jun 24, 2026 by copybara-service Bot Loading…
Apply XNN_NO_SANITIZE_FUNCTION to remaining type-erased call sites
#10576 opened Jun 24, 2026 by wangw-1991 Contributor Loading…
1
Add ARM f8mm8 dot kernels
#10574 opened Jun 24, 2026 by copybara-service Bot Loading…
Add NEONv8 microkernels for BF16/F16/F32 to QS8/QU8 vcvt.
#10573 opened Jun 24, 2026 by copybara-service Bot Loading…
cmake: avoid absolute path for libm in multilib builds
#10570 opened Jun 24, 2026 by jaeyoonjung Loading…
Cap maximum tensor sizes in YNNPACK reduce subgraph tests
#10562 opened Jun 23, 2026 by copybara-service Bot Loading…
Implement 2-bit packw templates for AVX2, SSSE3, NEONDOT, and Scalar
#10557 opened Jun 23, 2026 by copybara-service Bot Loading…
Fix required dot tiling
#10551 opened Jun 22, 2026 by copybara-service Bot Loading…
Fix qd8_f16_qb4w GEMM config getter always returning NULL on Arm
#10537 opened Jun 19, 2026 by outum1500 Loading…
1
ci: add cmake-windows-arm64-native job using windows-11-arm runner
#10528 opened Jun 18, 2026 by chinazhangchao Loading…
1
Test Tensor API StableHLO composite export
#10526 opened Jun 18, 2026 by copybara-service Bot Loading…
Add validation for StableHloComposite decomposition graph.
#10525 opened Jun 18, 2026 by copybara-service Bot Loading…
tensor api litert-lm executor
#10524 opened Jun 17, 2026 by copybara-service Bot Loading…
Add f32 x16 gemm microkernels for WASM Relaxed SIMD
#10521 opened Jun 17, 2026 by yolanda15 Contributor Loading…
1
Add Tensor API StableHLO composite op
#10506 opened Jun 16, 2026 by copybara-service Bot Loading…
Serialize StableHLO composites to TFLite
#10505 opened Jun 16, 2026 by copybara-service Bot Loading…
ProTip! Adding no:label will show everything without a label.