Skip to content

Pull requests: google/XNNPACK

New pull request New
188 Open 8,623 Closed
188 Open 8,623 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

Don't pass values to xnn_define_.* functions that could be overwritten if the subgraph nodes/values are re-allocated.
#9111 opened Nov 6, 2025 by copybara-service bot Loading…
Call xnn_define_all_input_shapes_const() on the subgraph since we are not modifying any of the shapes between the subgraph creation and reshape.
#9109 opened Nov 5, 2025 by copybara-service bot Loading…
Add a missing shim for xnn_define_all_input_shapes_static in ynnpack.
#9108 opened Nov 5, 2025 by copybara-service bot Loading…
Added subgraph level static_reduce benchmark.
#9106 opened Nov 5, 2025 by copybara-service bot Loading…
Added 2-bit qc2w variant for FullyConnected.
#9105 opened Nov 5, 2025 by copybara-service bot Loading…
Handle broadcasting with broadcast dimensions in slinky
#9103 opened Nov 5, 2025 by copybara-service bot Loading…
HVX v69 use FARF for output instead of printf
#9102 opened Nov 5, 2025 by copybara-service bot Loading…
Split large fully-connected nodes along k.
#9078 opened Nov 2, 2025 by copybara-service bot Loading…
Clean up unnecessary codepaths from operator-run
#9075 opened Nov 2, 2025 by copybara-service bot Loading…
Fingerprint convolution-nhwc kernels packing operations.
#9044 opened Oct 24, 2025 by copybara-service bot Loading…
Detect the number of SMCUs on Linux/Android
#9028 opened Oct 22, 2025 by doviethoa-at-work Loading…
Build option for disable_avx
#9025 opened Oct 22, 2025 by copybara-service bot Loading…
Copybara import of the project:
#9017 opened Oct 21, 2025 by copybara-service bot Loading…
Improve build options to disable SSE microkernels
#9013 opened Oct 20, 2025 by copybara-service bot Loading…
Add support for fp16 iGEMM with SME2
#9005 opened Oct 20, 2025 by JonathanC-ARM Loading…
13
Add pipelining to SME kernels
#8979 opened Oct 15, 2025 by copybara-service bot Loading…
Fingerprint convolution-nchw kernels packing operations.
#8954 opened Oct 10, 2025 by copybara-service bot Loading…
Fingerprint gemm kernel packing operations.
#8933 opened Oct 2, 2025 by copybara-service bot Loading…
Add a new fingerprinting method for XNNPack weight cache.
#8923 opened Sep 30, 2025 by copybara-service bot Loading…
Flip transpose of (slow) dynamic goi right-hand GEMM operands.
#8917 opened Sep 26, 2025 by copybara-service bot Loading…
Add int8xint4 FC XNNPACK kernel for AMX
#8910 opened Sep 24, 2025 by copybara-service bot Loading…
Rename XNN_FLAG_SLINKY_ENABLED to XNN_FLAG_USE_SLINKY to match the corresponding macros.
#8906 opened Sep 23, 2025 by copybara-service bot Loading…
Add int8xint4 FC XNNPACK kernel for Hexagon HVX
#8896 opened Sep 19, 2025 by copybara-service bot Loading…
Remove spurious transposes of non-static GEMM weights.
#8891 opened Sep 16, 2025 by copybara-service bot Loading…
Enable F16 for cpus with F16C instead of AVX2
#8889 opened Sep 15, 2025 by copybara-service bot Loading…
ProTip! Type g i on any issue or pull request to go back to the issue listing page.