Skip to content

Pull requests: google/XNNPACK

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
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

Make F32->BF16 dot kernel work with dynamic shapes.
#9588 opened Feb 24, 2026 by copybara-service bot Loading…
Change fp16 softmax kernels to compute the sum as fp32
#9581 opened Feb 21, 2026 by copybara-service bot Loading…
Add SVE partial loads/stores to SIMD wrappers
#9575 opened Feb 19, 2026 by copybara-service bot Loading…
Randomize arithmetic tests for SIMD wrappers
#9568 opened Feb 18, 2026 by copybara-service bot Loading…
s32_mul for simd-hvx.h use mpyieo for upper 16 bits.
#9566 opened Feb 17, 2026 by copybara-service bot Loading…
Add scalar int4 reduction kernels
#9560 opened Feb 16, 2026 by copybara-service bot Loading…
Optimize ARM SME2 Dot-Product Kernel
#9531 opened Feb 10, 2026 by kasper0406 Loading…
Automated Code Change
#9490 opened Feb 5, 2026 by copybara-service bot Loading…
Switch sme2 job to Docker.
#9435 opened Jan 27, 2026 by copybara-service bot Loading…
Upgrade GitHub Actions for Node 24 compatibility
#9415 opened Jan 23, 2026 by salmanmkc Loading…
Add a caching strategy version number.
#9409 opened Jan 22, 2026 by copybara-service bot Loading…
a very good change.
#9408 opened Jan 22, 2026 by copybara-service bot Loading…
Add int8xint4 FC XNNPACK kernels for AVXVNNIINT8
#9406 opened Jan 21, 2026 by copybara-service bot Loading…
Relax IEEE compliance for hexagon which uses qfloat
#9384 opened Jan 13, 2026 by copybara-service bot Loading…
(DNS) Simple rewrite
#9383 opened Jan 12, 2026 by copybara-service bot Loading…
Test sum_squared reductions at subgraph level
#9374 opened Jan 9, 2026 by copybara-service bot Loading…
Simplify dot by separating the float and integer paths
#9340 opened Dec 22, 2025 by copybara-service bot Loading…
Update scalar GEMM kernels to use unaligned.h
#9293 opened Dec 12, 2025 by copybara-service bot Loading…
Rewrite transpose and stencil_copy
#9281 opened Dec 9, 2025 by copybara-service bot Loading…
ProTip! Add no:assignee to see everything that’s not assigned.