Skip to content

Pull requests: google/XNNPACK

New pull request New
259 Open 10,171 Closed
259 Open 10,171 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

Add the golden_parity global configuration for architecture-neutral golden tests.
#10747 opened Jul 14, 2026 by copybara-service Bot Loading…
Add dynamic shapes to concatenated_mixed_dot_bench
#10746 opened Jul 14, 2026 by copybara-service Bot Loading…
Inject explicit architecture-neutral arithmetic flags and golden parity defines directly into the ARCore unit test BuildableUnit.
#10745 opened Jul 14, 2026 by copybara-service Bot Loading…
Support enforcing architecture-neutral baseline data cache sizes for Eigen GEMM operations.
#10744 opened Jul 14, 2026 by copybara-service Bot Loading…
Re-enable packw optimized kernels and refine ISA guards in GEMM configs.
#10743 opened Jul 14, 2026 by copybara-service Bot Loading…
Fix support for explicitly disabling x86 SIMD and matrix multiplication architecture extensions.
#10742 opened Jul 14, 2026 by copybara-service Bot Loading…
Implement a transformer layer for Gemma 4.
#10741 opened Jul 13, 2026 by copybara-service Bot Loading…
Implement attention layer for Gemma 4.
#10740 opened Jul 13, 2026 by copybara-service Bot Loading…
Initial Gemma 4 config.
#10739 opened Jul 13, 2026 by copybara-service Bot Loading…
Implement an XNNPack runner for Gemma 4.
#10738 opened Jul 13, 2026 by copybara-service Bot Loading…
Implement the Gemma 4 graph build.
#10737 opened Jul 13, 2026 by copybara-service Bot Loading…
Import safetensor loader for Gemma 4.
#10736 opened Jul 13, 2026 by copybara-service Bot Loading…
Add a transposed decode1 attention benchmark.
#10735 opened Jul 13, 2026 by copybara-service Bot Loading…
Implement Rotary Position Embedding (RoPE) operation for Gemma 4.
#10734 opened Jul 13, 2026 by copybara-service Bot Loading…
Implement feed forward network.
#10732 opened Jul 13, 2026 by copybara-service Bot Loading…
Support static FP32 bias for FP16 depthwise convolution 2D in XNNPACK subgraph.
#10730 opened Jul 13, 2026 by copybara-service Bot Loading…
[gn] add neoni8mmbf16 kernels
#10728 opened Jul 13, 2026 by copybara-service Bot Loading…
Implement RMSNorm for Gemma 4.
#10726 opened Jul 13, 2026 by copybara-service Bot Loading…
Force LockedBufferSpan data access through an lvalue.
#10722 opened Jul 13, 2026 by copybara-service Bot Loading…
Added unit tests to ensure the match of Gemma4 Tensor API TFLite execution to LiteRT-LM
#10718 opened Jul 13, 2026 by copybara-service Bot Loading…
Fix quantization export to allow explicit q/ dq nodes in the graph
#10717 opened Jul 13, 2026 by copybara-service Bot Loading…
Enable quantized Tensor API TFLite lowering from the python binding
#10716 opened Jul 13, 2026 by copybara-service Bot Loading…
Add AVX512 FP32 dot kernel specialized for k=16
#10713 opened Jul 12, 2026 by copybara-service Bot Loading…
Fix integer overflow in NHWC convolution kernel size calculation
#10710 opened Jul 11, 2026 by YellowJune Loading…
6
litert/tensor/arithmetic.h: bounds-check axis and index values before vector subscript
#10702 opened Jul 10, 2026 by destro4evr-rgb Contributor Loading…
ProTip! Filter pull requests by the default branch with base:master.