Skip to content

Pull requests: google/XNNPACK

New pull request New
190 Open 8,706 Closed
190 Open 8,706 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

Change i8mm to be a transpose_a kernel
#9196 opened Nov 22, 2025 by copybara-service bot Loading…
Force split_n to be at least 64 in dot subgraph.
#9194 opened Nov 21, 2025 by copybara-service bot Loading…
build: add support for generating sources for GN
#9191 opened Nov 21, 2025 by copybara-service bot Loading…
Optimize handling of slinky buffer objects
#9189 opened Nov 21, 2025 by copybara-service bot Loading…
Fix for varargs on fingerprint_id
#9187 opened Nov 21, 2025 by copybara-service bot Loading…
Fix data race in xnn_set_fingerprint
#9181 opened Nov 20, 2025 by copybara-service bot Loading…
Don't use enum value as variadic arguments
#9180 opened Nov 20, 2025 by copybara-service bot Loading…
Add SME1 support for qp8_f32_qc8w
#9178 opened Nov 20, 2025 by qti-vaiskv • Draft
5
Add Hexagon transpose kernels to YNNPACK
#9177 opened Nov 20, 2025 by copybara-service bot Loading…
Fingerprint deconvolution-nhwc kernels packing operations.
#9175 opened Nov 19, 2025 by copybara-service bot Loading…
Use the XNNPack packing fingerprints to invalidate the weight cache.
#9174 opened Nov 19, 2025 by copybara-service bot Loading…
Don't assume that shapes are correct when doing the static shape propagation.
#9162 opened Nov 17, 2025 by copybara-service bot Loading…
Enable f32 dots by default in YNNPACK
#9152 opened Nov 14, 2025 by copybara-service bot Loading…
Replace small constant tensors with static values.
#9149 opened Nov 13, 2025 by copybara-service bot Loading…
Be more strict with elided arithmetic op shapes.
#9139 opened Nov 12, 2025 by copybara-service bot Loading…
FIx logic in xnn_use_nr2 to match the previous behaviour.
#9138 opened Nov 12, 2025 by copybara-service bot Loading…
Internal code change
#9119 opened Nov 10, 2025 by copybara-service bot Loading…
Convert batch-matrix-multiply nodes with 2D weights to fully-connected nodes.
#9114 opened Nov 7, 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…
Improve build options to disable SSE microkernels
#9013 opened Oct 20, 2025 by copybara-service bot Loading…
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…
ProTip! Adding no:label will show everything without a label.