Skip to content

Pull requests: uxlfoundation/oneDNN

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

cpu: aarch64: run ACL post-op eltwise on current buffer platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#5101 opened Apr 30, 2026 by leoken01 Loading…
2 tasks done
[backport][rls-v3.12] conv #5073 backport backport component:common platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#5100 opened Apr 30, 2026 by henry-gar Contributor Loading…
[GPU] backport ref fixes to rls-v3.12-pc backport component:tests Codeowner: @oneapi-src/onednn-arch platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#5099 opened Apr 29, 2026 by dyoussif Contributor Loading…
[rls-v3.12] xe: address MSVC C4244 implicit type conversion warnings backport component:build component:common component:examples component:graph-api Codeowner: @oneapi-src/onednn-graph platform:gpu-generic Codeowner: @oneapi-src/onednn-gpu-generic platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel third_party
#5098 opened Apr 29, 2026 by atkassen Contributor Loading…
benchdnn: preparation for better skipped statuses accounting component:graph-api Codeowner: @oneapi-src/onednn-graph component:tests Codeowner: @oneapi-src/onednn-arch documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc
#5097 opened Apr 29, 2026 by dzarukin Contributor Loading…
xe: gemm: add Xe2 f16 kernel platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#5096 opened Apr 29, 2026 by Simonsays095 Contributor Loading…
cpu: aarch64: add f16 and bf16 support to jit_io_helper and jit_uni_binary platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#5092 opened Apr 29, 2026 by Sqvid Contributor Loading…
2 tasks done
doc: add Level Zero runtime materials component:api Codeowner: @oneapi-src/onednn-arch documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc
#5091 opened Apr 29, 2026 by dzarukin Contributor Loading…
common: add create/exec verbose on entry component:common
#5089 opened Apr 28, 2026 by echeresh Contributor Loading…
graph: backend: dnnl: exec: make host scalar copy async component:graph-api Codeowner: @oneapi-src/onednn-graph
#5088 opened Apr 28, 2026 by TaoLv Contributor Loading…
make test_ov tests documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc
#5087 opened Apr 28, 2026 by pmanczak Contributor Draft
[wip, do not review] quantization recipes update component:api Codeowner: @oneapi-src/onednn-arch component:common component:tests Codeowner: @oneapi-src/onednn-arch documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc
#5086 opened Apr 28, 2026 by mzhukova Contributor Draft
[Clang] Fix implicit conversion warning for opencl narrowing platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#5083 opened Apr 27, 2026 by h-sadia Contributor Loading…
cpu: x64: xbyak: update third-party xbyak to v7.37 third_party
#5081 opened Apr 27, 2026 by georgen117 Contributor Loading…
Add a new GEMV kernel to BRGEMM and enable it in MatMul platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#5077 opened Apr 24, 2026 by densamoilov Contributor Loading…
rfc: improve functional coverage processes documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc
#5071 opened Apr 22, 2026 by dzarukin Contributor Loading…
xe: remove with_punning platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#5067 opened Apr 22, 2026 by rjoursler Contributor Loading…
[WIP] [Graph] tests: benchdnn: in: graph: add f16 sample for GQA dropout bwd variant component:tests Codeowner: @oneapi-src/onednn-arch
#5063 opened Apr 21, 2026 by h-sadia Contributor Loading…
2 tasks
[WIP] xe: gated_mlp: improve performance of ukernel-based gmlp component:common component:tests Codeowner: @oneapi-src/onednn-arch platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#5059 opened Apr 21, 2026 by hidefromkgb Contributor Draft
ProTip! Filter pull requests by the default branch with base:main.