Skip to content

Pull requests: uxlfoundation/oneDNN

New pull request New
132 Open 3,608 Closed
132 Open 3,608 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

Matmul with compact C buffer and NUMA topology support component:common platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#5193 opened May 23, 2026 by ankalinin Contributor • Draft
1
xe: gated_mlp: enable gmlp primitive descriptor serialization component:common
#5192 opened May 23, 2026 by hidefromkgb Contributor Loading…
[GPU] Generalize GRF mode options platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#5191 opened May 22, 2026 by Simonsays095 Contributor Loading…
[wip, do not review] fixup for NVFP4 support in grouped matmul component:common component:tests Codeowner: @oneapi-src/onednn-arch documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#5190 opened May 22, 2026 by mzhukova Contributor • Draft
1
cmake: modify compilation to improve ccache hit rate component:build
#5188 opened May 21, 2026 by rjoursler Contributor Loading…
[do not review] benchdnn: remove all unimplemented logic component:common component:tests Codeowner: @oneapi-src/onednn-arch platform:gpu-generic Codeowner: @oneapi-src/onednn-gpu-generic platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#5187 opened May 21, 2026 by dzarukin Contributor • Draft
3
Upconvert fp8 weights to xf16 in Matmul in case of xf16 activations (v3) component:common component:tests Codeowner: @oneapi-src/onednn-arch platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#5186 opened May 21, 2026 by asimonov1 Contributor • Draft
1
cpu: riscv64: add rvv optimized gemm convolution platform:cpu-rv64 RISC-V
#5185 opened May 21, 2026 by strelkovkm • Draft
10 tasks
1
aarch64: fixes for jit_binary and post_op injectors component:tests Codeowner: @oneapi-src/onednn-arch platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#5184 opened May 21, 2026 by Sqvid Contributor Loading…
4 tasks done
[RFC] Drop internal GEMM API documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc
#5181 opened May 21, 2026 by echeresh Contributor Loading…
6
Fix labels for rfcs branch devops Github automation
#5180 opened May 20, 2026 by vpirogov Contributor Loading…
3
xe: gemm: fix cti application when enabled platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#5179 opened May 20, 2026 by Simonsays095 Contributor Loading…
3
benchdnn: styling and minor changes component:tests Codeowner: @oneapi-src/onednn-arch
#5178 opened May 20, 2026 by dzarukin Contributor Loading…
5
[GEMM] "Unknown" platform fix platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel third_party
#5176 opened May 20, 2026 by Simonsays095 Contributor Loading…
13
x64: sse41 conv: enable grayscale flat path and add regression test component:tests Codeowner: @oneapi-src/onednn-arch platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#5175 opened May 20, 2026 by azhai219 Loading…
2
cpu: rv64: fix relu alpha handling in default post-ops platform:cpu-rv64 RISC-V
#5174 opened May 20, 2026 by xiazhuozhao Member Loading…
rfcs: graph api scratchpad management documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc
#5173 opened May 20, 2026 by TaoLv Contributor Loading…
2
cpu: rv64: add JIT f32 support for ip, eltwise, bnorm and gnorm component:common platform:cpu-rv64 RISC-V
#5168 opened May 19, 2026 by xiazhuozhao Member • Draft
10 tasks
[TEST] fix grp post ops CL_OUT_OF_RESOURCES issue platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#5160 opened May 17, 2026 by riverlijunjie • Draft
10 tasks
cpu: rv64: matmul: add brgemm matmul for rv64 platform platform:cpu-rv64 RISC-V
#5157 opened May 15, 2026 by zhangjian29 Contributor Loading…
3 tasks done
11
cpu: aarch64: replace acl with kleidiai component:build component:common 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 platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64 third_party
#5156 opened May 14, 2026 by jondea Contributor • Draft
5
[GPU] fixup bad GEMM strategies platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#5152 opened May 13, 2026 by kealan-barbieri Contributor Loading…
2 of 4 tasks
11
[GPU] Xe3p/ARL-H GEMM Perf fixup platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#5147 opened May 12, 2026 by kealan-barbieri Contributor Loading…
3 of 5 tasks
4
cpu: aarch64: bnorm: improve SVE128 threading platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#5146 opened May 12, 2026 by keanucz Contributor Loading…
3 tasks done
8
rfcs: Simplify the AArch64 Stack by Replacing Compute Library with Arm KleidiAI documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc RFC A design document
#5145 opened May 12, 2026 by jondea Contributor Loading…
17
ProTip! Exclude everything labeled bug with -label:bug.