Skip to content

Pull requests: uxlfoundation/oneDNN

New pull request New
139 Open 3,705 Closed
139 Open 3,705 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

cpu: aarch64: prelu: add jit forward component:common platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#5299 opened Jun 11, 2026 by CodrutIrimieARM Loading…
3 tasks done
Extend GEMV code path to support bf16 and f16 data types platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#5297 opened Jun 11, 2026 by densamoilov Contributor Loading…
1
tests: benchdnn: fix grouped binary po no ref memory path component:tests Codeowner: @oneapi-src/onednn-arch
#5296 opened Jun 10, 2026 by mzhukova Contributor Loading…
@mzhukova
1
cpu: rv64: brgemm: add bf16 JIT kernel component:common platform:cpu-rv64 RISC-V third_party
#5295 opened Jun 10, 2026 by velonica0 Contributor • Draft
3 tasks done
cpu: rv64: brgemm: add f16 JIT kernel platform:cpu-rv64 RISC-V
#5294 opened Jun 10, 2026 by velonica0 Contributor Loading…
3 tasks done
4
Documented Level Zero minimal version and added runtime check component:common documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc governance third_party
#5291 opened Jun 10, 2026 by vpirogov Contributor • Draft
2 of 3 tasks
[GPU] Migrate RNN to matmul platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#5290 opened Jun 10, 2026 by echeresh Contributor Loading…
[GPU] Migrate inner product to matmul component:common platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#5289 opened Jun 10, 2026 by echeresh Contributor Loading…
1
Fixes and improvements for generic SYCL kernels component:build component:common component:examples 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
#5288 opened Jun 9, 2026 by dzarukin Contributor Loading…
5
build: introduced functions to handle build knobs behavior component:api Codeowner: @oneapi-src/onednn-arch component:build documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc
#5286 opened Jun 9, 2026 by vpirogov Contributor Loading…
11
[GPU][Xe3P] enforce xe3p+ prefetch count limitations platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#5282 opened Jun 9, 2026 by kealan-barbieri Contributor Loading…
4 tasks
11
graph: backend: dnnl: user scratchpad for gmlp component:graph-api Codeowner: @oneapi-src/onednn-graph
#5279 opened Jun 9, 2026 by TaoLv Contributor Loading…
3
benchdnn: refactor execution mode support (consolidate with graph driver) and introduce native_graph support component:graph-api Codeowner: @oneapi-src/onednn-graph component:tests Codeowner: @oneapi-src/onednn-arch
#5273 opened Jun 6, 2026 by dzarukin Contributor • Draft
1
[GPU] More threads/EU changes platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#5272 opened Jun 6, 2026 by Simonsays095 Contributor Loading…
6
cpu: aarch64: Enable s8:s8:s32 jit_int8_matmul component:common component:tests Codeowner: @oneapi-src/onednn-arch platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#5267 opened Jun 5, 2026 by aditew01 Contributor • Draft
10 tasks
[WIP][benchdnn] experimental auto-generated GPU nightly coverage component:tests Codeowner: @oneapi-src/onednn-arch documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc
#5260 opened Jun 4, 2026 by karturov Contributor • Draft
5 of 6 tasks
1
cpu: matmul: fix implicit narrowing conversions component:build platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#5254 opened Jun 4, 2026 by inteldimitrius Contributor • Draft
common: minor fixes for verbose component:common
#5246 opened Jun 3, 2026 by TaoLv Contributor Loading…
12
[GPU] JIT GEMM: consolidate problem properties in kernel/exec configs platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#5245 opened Jun 3, 2026 by echeresh Contributor • Draft
11
[draft, do not review] grouped matmul extension component:api Codeowner: @oneapi-src/onednn-arch component:common component:tests Codeowner: @oneapi-src/onednn-arch platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#5244 opened Jun 2, 2026 by mzhukova Contributor • Draft
@mzhukova
1
Test PR. Upconvert fp8 weights to xf16 in Matmul in case of xf16 activations for 3.10 (v3) backport component:common component:tests Codeowner: @oneapi-src/onednn-arch platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#5242 opened Jun 2, 2026 by asimonov1 Contributor • Draft
cpu: x64: matmul: Enable full tensor scales and zero points for 3D/4D matmul component:tests Codeowner: @oneapi-src/onednn-arch platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#5238 opened Jun 2, 2026 by inteldimitrius Contributor Loading…
15
[WIP] cpu: x64: fix brgemm deconv with uneven spatial and post-ops platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#5237 opened Jun 2, 2026 by tczeszun Contributor • Draft
[Do Not Review] examples: deconv + binary fusion cases component:common component:examples component:graph-api Codeowner: @oneapi-src/onednn-graph platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#5236 opened Jun 2, 2026 by TaoLv Contributor • Draft
asynchronous verbose mode for L0 runtime component:common platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#5232 opened Jun 1, 2026 by avmanerikar Contributor Loading…
1
ProTip! Add no:assignee to see everything that’s not assigned.