Skip to content

Pull requests: uxlfoundation/oneDNN

New pull request New
Clear current search query, filters, and sorts
70 Open 474 Closed
70 Open 474 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

xe: jit: conv: improve walk order heuristic backport platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#4292 opened Nov 5, 2025 by rjoursler Loading…
1
rfcs: graph api: support rms norm RFC A design document
#4291 opened Nov 5, 2025 by rongzha1 Loading…
xe: jit: break codegen dependency on func_impl_t platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#4282 opened Nov 4, 2025 by rjoursler Loading…
cpu: rv64: postops: add rvv postops eltwise op support platform:cpu-rv64 RISC-V
#4281 opened Nov 4, 2025 by zhangjian29 Loading…
3 tasks done
rfcs: gpu: add Level Zero runtime platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel RFC A design document
#4275 opened Nov 3, 2025 by spalicki Loading…
@spalicki
cpu: x64: matmul: brgemm: add zp per_oc support for dst and wei platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#4263 opened Oct 31, 2025 by pmanczak Loading…
cpu: rv64: gemm: Implemented variable loop unrolling for GEMM platform:cpu-rv64 RISC-V
#4258 opened Oct 31, 2025 by xiazhuozhao Loading…
3 tasks done
2
[GPU] Dynamic Dst Scale component:common platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#4245 opened Oct 30, 2025 by kealan-barbieri Loading…
1 of 2 tasks
11
Ryo not rio/test 3.10 convs backport component:common devops Github automation platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#4230 opened Oct 28, 2025 by Ryo-not-rio • Draft
Backport: conv: enable SVE128 convolutions backport component:api Codeowner: @oneapi-src/onednn-arch component:common component:tests Codeowner: @oneapi-src/onednn-arch platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#4225 opened Oct 28, 2025 by Ryo-not-rio • Draft
3
cpu: rv64: reorder: fp32 to u8 for matmul platform:cpu-rv64 RISC-V
#4200 opened Oct 24, 2025 by zhangfeiv0 Loading…
2 tasks done
Georgena/hybrid cache topology component:common platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#4194 opened Oct 22, 2025 by georgen117 • Draft
10 tasks
12
cpu:ppc64: implemented reorder kernel for s8 to s8 and f32 to u8 platform:cpu-ppc64 PowerPC
#4193 opened Oct 22, 2025 by Tiwari-Avanish • Draft
[GPU] a non-blocking, profiler-based verbose mode for execution time tracking component:common documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#4187 opened Oct 22, 2025 by avmanerikar Loading…
1 of 3 tasks
5
gpu: conv: jit: add early slm check to skip ngen jitting platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#4184 opened Oct 22, 2025 by ZackyLake Loading…
2 of 10 tasks
2
cpu: rv64: add rvv softmax implementation using rvv intrinsics component:common platform:cpu-rv64 RISC-V
#4173 opened Oct 21, 2025 by zhangjian29 Loading…
3 tasks done
cpu: rv64: add rvv batch normalization implementation using rvv intrinsics component:common platform:cpu-rv64 RISC-V
#4158 opened Oct 16, 2025 by zhangjian29 Loading…
3 tasks done
eigen: Fix Eigen version comparison. component:tests Codeowner: @oneapi-src/onednn-arch
#4112 opened Oct 10, 2025 by cantonios Loading…
3 tasks done
3
Enable GEMV code path to brgemm matmul for f32/avx512 platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#4111 opened Oct 10, 2025 by asimonov1 • Draft
xe: gemm: upstream MLPerf kernels for llama2-70b and llama3-8b platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#4048 opened Sep 30, 2025 by PershingSquare Loading…
3
cpu: x64: matmul: updated threading scheme for reduction platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#4036 opened Sep 30, 2025 by yair-obodovsky Loading…
cpu: x64: matmul: updated AMX blocking heuristics to support B transform platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#4032 opened Sep 30, 2025 by yair-obodovsky Loading…
5
WIP: POC with dropout attribute extensions 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
#4031 opened Sep 30, 2025 by mgouicem • Draft
rfcs: extend dropout with offset, s64 and host_scalars RFC A design document
#4030 opened Sep 30, 2025 by mgouicem Loading…
3
Update fwks KPIs component:tests Codeowner: @oneapi-src/onednn-arch
#3953 opened Sep 16, 2025 by kjackiew Loading…
2 tasks
24
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.