Skip to content

Pull requests: uxlfoundation/oneDNN

New pull request New
104 Open 1,879 Closed
104 Open 1,879 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: conv: drop incorrect move backport platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#3370 opened May 29, 2025 by echeresh Loading…
common: verbose: add SDPA attention scale info component:common
#3369 opened May 29, 2025 by atkassen Loading…
@atkassen
[GPU][GEMM][rls-v3.9-pc] Align v3.9-pc GEMM Perf backport platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#3368 opened May 29, 2025 by kealan-barbieri Loading…
1 of 3 tasks
2
cpu: enable eltwise support for fp8 on avx10.2 bug A confirmed library bug component:common platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#3366 opened May 29, 2025 by xuxinzen Loading…
1
tests: gtest: add check for khr_get_default_context component:tests Codeowner: @oneapi-src/onednn-arch platform:gpu-amd Codeowner: @oneapi-src/onednn-gpu-amd
#3365 opened May 29, 2025 by spalicki Loading…
@spalicki
ci: aarch64: Add manual trigger to the performance aarch64 workflow devops Github automation
#3364 opened May 29, 2025 by gausah-arm Loading…
cpu: aarch64: extend brgemm conv to sve_128 component:common platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#3363 opened May 29, 2025 by jondea Loading…
3 tasks done
11
graph pattern name refactor component:graph-api Codeowner: @oneapi-src/onednn-graph component:tests Codeowner: @oneapi-src/onednn-arch
#3362 opened May 29, 2025 by ShanSimu Loading…
@ShanSimu
cpu: matmul: fix select postop failures for scalar broadcasting platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#3361 opened May 29, 2025 by avmanerikar Loading…
1
xehpg: jit: gemm: reduce m tile size for int4 * int8 gemv strategies backport platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#3360 opened May 28, 2025 by petercad Loading…
xehpg: jit: gemm: reduce m tile size for int4 * int8 gemv strategies backport platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#3359 opened May 28, 2025 by petercad Loading…
xe: softmax: specialized acceleration beyond xe_hpc platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#3358 opened May 28, 2025 by pv-pterab-s • Draft
2
xehpg: jit: gemm: reduce m tile size for int4 * int8 gemv strategies platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#3357 opened May 28, 2025 by petercad Loading…
4
gpu:cuda: Fix matmul queue recording platform:gpu-nvidia Codeowner: @oneapi-src/onednn-gpu-nvidia
#3352 opened May 28, 2025 by EwanC • Draft
cpu: aarch64: matmul: addition of JIT bf16 kernel 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
#3350 opened May 28, 2025 by vishwascm Loading…
6
aarch64: matmul: Enabling variable N block sizes for jit int8 matmul 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
#3348 opened May 28, 2025 by Shreyas-fuj Loading…
9
xe: softmax: restrict new kernel from PR2525 for only xe_hpc platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#3339 opened May 27, 2025 by pv-pterab-s • Draft
8
benchdnn: memory: gpu: enable support for RNG memory fill component:tests Codeowner: @oneapi-src/onednn-arch platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#3336 opened May 27, 2025 by yehudaorel Loading…
2 tasks done
2
build: add call to find_package(OpenCL) in config.cmake.in component:build
#3335 opened May 27, 2025 by AD2605 Loading…
3
graph: backend: dnnl: sdpa v1 kernel support quantize SDPA and backend refactor component:graph-api Codeowner: @oneapi-src/onednn-graph
#3334 opened May 27, 2025 by xiang1guo Loading…
3 tasks done
@xiang1guo
Enable FP16 ACL kernels that accumulate into FP32 platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#3332 opened May 27, 2025 by renato-arantes Loading…
3 tasks done
7
tests: benchdnn: graph: add skip logic for NV GPU component:graph-api Codeowner: @oneapi-src/onednn-graph component:tests Codeowner: @oneapi-src/onednn-arch
#3331 opened May 26, 2025 by Jiexin-Zheng Loading…
@Jiexin-Zheng
example: add backward propagation to vanilla rnn example component:examples
#3329 opened May 26, 2025 by raistefintel Loading…
1 of 2 tasks
11
various improvements for examples documentation component:examples documentation A request to change/fix/improve the documentation. Codeowner: @oneapi-src/onednn-doc
#3326 opened May 23, 2025 by mzhukova Loading…
@mzhukova
6
xe: sdpa: add support for reusable sdpa component:tests Codeowner: @oneapi-src/onednn-arch platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#3322 opened May 23, 2025 by syurkevi Loading…
2 tasks
3
ProTip! Adding no:label will show everything without a label.