Skip to content

Issues: oneapi-src/oneDNN

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

34 Open 1,282 Closed
34 Open 1,282 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
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

s8 quantization and bias shows unexpected behavior question
#2269 opened Dec 13, 2024 by lucasreis1
@onednnsupporttriage
BF16 Softmax on EMR got 40% performance regression enhancement A feature or an optimization request platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#2237 opened Dec 2, 2024 by a3213105 v3.7
1
@dzarukin
6
Test test_bfloat16_plus_float fails on s390x help wanted platform:cpu-s390x IBM Z systems based on s390x architecture sighting Suspicious library behavior. Should be promoted to a bug when confirmed
#2228 opened Nov 26, 2024 by skriesch
1
[ARM] Support fp16 data type in JIT Reorder kernel enhancement A feature or an optimization request help wanted platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#2185 opened Oct 28, 2024 by dmitry-gorokhov
Extend support for JIT Backward Convolution Operators with ARM SVE 128bit enhancement A feature or an optimization request help wanted platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#2165 opened Oct 14, 2024 by snadampal
1
[ARM] Support 8bit/4bit weights decompression for Matmul primitive enhancement A feature or an optimization request help wanted platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#2081 opened Sep 4, 2024 by dmitry-gorokhov
4
RFC: Integrate Arm Compute Library (ACL) as an in-tree module into oneDNN question
#2076 opened Sep 3, 2024 by snadampal
5
[ARM] Suport 32-bits CPUs within ACL integration enhancement A feature or an optimization request help wanted platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#2069 opened Sep 2, 2024 by dmitry-gorokhov
1
[ARM] Support FP16 post-ops fusion into ACL kernels enhancement A feature or an optimization request help wanted platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#2067 opened Aug 30, 2024 by dmitry-gorokhov
2
Build with SYCL fails using intel/llvm compiler sighting Suspicious library behavior. Should be promoted to a bug when confirmed
#2035 opened Aug 13, 2024 by dvrogozh
@vpirogov
5
brg:sve_256 fails benchdnn accuracy tests bug A confirmed library bug help wanted platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#2008 opened Jul 24, 2024 by jondea
brgconv:sve_256 uses a lot of memory help wanted platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64 sighting Suspicious library behavior. Should be promoted to a bug when confirmed
#2007 opened Jul 24, 2024 by jondea
5
New/other Matrix multiplication algorithm implementation enhancement A feature or an optimization request help wanted platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#1971 opened Jun 20, 2024 by vineel96
11
GPU tests pass when they probably shouldn't bug A confirmed library bug help wanted platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#1961 opened Jun 13, 2024 by nwnk
4
Generic OpenCL kernels are broken enhancement A feature or an optimization request help wanted platform:gpu-intel Codeowner: @oneapi-src/onednn-gpu-intel
#1960 opened Jun 13, 2024 by nwnk
@nwnk
4
batchnorm requires consistent in- and output mem format_tags sighting Suspicious library behavior. Should be promoted to a bug when confirmed
#1944 opened Jun 4, 2024 by IngmarVoigt2
@yehudaorel
4
[ACL] 3D convolution kernel NEConv3D is not integrated enhancement A feature or an optimization request help wanted platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#1908 opened May 10, 2024 by alvoron
[Proposal] Add cpu alloc/free callback to support customlize memory alloctor APIs. enhancement A feature or an optimization request
#1898 opened May 7, 2024 by xuhancn
@mgouicem
4
GEMM API for efficient LLM inference with W8A16 enhancement A feature or an optimization request help wanted platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#1788 opened Jan 20, 2024 by oleotiger
3
Add support for dimension selection for layer normalization enhancement A feature or an optimization request help wanted
#1766 opened Dec 6, 2023 by WilliamTambellini
@WilliamTambellini
1
[nvidia|amd] Add missing synchronization bug A confirmed library bug help wanted platform:gpu-amd Codeowner: @oneapi-src/onednn-gpu-amd platform:gpu-nvidia Codeowner: @oneapi-src/onednn-gpu-nvidia
#1732 opened Oct 3, 2023 by densamoilov
3
[nvidia] batch normalization primitive fails correctness check bug A confirmed library bug platform:gpu-nvidia Codeowner: @oneapi-src/onednn-gpu-nvidia
#1725 opened Sep 14, 2023 by dzarukin
@dzarukin
2
Some unimplemented unary expressions? enhancement A feature or an optimization request help wanted
#1697 opened Aug 7, 2023 by WilliamTambellini
5
ctest test_concurrency intermittent error on AArch64 with gcc bug A confirmed library bug help wanted platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
#1690 opened Jul 21, 2023 by AmyWignall-arm
1
Bad perf for matmul of ba tensors help wanted platform:cpu-x64 Intel64/AMD64 processors. Codeowner: @oneapi-src/onednn-cpu-x64
#1667 opened Jun 9, 2023 by WilliamTambellini
5
ProTip! Add no:assignee to see everything that’s not assigned.