onednn
https://github.com/oneapi-src/onednn
C++
oneAPI Deep Neural Network Library (oneDNN)
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
C++ not yet supported2 Subscribers
Add a CodeTriage badge to onednn
Help out
- Issues
- x64: matmul: fuse select post-op with scalar-broadcast src1 on avx512_core
- cpu: rv64: refactor matmul/conv using a multi-level IR component system
- Optimize the oneDNN matmul (brgemm) to close the gap with AMX intrinsics for DeepSeek R1 shapes MoE on GNR
- [GPU] JIT GEMM: support robust jit gemm kernel override via primitive attribute
- rfcs: Add RFC for public SDPA primitive
- x64: matmul: testing coverage
- Rename isa_has_masks() -> isa_has_evex()
- benchdnn: add hard-timeout monitor wrapper (benchdnn.py)
- ci: dispatch torch-xpu-ops acceptance from oneDNN make test_pt comment
- [WIP][benchdnn] experimental auto-generated GPU nightly coverage
- Docs
- C++ not yet supported