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
- [rls-v3.11] graph: re-enable sdpa training bwd
- cpu: aarch64: Support for Bf16 LUT Eltwise Operations
- graph: re-enable sdpa training bwd
- cpu: x64: binary injector: per_mb_spatial non-trivial stride support
- [WIP] cpu: x64 : mxfp4 weights support for matmul
- [rls-v3.12-pc] xe: ukernel: fix alignment for non-2D loads
- cpu: rv64: switch layernorm fwd to fully JIT-based RVV kernels
- xe: ir: reorder: use int8 intermediate for int4 conversion
- cpu: matmul: Enable int8 matmul weight decompression
- update xbyak library to v7.35.3
- Docs
- C++ not yet supported