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
- bnorm can fail with out_of_memory on cpu
- xe: gemm: reintroduce bf16 kernel for Xe2
- We need better ways to extend memory layouts to support vector length agnosticism on RISC-V vector systems
- common: verbose: drop extra CSV header column
- gtests: graph: api: test concurrent execution
- Temporary fix nightly crash for large l_pad failing test
- Enable GEMV code path to brgemm matmul for f32/avx512
- [Doc] Update documentation on "flags" parameter in dnnl_lstm_backward_primitive_desc_create()
- Enable bf16 ukernel path on aarch64
- GPU: GEMM: update accumulation + quantization
- Docs
- C++ not yet supported