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
- xe: gemm: revert gemmstone API changes
- Enable bf16 ukernel path on aarch64
- xe: gemm: move gemm_with_po lower in impl list
- [draft for testing purposes, do not review] grouped gemm support
- Make DNNL_RISCV_USE_{RVV,ZVFH}_INTRINSICS overridable
- Deprecate f4_e3m0
- Example of dnnl::vanilla_rnn_backward
- [POC] xe: jit: gemm: nf4 weights decompression
- xe: softmax: specialized acceleration beyond xe_hpc
- tests: benchdnn: inputs: Update gpu fwks inputs
- Docs
- C++ not yet supported