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
- [WIP] Replace gemm with matmul in RNN for fp32 on avx512
- [GPU] Update fwks input files
- cpu: x64: brgconv: inp buffer size reduction
- cpu: x64: matmul: dispatch shapes with small K to gemm
- cpu: enable avx10.2 by default
- cpu: x64 brgemm: fix for destination data check
- [WIP] gpu: intel: add Level Zero backend
- benchdnn: cold cache improvement
- cpu: arch64: Support brdgmm convolution with destination int8/int32
- gpu: cuda: Fix matmul queue recording
- Docs
- C++ not yet supported