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
- extend grouped gemm to support grouped (variable idx 1) by grouped (variable idx 0) into 3D dense
- [Do Not Review] examples: deconv + binary fusion cases
- cpu: x64: matmul: Enable full tensor scales and zero points for 3D/4D matmul
- asynchronous verbose mode for L0 runtime
- rfc: appendix to improve functional coverage - implementation proposals
- [rls-v3.12] graph: backend: dnnl: passes: fused_sdpa supports reorder
- github: workflows autotrigger for ov tests
- Matmul with compact C buffer and NUMA topology support
- [do not review] benchdnn: remove all unimplemented logic
- Upconvert fp8 weights to xf16 in Matmul in case of xf16 activations (v3)
- Docs
- C++ not yet supported