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: jit: prefer xehpc f16 kernel for ~300-row gemms
- gpu: gemm: fix stale flag reuse in k-loop cooldown guards
- cpu: aarch64: threading and cache optimization for jit int8 matmul
- RFC: RV64 vendor-specific ISA and microarchitecture support
- Add MSVC host compiler support for SYCL configuration
- Added workflow to publish binary builds for Github releases
- benchdnn: inputs: matmul: move grouped CI coverage to generated
- graph: bound softmax and layernorm axis in shape inference
- benchdnn: fix CSV field escaping and document report columns
- xe: gemm: jit: fix early 2D quant k remainder for sdpa
- Docs
- C++ not yet supported