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
- cpu: x64: fix f32->fp8 double rounding and add native AVX10.2-aux down-converts WIP
- common: sum, concat: reject negative index in src_md
- Proposal of Supporting RISC-V Vendor-Specific ISA Extensions and Microarchitectural Optimizations
- fp32 OneDNN convolutions are slower OpenCL
- benchdnn: memory: return status from init_md
- Don't merge, debug
- xe: sdpa: add model-based forward tile selection
- cpu: x64: injectors: binary: fix select for negative conditions
- gpu: gemm: add 2-4 row u4 dot entries to the XeHPG catalog
- tests: benchdnn: graph: migrate gtests cases to benchdnn
- Docs
- C++ not yet supported