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: improve fp8 performance on NVL
- aarch64: brgemm: introduce a bfmmla kernel path
- x64: resampling: fix implicit narrowing conversions
- x64: binary: fix implicit narrowing conversions
- x64: reduction: fix implicit narrowing conversions
- cpu: aarch64: utils: fully redesign jit_io_helper
- x64: brgemm: widen JIT kernel internals to dim_t
- Enable per-k wei scales in brgemm for fp8
- x64: brgemm: widen infrastructure types to dim_t
- x64: matmul: reject select post-op with broadcast condition
- Docs
- C++ not yet supported