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
- Fix backward SDPA descriptor validation
- [GPU] Enable mn group bdpas scales
- [WIP] xe: gemm: dsl: pull down from upstream
- gpu: intel: sdpa: fallback f32 sdpa w/ explicit mask on more platforms
- x64: reduce scalar binary post-op overhead
- gpu: intel: jit: gemm: bound quantization buffers in gemmCheck32
- benchdnn brgemm: fix driver segfaults for binary and prelu postops
- cpu: x64: dispatch matmul and convolution to avx10_2_amx_2
- cpu: aarch64: accelerate Swish with polynomial approximations
- benchdnn: sdpa: account for reference memory in memory check
- Docs
- C++ not yet supported