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: matmul: Disable small-shapes heuristic fallback to AVX‑512 for s8s8 matmul
- AArch64+SVE correctness failure in conv ( indirect_gemm:acl ) seen in pytorch unit test
- [backport][rls-v3.12] common: norm: differentiate scale and shift tensors
- add limited postops support (eltwise_swish, binary_mul) for grouped gemm in CPU ref and benchdnn
- build: graph: enable msvc c4244 and fix warnings
- [WIP, do not review] Polling-based asynchronous verbose mode for execution time-tracking
- [rls-v3.12] build: exclude Xe3p from default DNNL_ENABLE_PRIMITIVE_GPU_ISA
- [GPU] backport ref fixes to rls-v3.12-pc
- cpu: aarch64: run ACL post-op eltwise on current buffer
- xe: gemm: add Xe2 f16 kernel
- Docs
- C++ not yet supported