onnxruntime
d86249ab - [CPU/MLAS] Add QMoE shared layout NVFP4/MXFP4 AVX-512 kernels and shared layout tests

Commit
10 days ago
[CPU/MLAS] Add QMoE shared layout NVFP4/MXFP4 AVX-512 kernels and shared layout tests Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Author
Parents
Loading