onnxruntime
d86249ab
- [CPU/MLAS] Add QMoE shared layout NVFP4/MXFP4 AVX-512 kernels and shared layout tests
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
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>
References
#33450 - [CPU/MLAS] Add QMoE shared layout INT4/INT3/FP4 AVX-512 & AVX2 kernels, FileExpertStore, and direct CPU QMoE
Author
tianleiwu
Parents
cf003059
Loading