onnxruntime
Batch QMoE CPU QNBit expert GEMMs into grouped MLAS dispatches
#32668

Merged

Batch QMoE CPU QNBit expert GEMMs into grouped MLAS dispatches #32668

tianleiwu merged 2 commits into main from tlwu/qmoe-cpu-grouped-qnbit-gemm

Batch QMoE CPU QNBit expert GEMMs into grouped MLAS dispatches

8db7457a

tianleiwu requested a review from

copilot-pull-request-reviewer 6 days ago

copilot-pull-request-reviewer commented on 2026-09-17

Limit grouped QMoE staging memory

1fc1fe55

tianleiwu requested a review from

copilot-pull-request-reviewer 6 days ago

copilot-pull-request-reviewer commented on 2026-09-17

xadupre approved these changes on 2026-09-17

tianleiwu merged 4b728dd1 into main 5 days ago

tianleiwu deleted the tlwu/qmoe-cpu-grouped-qnbit-gemm branch 5 days ago

Reviewers

xadupre

Assignees

No one assigned

Labels

None yet

Milestone

No milestone