onnxruntime
MatMulNBits subgroup matrix 8x16x16: reduce robustness overhead
#33674

Merged

MatMulNBits subgroup matrix 8x16x16: reduce robustness overhead #33674

mirounga merged 1 commit into microsoft:main from jchen10:nbits_robustness

MatMulNBits subgroup matrix 8x16x16: reduce robustness overhead

342e8a52

jchen10 requested a review from

copilot-pull-request-reviewer 5 days ago

copilot-pull-request-reviewer commented on 2026-10-28

mirounga requested a review from

mirounga 5 days ago

mirounga approved these changes on 2026-10-28

mirounga merged 0dacf7ee into main 5 days ago

Reviewers

mirounga

Assignees

No one assigned

Labels

None yet

Milestone

No milestone