onnxruntime
[CUDA] Address feedback for block-scaled MatMul and MoE GEMV
#29910

Merged

[CUDA] Address feedback for block-scaled MatMul and MoE GEMV #29910

tianleiwu merged 6 commits into main from tlwu/20260727/address_pr_feedbacks

refactoring

4f8380f0

Add edge test cases for MatMulBlockQuantizedFp4Weight

3797869a

tianleiwu requested a review from

copilot-pull-request-reviewer 30 days ago

copilot-pull-request-reviewer commented on 2026-07-27

tianleiwu requested a review from

kunal-vaishnavi 30 days ago

kunal-vaishnavi commented on 2026-07-27

type const => const type

976d3247

tianleiwu requested a review from

kunal-vaishnavi 29 days ago

tianleiwu enabled auto-merge (squash) 29 days ago

kunal-vaishnavi dismissed these changes on 2026-07-29

fix build error

7d5fbdee

Merge remote-tracking branch 'origin/main' into tlwu/20260727/address…

ae583064

tianleiwu dismissed their stale review via ae583064 28 days ago

format

546152c2

tianleiwu requested a review from

kunal-vaishnavi 28 days ago

kunal-vaishnavi approved these changes on 2026-07-30

tianleiwu merged e2856db8 into main 28 days ago

tianleiwu deleted the tlwu/20260727/address_pr_feedbacks branch 28 days ago

Reviewers

kunal-vaishnavi

Assignees

No one assigned

Labels

None yet

Milestone

No milestone