onnxruntime
Validate PackedMultiHeadAttention token offsets
#33098
Merged

Validate PackedMultiHeadAttention token offsets #33098

apsonawane
apsonawane Validate PackedMultiHeadAttention token offsets
8ff1b613
apsonawane apsonawane requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 22 days ago
apsonawane apsonawane enabled auto-merge (squash) 22 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-10-05
apsonawane Support token validation during CUDA graph capture
5e793ee9
tianleiwu
tianleiwu requested changes on 2026-10-05
apsonawane Widen token validation index progression
5421f440
tianleiwu
tianleiwu requested changes on 2026-10-05
apsonawane Guard CUDA token validation regression
69b7be2e
tianleiwu
tianleiwu approved these changes on 2026-10-05
apsonawane apsonawane merged ca3e9482 into main 21 days ago
apsonawane apsonawane deleted the fix/packed-mha-token-offset-validation branch 21 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone