onnxruntime
[CUDA] Optimize FlashDecode split planning for local-window GQA
#29161
Merged

[CUDA] Optimize FlashDecode split planning for local-window GQA #29161

tianleiwu
tianleiwu Optimize FlashDecode split planning for local-window GQA
1e86cf4e
tianleiwu tianleiwu changed the title Optimize FlashDecode split planning for local-window GQA [CUDA] Optimize FlashDecode split planning for local-window GQA 26 days ago
tianleiwu tianleiwu requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 26 days ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-06-19
kunal-vaishnavi
kunal-vaishnavi approved these changes on 2026-06-19
kunal-vaishnavi kunal-vaishnavi merged 89a23d8b into main 26 days ago
kunal-vaishnavi kunal-vaishnavi deleted the tlwu/20260618/flash_decode_split_local_window branch 26 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone