onnxruntime
Use CUDART_VERSION reduction compatibility in GQA attention
#28296

Merged

Use CUDART_VERSION reduction compatibility in GQA attention #28296

tianleiwu merged 2 commits into main from copilot/fix-cuda-13-build-error

Fix CUDA 13 build error: replace cub::Max/cub::Sum with local functor…

ba7d21a1

Use CUDART_VERSION reduction compatibility in GQA attention

2aa0c261

copilot-swe-agent assigned

copilot-swe-agent 8 days ago

copilot-swe-agent assigned

tianleiwu 8 days ago

copilot-swe-agent requested a review from

tianleiwu 8 days ago

tianleiwu approved these changes on 2026-04-30

tianleiwu marked this pull request as ready for review 8 days ago

sanaa-hamel-microsoft approved these changes on 2026-04-30

tianleiwu enabled auto-merge (squash) 8 days ago

tianleiwu merged 9c2b0c31 into main 8 days ago

tianleiwu deleted the copilot/fix-cuda-13-build-error branch 8 days ago

Reviewers

tianleiwu

Assignees

tianleiwu

Copilot

Labels

None yet

Milestone

No milestone