onnxruntime
[CUDA] Run FlashAttention regression test only when FlashAttention is available
#27206

Merged

[CUDA] Run FlashAttention regression test only when FlashAttention is available #27206

hariharans29 merged 3 commits into main from hari/fix_GQA_build_errors

Run FLashAttention regression test only when FlashAttention is available

4e9cc077

github-actions commented on 2026-01-29

Update onnxruntime/test/python/transformers/test_gqa.py

970418d3

hariharans29 requested a review from

tianleiwu 10 days ago

hariharans29 requested a review from

copilot-pull-request-reviewer 10 days ago

copilot-pull-request-reviewer commented on 2026-01-29

tianleiwu approved these changes on 2026-01-29

hariharans29 enabled auto-merge (squash) 10 days ago

disabled auto-merge 10 days ago
Manually disabled by user

titaiwangms approved these changes on 2026-01-30

Merge remote-tracking branch 'origin' into hari/fix_GQA_build_errors

65c07068

hariharans29 enabled auto-merge (squash) 9 days ago

hariharans29 merged 260a48c8 into main 5 days ago

hariharans29 deleted the hari/fix_GQA_build_errors branch 5 days ago

Reviewers

titaiwangms

tianleiwu

github-actions

Assignees

No one assigned

Labels

None yet

Milestone

No milestone