onnxruntime
Optimize CUDA QSA sparse attention indexing
#32656
Open

Optimize CUDA QSA sparse attention indexing #32656

copilot-swe-agent
Copilot Optimize CUDA QSA scoring and selection
ebc6bdfd
Copilot Add single-pass TopK coverage
ecabf39f
copilot-swe-agent copilot-swe-agent assigned kunal-vaishnavi kunal-vaishnavi 1 day ago
azure-pipelines
kunal-vaishnavi kunal-vaishnavi changed the base branch from main to copilot/copilotimplement-packed-sparse-attention-indexer 1 day ago
kunal-vaishnavi kunal-vaishnavi marked this pull request as ready for review 1 day ago
kunal-vaishnavi kunal-vaishnavi requested a review from copilot-pull-request-reviewer copilot-pull-request-reviewer 1 day ago
copilot-pull-request-reviewer
copilot-pull-request-reviewer commented on 2026-09-16
Copilot Merge remote-tracking branch 'origin/copilot/copilotimplement-packed-…
49ade0cb
Copilot Address CUDA QSA review feedback
8f506aab
copilot-swe-agent copilot-swe-agent requested a review from kunal-vaishnavi kunal-vaishnavi 1 day ago
Copilot Merge remote-tracking branch 'origin/copilot/copilotimplement-packed-…
51b64039
kunal-vaishnavi kunal-vaishnavi marked this pull request as draft 1 day ago
Copilot Implement profile-driven QSA selection optimizations
24bccfdf
Copilot Fix and format QSA radix selection
1593b64e
Copilot Include CUDA kernel scratch API
5b77441d
kunal-vaishnavi Fix sparse attention indexer CUDA kernel type
1f123608
github-actions
github-actions commented on 2026-09-17
Copilot Implement bounded exact QSA selection
d2de2583
Copilot Finalize bounded QSA decode path
a6c7873d
github-advanced-security
github-advanced-security commented on 2026-09-17
github-advanced-security
github-advanced-security commented on 2026-09-17
github-actions
github-actions commented on 2026-09-17
kunal-vaishnavi Support shared rotary caches in sparse indexer
15d73bae
kunal-vaishnavi Accept padding masks in sparse attention indexer
3d6bf1aa

Login to write a write a comment.

Login via GitHub