onnxruntime
[CUDA] Parallelize ArgMax/ArgMin over wide last axes
#32092

Merged

[CUDA] Parallelize ArgMax/ArgMin over wide last axes #32092

justinchuby merged 2 commits into microsoft:main from justinchuby:justinchuby/optimize-wide-argmax

[CUDA] Parallelize ArgMax/ArgMin over wide last axes

7b78c521

[CUDA] Fix int overflow in the cooperative arg reduction scan

0d85ddfa

justinchuby marked this pull request as ready for review 62 days ago

justinchuby requested a review from

tianleiwu 62 days ago

justinchuby removed review request from

tianleiwu 62 days ago

justinchuby requested a review from

copilot-pull-request-reviewer 62 days ago

justinchuby requested a review from

tianleiwu 62 days ago

copilot-pull-request-reviewer commented on 2026-08-14

tianleiwu approved these changes on 2026-08-15

justinchuby merged d4d792f5 into main 61 days ago

justinchuby deleted the justinchuby/optimize-wide-argmax branch 61 days ago

Reviewers

tianleiwu

Assignees

No one assigned

Labels

None yet

Milestone

No milestone