onnxruntime
[CUDA Plugin EP] Expose kernel sync stream for scratch allocation
#29244

Merged

[CUDA Plugin EP] Expose kernel sync stream for scratch allocation #29244

tianleiwu merged 6 commits into main from tlwu/concurrent_stream

tianleiwu requested a review from

copilot-pull-request-reviewer 33 days ago

tianleiwu requested a review from

edgchen1 33 days ago

copilot-pull-request-reviewer commented on 2026-06-24

Base automatically changed from tlwu/20260623/cuda_plugin_ep_cuda_graph_stream to main 32 days ago

yuslepukhin commented on 2026-06-25

Add KernelContext_GetSyncStream

39c5fe27

tianleiwu force pushed from e3d1cc9e to 39c5fe27 32 days ago

address feedbacks

58809a8d

add more tests

93871848

tianleiwu requested a review from

copilot-pull-request-reviewer 32 days ago

copilot-pull-request-reviewer commented on 2026-06-25

address feedback: stream-tag scratch from Stream(ctx); drop unused se…

35b43a73

tianleiwu requested a review from

copilot-pull-request-reviewer 31 days ago

tianleiwu requested a review from

yuslepukhin 31 days ago

copilot-pull-request-reviewer commented on 2026-06-25

address feedback: scope per-thread compute stream via RAII guard

1e7bf741

Merge remote-tracking branch 'origin/main' into tlwu/concurrent_stream

86011344

yuslepukhin approved these changes on 2026-06-26

tianleiwu merged 126ea8d3 into main 30 days ago

tianleiwu deleted the tlwu/concurrent_stream branch 30 days ago

Reviewers

yuslepukhin

edgchen1

Assignees

No one assigned

Labels

None yet

Milestone

No milestone