Destroy nvexec continues_on storage on CUDA errors - #2190
Open
fallintoplace wants to merge 1 commit into
Open
Conversation
fallintoplace
marked this pull request as draft
August 11, 2026 16:50
fallintoplace
force-pushed
the
fix/nvexec-continues-on-error-cleanup
branch
from
August 11, 2026 16:57
b4d280f to
bb13404
Compare
Collaborator
|
why is this a draft PR? |
Collaborator
|
/ok to test bb13404 |
fallintoplace
marked this pull request as ready for review
August 11, 2026 20:16
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
cudaMemPrefetchAsyncto failWhy
continues_onconstructs non-trivial completion storage on the host before several CUDA calls. An early error returned without running the active completion value destructor, and the operation state only released the raw allocation.Cleanup now happens before the downstream completion operation because that operation may destroy the operation state.