Add workaround for cuTENSOR 2.3.x - 2.5.x OOB host write bug impacting large problem sizes#113
Merged
romerojosh merged 3 commits intomainfrom Mar 12, 2026
Merged
Conversation
…g large problem sizes. Signed-off-by: Josh Romero <joshr@nvidia.com>
Signed-off-by: Josh Romero <joshr@nvidia.com>
Signed-off-by: Josh Romero <joshr@nvidia.com>
Collaborator
Author
|
/build |
|
🚀 Build workflow triggered! View run |
|
✅ Build workflow passed! View run |
romerojosh
added a commit
that referenced
this pull request
Mar 12, 2026
…g large problem sizes (#113) * Add workaround for cuTENSOR 2.3.x - 2.5.x OOB host write bug impacting large problem sizes. Signed-off-by: Josh Romero <joshr@nvidia.com> * Formatting. Signed-off-by: Josh Romero <joshr@nvidia.com> * Bump cuDecomp version to prep for hotfix release. Signed-off-by: Josh Romero <joshr@nvidia.com> --------- Signed-off-by: Josh Romero <joshr@nvidia.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #112.
This PR adds a check that detects the affected cuTENSOR versions at runtime via
cutensorGetVersion()and pre-splits the input/output tensors into chunks below theINT32_MAX/2threshold before calling cuTENSOR, avoiding the problematic code path described in #112. No behavior change occurs for unaffected cuTENSOR versions or for tensors below the split threshold.