Graph degree equals intermediate graph degree bug fix#1834
Merged
rapids-bot[bot] merged 6 commits intorapidsai:mainfrom Feb 24, 2026
Merged
Conversation
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
irina-resh-nvda
added
non-breaking
dantegd
approved these changes
Feb 23, 2026
Member
dantegd
left a comment
dantegd
left a comment
There was a problem hiding this comment.
bug fix looks good to me, just had some small suggestions
tfeher
approved these changes
Feb 24, 2026
Contributor
tfeher
left a comment
tfeher
left a comment
There was a problem hiding this comment.
Thanks Irina for the fix, it looks good to me!
Contributor
|
/merge |
github-project-automation
bot
moved this to Done
in Vector Search, ML, & Data Mining Release Board
tfeher
pushed a commit
to Stardust-SJF/cuvs_rabitq
that referenced
this pull request
Mar 3, 2026
This PR fixes a cudaErrorIllegalAddress error in the iterative CAGRA graph build caused by an out-of-bounds memory access. The issue occurred because the algorithm allocated memory for intermediate_graph_degree neighbors but attempted to write one additional neighbor during the search phase. The fix updates the topk allocation to ensure buffers are sized for intermediate_graph_degree + 1. I also added a new test into NEIGHBORS_ANN_CAGRA_TEST_BUGS to reproduce the failure. It confirms the fix works correctly for float, int8_t, and uint8_t data types. Fixes rapidsai#1818 rapidsai#1818 Authors: - https://github.com/irina-resh-nvda Approvers: - Dante Gama Dessavre (https://github.com/dantegd) - Tamas Bela Feher (https://github.com/tfeher) URL: rapidsai#1834
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
3 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.
This PR fixes a cudaErrorIllegalAddress error in the iterative CAGRA graph build caused by an out-of-bounds memory access. The issue occurred because the algorithm allocated memory for intermediate_graph_degree neighbors but attempted to write one additional neighbor during the search phase. The fix updates the topk allocation to ensure buffers are sized for intermediate_graph_degree + 1.
I also added a new test into NEIGHBORS_ANN_CAGRA_TEST_BUGS to reproduce the failure. It confirms the fix works correctly for float, int8_t, and uint8_t data types.
Fixes #1818
#1818