[BUG] Fix graph index sorting in CAGRA graph build by NN Descent #763
Merged
rapids-bot[bot] merged 7 commits intorapidsai:branch-25.04from Mar 25, 2025
Merged
Conversation
enp1s0
added
bug
tfeher
added
non-breaking
…o fix-cagra-build-nnd-sort
Contributor
|
/merge |
moccch
pushed a commit
to Supercomputing-System-AI-Lab/VecFlow
that referenced
this pull request
Apr 11, 2025
Graph neighbor sorting after the initial kNN graph construction by NN descent always uses the L2 norm, while NN descent also supports the inner product and cosine distance. This PR adds support for the inner product and cosine distance in graph neighbor sorting. ## TODO - [x] Normalize vector when metric == Cosine Authors: - tsuki (https://github.com/enp1s0) Approvers: - Tamas Bela Feher (https://github.com/tfeher) URL: rapidsai/cuvs#763
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Graph neighbor sorting after the initial kNN graph construction by NN descent always uses the L2 norm, while NN descent also supports the inner product and cosine distance. This PR adds support for the inner product and cosine distance in graph neighbor sorting.
TODO