Repository navigation
Add distributed IVF_RQ builds with a shared rotation model - #85
Merged
everySympathy merged 2 commits intoOct 12, 2026
Merged
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add
IVF_RQto distributed vector index creation. The coordinator trains IVF centroids and generates one RaBitQ rotation model, then every worker uses those shared models to write its segment. This makes separately built RQ segments searchable together and mergeable throughoptimize_indices.RQ defaults to 1 bit per dimension;
num_bitsconfigures its bit width. Omittingnum_bitscontinues to use 8 bits for PQ. Lance validates RQ configurations, including dimensions divisible by 8. Model generation stays internal, and caller-suppliedrabitq_modelis rejected.Creation still covers the full snapshot, replacement uses one atomic commit, and incremental coverage belongs to
optimize_indices. The README explains lossy RQ query results and refinement with original vectors.Validation: