feat: support distributed IVF_RQ segment builds#6359
Merged
Conversation
24 tasks
Codecov Report❌ Patch coverage is 📢 Thoughts on this report? Let us know! |
BubbleCal
approved these changes
Mar 31, 2026
| .with_ivf(ivf_model) | ||
| // For distributed shards, keep RQ codes in row-major layout. | ||
| // A single packing pass is performed in the distributed merge stage. | ||
| .with_transpose(false) |
eddyxu
pushed a commit
that referenced
this pull request
Mar 31, 2026
This PR wires IVF_RQ into the distributed vector index segment build path so workers can build and commit shard-local RQ segments through the existing distributed indexing workflow. It also adds the missing RQ handling in the distributed auxiliary metadata plumbing and regression coverage for distributed RQ segment build plus auxiliary merge. Current limitation: IVF_RQ still does not have a pre-trained/shared RQ metadata contract. Different RQ segments can therefore carry different rotations and centroids, so merging multiple IVF_RQ segments into a single physical segment is not a supported workflow yet. I plan to follow up by adding shared/pre-trained RQ metadata so segment merge can be supported safely.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR wires IVF_RQ into the distributed vector index segment build path so workers can build and commit shard-local RQ segments through the existing distributed indexing workflow. It also adds the missing RQ handling in the distributed auxiliary metadata plumbing and regression coverage for distributed RQ segment build plus auxiliary merge.
Current limitation: IVF_RQ still does not have a pre-trained/shared RQ metadata contract. Different RQ segments can therefore carry different rotations and centroids, so merging multiple IVF_RQ segments into a single physical segment is not a supported workflow yet. I plan to follow up by adding shared/pre-trained RQ metadata so segment merge can be supported safely.