feat(python): add shared RaBitQ rotation for distributed IVF_RQ builds#7014
Open
gstamatakis95 wants to merge 1 commit into
Open
feat(python): add shared RaBitQ rotation for distributed IVF_RQ builds#7014gstamatakis95 wants to merge 1 commit into
gstamatakis95 wants to merge 1 commit into
Conversation
Contributor
|
ACTION NEEDED The PR title and description are used as the merge commit message. Please update your PR title and description to match the specification. For details on the error please inspect the "PR Title Check" action. |
a8438c2 to
a5bd8a8
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes: #7012
What
Distributed
IVF_RQbuilds work in the Rust engine (#6359) but could not be driven from Python because the RaBitQ rotation could not be pinned across workers. Each per-fragment build generated its own random rotation, so segments rotated vectors differently, their binary codes were not comparable, and merging corrupted the index.This adds a way to mint one rotation, broadcast it, and reuse it in every per-fragment build, mirroring how
pq_codebookis injected.Changes
build_rq_rotation(dimension, num_bits=1, rotation_type="fast", dtype="float32")that returns one rotation as a JSON string.rq_rotationparameter tocreate_index_uncommitted, parsed into a new transientRQBuildParams.rotationfield and consumed byRabitQuantizer::build.build()reuses the supplied rotation instead of generating a random one, after validatingnum_bits,code_dim, and the signs length.Notes
Tests
IVF_RQsegments on separate fragments with one shared rotation, merges, commits, and queries.