[WIP] [FEA] IVF_PQ build_from_args API #1483
Open
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
github-project-automation
bot
moved this to Todo
in Vector Search, ML, & Data Mining Release Board
|
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. |
tarang-jain
added
feature request
tarang-jain
changed the title
…into build-from-args
tarang-jain
moved this from Todo
to In Progress
in Vector Search, ML, & Data Mining Release Board
… build-from-args
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
7 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Outdated suggestions cannot be applied.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.
IVF-PQ Index Build API Enhancements and Pimpl Refactoring
Summary
This PR adds new build APIs for IVF-PQ indices using precomputed centroids and implements a complete PIMPL refactoring with owning/view semantics
Key Changes
Added cuvs::neighbors::ivf_pq::build() overloads that accept precomputed cluster centroids, PQ codebooks, and rotation matrices
Enables building indices from pre-trained models without re-training
Supports both device and host input data with automatic memory transfer
owning_impl: Owns centroid and codebook data (traditional behavior)
view_impl: References external centroid data without copying
Maintains identical search behavior with zero data copying
Removed mutator functions that directly modify the state of the index. Instead we have helpers for the user to fetch and own the transformed data
View indices avoid copying large centroid arrays
Backward Compatibility: All existing APIs work unchanged