[FEA] IVF-PQ to Write Flat PQ Codes#1607
Merged
rapids-bot[bot] merged 47 commits intorapidsai:release/26.02from Jan 24, 2026
Merged
[FEA] IVF-PQ to Write Flat PQ Codes#1607rapids-bot[bot] merged 47 commits intorapidsai:release/26.02from
rapids-bot[bot] merged 47 commits intorapidsai:release/26.02from
Conversation
tarang-jain
added
feature request
tarang-jain
changed the title
Contributor
Author
tarang-jain
changed the title
Contributor
Author
|
/ok to test dc99bfb |
…with strat pattern
…into ivfpq-flat-codes
tarang-jain
force-pushed
the
ivfpq-flat-codes
branch
from
3bf9018 to
b5cfc7e
Compare
Contributor
Author
|
/ok to test b5cfc7e |
robertmaynard
requested changes
Jan 22, 2026
cjnolet
approved these changes
Jan 22, 2026
Member
cjnolet
left a comment
cjnolet
left a comment
There was a problem hiding this comment.
LGTM, pending addressing @robertmaynard's feedback. LanceDB is chomping at the bit to try this out, so we can continue to improve over time if we need to (and also use the upcoming preprocessing API directly in IVFPQ in the future).
| * - INTERLEAVED: Codes are interleaved for optimized search performance. | ||
| * This is the default and recommended for search workloads. | ||
| */ | ||
| enum list_layout codes_layout; |
Member
There was a problem hiding this comment.
Just making a note here that this is going to break the C ABI. No action needed, but we will need to track these things in the future. I'll share the POR with you (and the team) for more info.
| virtual size_type get_size() const noexcept = 0; | ||
|
|
||
| /** Set the current size (number of records). */ | ||
| virtual void set_size(size_type new_size) noexcept = 0; |
Member
There was a problem hiding this comment.
I suppose as long as users are never direclty mutating this object then we shouldn't have to be too vigilent. Would be nice if we could make this internal, though, so that only cuVS funcitons are capable of changing it. Just concerned for users shooting themselves in the foot.
Contributor
Author
|
/ok to test b0ff258 |
Contributor
Author
|
/ok to test 36339c8 |
robertmaynard
approved these changes
Jan 23, 2026
Contributor
Author
|
/merge |
Contributor
Author
|
/ok to test 4f761fb |
Contributor
Author
|
/ok to test 400d234 |
Contributor
Author
|
/ok to test cb3fec1 |
Member
|
/merge |
github-project-automation
Bot
moved this from In Progress
to Done
in Unstructured Data Processing
lowener
pushed a commit
to lowener/cuvs
that referenced
this pull request
Jan 26, 2026
This PR brings new params to ivf_pq: an option for the user to choose the layout of the ivf lists. The lists can be flat (no interleaving) or interleaved (current default). Flat codes allows building the index in a CPU-compatible format. [UPDATE as of 12/19/2025]: After rapidsai#1278 is merged, we can unify IVF-PQ and PQ API codepaths. [UPDATE 01/08/2026]: This PR can be merged before rapidsai#1278. The flat code-writing can potentially be reverted once rapidsai#1278 is merged (so we can later use the PQ preprocessing API directly). However that will come naturally as a part if a broader unification of IVF-PQ and PQ codepaths. [Benchmarks 01/15/2026]: ## IVF-PQ Layout Benchmark Results **Dataset**: 1,000,000 vectors × 128 dimensions | **pq_dim**: 32 pq_bits | Code Size | Direct FLAT Build (ms) | INTERLEAVED Build (ms) | Convert INTERLEAVED to FLAT with Codepacker (ms) | Total time for INTERLEAVED build + Conversion to FLAT with Codepacker (unpack) (ms) | Overhead | |:-------:|:---------:|:---------------:|:----------------------:|:-------------------:|:----------------------:|:--------:| | 8 | 32 bytes | 372.46 | 385.86 | 985.28 | 1371.13 | 3.68× | | 6 | 24 bytes | 298.83 | 300.99 | 961.82 | 1262.82 | 4.23× | | 5 | 20 bytes | 283.25 | 281.95 | 795.43 | 1077.38 | 3.80× | | 4 | 16 bytes | 270.63 | 271.01 | 489.73 | 760.75 | 2.81× | Authors: - Tarang Jain (https://github.com/tarang-jain) Approvers: - Corey J. Nolet (https://github.com/cjnolet) - Robert Maynard (https://github.com/robertmaynard) URL: rapidsai#1607
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
4 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 brings new params to ivf_pq: an option for the user to choose the layout of the ivf lists. The lists can be flat (no interleaving) or interleaved (current default). Flat codes allows building the index in a CPU-compatible format.
[UPDATE as of 12/19/2025]:
After #1278 is merged, we can unify IVF-PQ and PQ API codepaths.
[UPDATE 01/08/2026]:
This PR can be merged before #1278. The flat code-writing can potentially be reverted once #1278 is merged (so we can later use the PQ preprocessing API directly). However that will come naturally as a part if a broader unification of IVF-PQ and PQ codepaths.
[Benchmarks 01/15/2026]:
IVF-PQ Layout Benchmark Results
Dataset: 1,000,000 vectors × 128 dimensions | pq_dim: 32