Use PQ API in CAGRA-Q + SCANN#1746
Merged
rapids-bot[bot] merged 21 commits intorapidsai:mainfrom Mar 13, 2026
Merged
Conversation
Signed-off-by: Mickael Ide <mide@nvidia.com>
Signed-off-by: Mickael Ide <mide@nvidia.com>
Signed-off-by: Mickael Ide <mide@nvidia.com>
lowener
added
improvement
tarang-jain
reviewed
Jan 27, 2026
rmaschal
reviewed
Jan 28, 2026
rmaschal
reviewed
Jan 28, 2026
rmaschal
reviewed
Jan 28, 2026
Contributor
|
I know it's hard to test the recall of a ScaNN index, I apologize for that. I pulled this PR to test. Compared to main, recall looks overall the same, so no concern there, but there is a build time regression due to the two issues I mentioned in the comments. Your prior PR #1278 improved PQ training quite a lot for ScaNN, thank you for that :) For larger dim datasets like LAION and OpenAI, it shaves 2-4s from the overall build time. |
Signed-off-by: Mickael Ide <mide@nvidia.com>
Signed-off-by: Mickael Ide <mide@nvidia.com>
Signed-off-by: Mickael Ide <mide@nvidia.com>
Signed-off-by: Mickael Ide <mide@nvidia.com>
cjnolet
approved these changes
Mar 13, 2026
Contributor
Author
|
/merge |
github-project-automation
Bot
moved this from In Progress
to Done
in Unstructured Data Processing
lowener
added a commit
to lowener/cuvs
that referenced
this pull request
Mar 30, 2026
Follow-up to the PQ PR rapidsai#1278 . Closes rapidsai#1575 Closes rapidsai#1747 This PR removes the need to compile multiple times the same code for PQ in CAGRA-Q and SCANN, removing code duplication and improving build time. CAGRA-Q can't use the new public API since it is using half for its math type so an private API function is used. A small test is added to SCANN to make sure that the returned index is not complete garbage but more testing should be done there. (Created issue rapidsai#1747 to track this) This PR saves ~2-3 Mb on libcuvs.so compiled on a single architecture (141 Mb -> 138Mb) Authors: - Micka (https://github.com/lowener) Approvers: - Corey J. Nolet (https://github.com/cjnolet) URL: rapidsai#1746
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
5 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.
Follow-up to the PQ PR #1278 .
Closes #1575
Closes #1747
This PR removes the need to compile multiple times the same code for PQ in CAGRA-Q and SCANN, removing code duplication and improving build time.
CAGRA-Q can't use the new public API since it is using half for its math type so an private API function is used.
A small test is added to SCANN to make sure that the returned index is not complete garbage but more testing should be done there. (Created issue #1747 to track this)
This PR saves ~2-3 Mb on libcuvs.so compiled on a single architecture (141 Mb -> 138Mb)