Minor ivf cleanups and fixing quantization performance #129566
Merged
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
elasticsearchmachine
added
the
Team:Search Relevance
|
Pinging @elastic/es-search-relevance (Team:Search Relevance) |
benwtrent
added
the
auto-merge-without-approval
kderusso
pushed a commit
to kderusso/elasticsearch
that referenced
this pull request
Jun 23, 2025
We are accidentally utilizing the non-vectorized quantizer when building ivf indices. This provides a 3-5x speed improvement on quantizing on my mac This fixes that and addresses some minor fixes (removing unused code, etc.) Here is a small benchmark result. time spent quantizing goes down significantly. <img width="652" alt="image" src="https://github.com/user-attachments/assets/9f46398c-c587-4e74-bc91-f2e07a63b406" /> vs. <img width="673" alt="image" src="https://github.com/user-attachments/assets/c4f4679f-d7a7-4486-841f-7dd3e75a11cb" />
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Outdated suggestions cannot be applied.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.
We are accidentally utilizing the non-vectorized quantizer when building ivf indices. This provides a 3-5x speed improvement on quantizing on my mac
This fixes that and addresses some minor fixes (removing unused code, etc.)
Here is a small benchmark result. time spent quantizing goes down significantly.
vs.