Use IVF_PQ for GPU index build for large datasets #137126
Draft
+168
−8
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
Use IVF_PQ algorithm for GPU index building for large dataset (>= 1M vectors). Temporarily add a factory for calculating IVF_PQ params. Also skip estimation of needed memory when IVF_PQ is used.
mayya-sharipova
added
>enhancement
auto-backport
elasticsearchmachine
added
the
Team:Search Relevance
|
Pinging @elastic/es-search-relevance (Team:Search Relevance) |
|
Hi @mayya-sharipova, I've created a changelog YAML for you. |
mayya-sharipova
commented
Oct 24, 2025
| } | ||
|
|
||
| private long estimateRequiredMemory(int numVectors, int dims, CuVSMatrix.DataType dataType) { | ||
| // for large vector sets, we use IVF+PQ or similar, so we don't skip blocking based on memory usage |
There was a problem hiding this comment.
@ldematte What do you think we should do here? I made it very naively.
|
With this params (1M byte vectors): @achirkin Notice how here when switching from NN_DESCENT, we got worse graph building time, and more dense graphs. gist: 1_000_000 docs; 960 dims; euclidean metric
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
Use IVF_PQ algorithm for GPU index building for large dataset (>= 1M vectors). Temporarily add a factory for calculating IVF_PQ params. Also skip estimation of needed memory when IVF_PQ is used.