Add support for 1024+ dim vectors in CAGRA search #1994
Merged
Conversation
This file contains 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
enp1s0
added
feature request
|
|
/ok to test |
…s0/raft into CAGRA-remove-max_dim-template-param
|
No significant performance drop is observed |
…s0/raft into CAGRA-remove-max_dim-template-param
…s0/raft into CAGRA-remove-max_dim-template-param
|
/ok to test |
…A-remove-max_dim-template-param
…s0/raft into CAGRA-remove-max_dim-template-param
|
/ok to test |
|
/ok to test |
cjnolet
approved these changes
Dec 8, 2023
|
/merge |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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 updates the CAGRA search implementation to support 1024+ dim vectors.
For 1024+ dim vectors, the distance between a vector and the query vector is calculated by splitting the vector into multiple 1024 dim vectors and accumulating the distances of each sub-vector.
Rel: #1948