Dot-product implementation and distance template #237
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
tyb0807
reviewed
Dec 29, 2024
hicder
approved these changes
Dec 29, 2024
hicder
approved these changes
Jan 3, 2025
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Outdated suggestions cannot be applied.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.
In the future, all the index related code needs to add distance template parameter (SPANN, Segment). It will increase the complexity of codebase as we may need to maintain multiple distance template params (e.g SPANN index is composed of hnsw and ivf).
Another method to support multiple distance is enum dispatch. It is easier to implement and integrate. However, the performance may degrade as we will use match arm in distance calculation. Should we compare the performance of both implementation on KMeans/IVF before deciding to continue with the template solution?