[REVIEW] Reverting default knn distance to L2Unexpanded for now. #403
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
cjnolet
added
3 - Ready for Review
bug
|
@gpucibot merge |
dantegd
approved these changes
Dec 1, 2021
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Outdated suggestions cannot be applied.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.
I believe the new expanded knn changes might need some further investigation. Before we started using the fused l2 knn, both unexpanded and expanded variants mapped to the same (expanded) distance computation in FAISS and the cuml tests passed consistently. For some reason, the new expanded fused l2 knn version is causing test failures within cuml. We should figure out if this is from assertions which are too tight or from a possible bug.