Increase kMinWorkspaceRatio in build_knn_graph()#1937
Open
julianmi wants to merge 1 commit intorapidsai:mainfrom
Open
Increase kMinWorkspaceRatio in build_knn_graph()#1937julianmi wants to merge 1 commit intorapidsai:mainfrom
julianmi wants to merge 1 commit intorapidsai:mainfrom
Conversation
aamijar
added
improvement
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
OpenAI 5M dataset runs OOM when using quantized data (
floattoint8) as show in this example. ThekMinWorkspaceRatiois too small for theint8data such that the IVF-PQ searchmax_internal_batch_sizeis not reduced. DoublingkMinWorkspaceRatiofixes this. There is no performance degradation for the OpenAI 5Mfloatdataset with this change. Let me know if I should test more datasets.CC @tfeher