Add --miles-nsa-topk-backend#1058
Open
zianglih wants to merge 1 commit into
Open
Conversation
zianglih
requested review from
Zhichenzzz,
fzyzcjy,
guapisolo,
maocheng23 and
yueming-yuan
as code owners
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request introduces a configurable backend for the Top-k operation in the Miles NSA indexer, allowing users to select between torch and flashinfer. The implementation includes a new command-line argument, propagation of the backend setting through the GLM5 model architecture, and the integration of FlashInfer's top-k logic within the indexer's forward pass. I have no feedback to provide.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
--dsa-topk-backendand integrate FlashInfer and pytorch topk sgl-project/sglang#22851