Open
Conversation
Collaborator
|
@inkcherry Thanks for this PR! @isytwu Could you please help review this? The idea is very similar to what we have discussed before to reduce memory usage. |
isytwu
reviewed
Sep 3, 2025
|
|
||
| inline __host__ __device__ int MaxNumTokensToRecv() const { | ||
| if (numWorstToken != 0) { | ||
| return numWorstToken; |
Collaborator
There was a problem hiding this comment.
I wonder if return worldSize * numWorstToken will be better?
Collaborator
There was a problem hiding this comment.
Perhaps using min(numWorstToken, worldSize * MaxNumTokensToRecvPerRank()) could prevent users from passing large values. And should MaxNumTokensToSend() also be changed to add numWorstToken?
ChuanLi1101
approved these changes
Nov 28, 2025
ChuanLi1101
left a comment
ChuanLi1101
left a comment
There was a problem hiding this comment.
Looks good to me.
The num_worst_token config improves stability for worst-case token routing.
Approving.
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
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
Adjustable
max_token_recv_per_rank, allowing for reduced memory overhead in some balancing scenarios.FYI @zhenhuang12