[fix] Only enable flashinfer all reduce fusion by default for single-node servers#12724
Merged
Fridge003 merged 1 commit intosgl-project:mainfrom Nov 6, 2025
Conversation
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
leejnau
changed the title
Fridge003
approved these changes
Nov 6, 2025
leejnau
force-pushed
the
workaround-flashinfer-allreduce-fusion-bug
branch
from
2c40110 to
8069e8f
Compare
trevor-m
approved these changes
Nov 6, 2025
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Currently multi-node non-data-parallel inference does not work for
DeepseekV3ForCausalLMmodels.This is due to a bug in flashinfer: flashinfer-ai/flashinfer#2006
Modifications
Currently enable_flashinfer_allreduce_fusion is enabled by default for
DeepseekV3ForCausalLMandGptOssForCausalLM. Because of the flashinfer all reduce fusion bug, a workaround is to only enable flashinfer all reduce fusion if a single node is used.