avoid cudaStreamSynchronize in DeepSeekV2AttentionMLA#4577
Merged
zhyncs merged 1 commit intosgl-project:mainfrom Mar 19, 2025
Merged
avoid cudaStreamSynchronize in DeepSeekV2AttentionMLA#4577zhyncs merged 1 commit intosgl-project:mainfrom
zhyncs merged 1 commit intosgl-project:mainfrom
Conversation
…ze in DeepSeekV2AttentionMLA
Collaborator
Author
|
I benchmark it with cuda12.8 and DeepGEMM
with TTFT from 914ms to 827ms |
This was referenced Mar 20, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
I profiled deepseek and observed some bubbles in timeline, finally found the cause:

This is caused by D2H copy in DeepSeekV2AttentionMLA.
Modifications
Using forward_batch.extend_prefix_lens_cpu directy instead of forward_batch.extend_prefix_lens, this can decrease TTFT
Checklist