[0.9.1][Perf] Port MLA multistream optimazition and prefetch to v0.9.1#1750
Merged
ganyi1996ppo merged 1 commit intovllm-project:v0.9.1-devfrom Jul 13, 2025
Merged
Conversation
wangxiyuan
changed the title
whx-sjtu
force-pushed
the
mla_cv_prefetch_091
branch
2 times, most recently
from
559c84f to
2d6640b
Compare
Signed-off-by: whx-sjtu <2952154980@qq.com>
whx-sjtu
force-pushed
the
mla_cv_prefetch_091
branch
from
2d6640b to
36ee7ec
Compare
ApsarasX
reviewed
Jul 12, 2025
| 0, | ||
| enabled=use_multistream_mla): | ||
| hidden_states_or_q_c = self.q_a_layernorm(ckq) | ||
| hidden_states_or_q_c = self.q_a_layernorm(ckq) |
Collaborator
There was a problem hiding this comment.
Compared to #1353, there is a missing line of code here.
forward_kwargs['ckq'] = ckqIs there any special consideration for not adding this line of code, or was it simply forgotten?
Collaborator
Author
There was a problem hiding this comment.
This tensor ckq is passed into mla in order to add a npu_wait_tensor control edge before kv_a_proj_with_mqa of stream2, while in my testing scenario I found that removing this control edge results in a little better performance.
ganyi1996ppo
approved these changes
Jul 13, 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
5 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR port the optimization in PR #1353 to v0.9.1-dev.