Add VLLM_DEFRAG env to enable defrag without UA #608
Conversation
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
Signed-off-by: Xiaochang Wu <xiaochang.wu@intel.com>
xwu-intel
requested review from
adobrzyn,
afierka-intel,
iboiko-habana,
kzawora-intel,
mgawarkiewicz-intel,
michalkuligowski,
mswiniarsk,
vivekgoe and
xuechendi
as code owners
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR adds support for enabling defragmentation in vLLM for Gaudi without requiring unified attention to be enabled, specifically to support DeepSeek R1. The change introduces a VLLM_DEFRAG environment variable that allows users to override the default behavior.
Key changes:
- Added
VLLM_DEFRAGenvironment variable to control defragmentation feature independently
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
✅ CI PassedAll checks passed successfully against the following vllm commit: |
Collaborator
|
@adobrzyn @michalkuligowski , may you help to review the PR |
Collaborator
|
@xwu-intel , can you give more context, will that be impact for non-mla attn? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
We need to enable defrag with contiguous pa for deepseek r1. Add the env to enable defrag.