Skip to content

[BugFix] Fix multi-node offline data-parallel #18981

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 1 commit into from
May 31, 2025
Merged

[BugFix] Fix multi-node offline data-parallel #18981

merged 1 commit into from
May 31, 2025

Conversation

@njhill
Copy link
Member

@njhill njhill commented May 31, 2025 •
edited by github-actions bot
Loading

Fixes #18553.

Thanks @yiz-liu for reporting and suggesting the fix.

@njhill @yiz-liu
[BugFix] Fix multi-node offline data-parallel
912b103 
Signed-off-by: Nick Hill <[email protected]>

Co-authored-by: Yizhou Liu <[email protected]>
Signed-off-by: Nick Hill <[email protected]>
@njhill njhill requested a review from WoosukKwon as a code owner May 31, 2025 00:23
@njhill njhill added the bug Something isn't working label May 31, 2025
@github-actions
Copy link

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

@mergify mergify bot added documentation Improvements or additions to documentation v1 labels May 31, 2025
@njhill njhill added the ready ONLY add when PR is ready to merge/full CI is needed label May 31, 2025
houseroad
houseroad approved these changes May 31, 2025
View reviewed changes
Copy link
Collaborator

@houseroad houseroad left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks good.

Btw, shall we just attach the design doc link in the data_parallel.py, so folks can understand the design better?

@njhill njhill merged commit 9a1b9b9 into vllm-project:main May 31, 2025
74 of 75 checks passed
@njhill njhill deleted the fix-offline-multinode-dp branch May 31, 2025 15:34
@njhill
Copy link
Member Author

njhill commented May 31, 2025

Thanks @houseroad

Btw, shall we just attach the design doc link in the data_parallel.py, so folks can understand the design better?

Actually the design doc for online DP doesn't really apply to data_parallel.py which is an example for one-shot offline DP.

amitm02 pushed a commit to amitm02/vllm that referenced this pull request Jun 1, 2025
@njhill @yiz-liu @amitm02
[BugFix] Fix multi-node offline data-parallel (vllm-project#18981)
ec23b86 
Signed-off-by: Nick Hill <[email protected]>
Co-authored-by: Yizhou Liu <[email protected]>
Signed-off-by: amit <[email protected]>
amitm02 pushed a commit to amitm02/vllm that referenced this pull request Jun 1, 2025
@njhill @yiz-liu @amitm02
[BugFix] Fix multi-node offline data-parallel (vllm-project#18981)
21db17a 
Signed-off-by: Nick Hill <[email protected]>
Co-authored-by: Yizhou Liu <[email protected]>
Signed-off-by: amit <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@houseroad houseroad houseroad approved these changes

@WoosukKwon WoosukKwon Awaiting requested review from WoosukKwon

@robertgshaw2-redhat robertgshaw2-redhat Awaiting requested review from robertgshaw2-redhat

@ywang96 ywang96 Awaiting requested review from ywang96

@comaniac comaniac Awaiting requested review from comaniac

@alexm-redhat alexm-redhat Awaiting requested review from alexm-redhat

Assignees

No one assigned

Labels

bug Something isn't working documentation Improvements or additions to documentation ready ONLY add when PR is ready to merge/full CI is needed v1

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

[Bug]: data_parallel.py not working in multi-node case

2 participants

@njhill @houseroad