Skip to content

Support sequence parallelism combined with pipeline parallelism #18243

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 3 commits into from
May 17, 2025
Merged

Support sequence parallelism combined with pipeline parallelism #18243

merged 3 commits into from
May 17, 2025

Conversation

cascade812
Copy link
Contributor

@cascade812 cascade812 commented May 16, 2025 •
edited by github-actions bot
Loading

this PR adds support for sp+pp scenario.

vllm serve meta-llama/Llama-3.2-1B-Instruct --tensor-parallel-size 2 --pipeline-parallel-size 2 --distributed-executor-backend mp -O '{"level": 3, "compile_sizes": [4, 8, 16], "splitting_ops": [], "pass_config": {"enable_sequence_parallelism" : true}}'

@cascade812
Suppport SP + PP
f5a6f2c 
Signed-off-by: cascade812 <[email protected]>
@github-actions 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 the v1 label May 16, 2025
cascade812
cascade812 commented May 16, 2025
View reviewed changes
vllm/v1/worker/gpu_model_runner.py Outdated
@@ -1172,6 +1184,7 @@ def execute_model(

if not get_pp_group().is_last_rank:
# For mid-pipeline stages, return the hidden states.
# print(f"cascade pp is not last rank, return hidden states")
Copy link
Contributor Author

Choose a reason for hiding this comment

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

for debug usage, will remove.

@mergify Mergify
Copy link

mergify bot commented May 16, 2025

This pull request has merge conflicts that must be resolved before it can be
merged. Please rebase the PR, @cascade812.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

@mergify mergify bot added the needs-rebase label May 16, 2025
tlrmchlsmth
tlrmchlsmth reviewed May 16, 2025
View reviewed changes
tlrmchlsmth
tlrmchlsmth approved these changes May 16, 2025
View reviewed changes
Copy link
Collaborator

@tlrmchlsmth tlrmchlsmth left a comment

Choose a reason for hiding this comment

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

Great work! Left a few minor comments

cascade812 added 2 commits May 17, 2025 04:15
@cascade812
address comments
031c46d 
Signed-off-by: cascade812 <[email protected]>
@cascade812
remove debug log
4f28717 
Signed-off-by: cascade812 <[email protected]>
@mergify mergify bot removed the needs-rebase label May 17, 2025
@tlrmchlsmth tlrmchlsmth added the ready ONLY add when PR is ready to merge/full CI is needed label May 17, 2025
@tlrmchlsmth tlrmchlsmth enabled auto-merge (squash) May 17, 2025 04:40
@tlrmchlsmth tlrmchlsmth merged commit 9ab2c02 into vllm-project:main May 17, 2025
71 checks passed
@cascade812 cascade812 mentioned this pull request May 17, 2025
Merged
4 tasks
shaoyuyoung pushed a commit to shaoyuyoung/vllm that referenced this pull request May 18, 2025
@cascade812 @shaoyuyoung
Support sequence parallelism combined with pipeline parallelism (vllm…
90b3234 
…-project#18243)

Signed-off-by: cascade812 <[email protected]>
Signed-off-by: shaoyuyoung <[email protected]>
huachenheli pushed a commit to huachenheli/vllm that referenced this pull request May 22, 2025
@cascade812 @huachenheli
Support sequence parallelism combined with pipeline parallelism (vllm…
d1f1674 
…-project#18243)

Signed-off-by: cascade812 <[email protected]>
Signed-off-by: Chenheli Hua <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@tlrmchlsmth tlrmchlsmth tlrmchlsmth approved these changes

@WoosukKwon WoosukKwon Awaiting requested review from WoosukKwon WoosukKwon is a code owner

@robertgshaw2-redhat robertgshaw2-redhat Awaiting requested review from robertgshaw2-redhat robertgshaw2-redhat is a code owner

@njhill njhill Awaiting requested review from njhill njhill is a code owner

@ywang96 ywang96 Awaiting requested review from ywang96 ywang96 is a code owner

@comaniac comaniac Awaiting requested review from comaniac comaniac is a code owner

@alexm-redhat alexm-redhat Awaiting requested review from alexm-redhat alexm-redhat is a code owner

Assignees
No one assigned
Labels
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.
2 participants
@cascade812 @tlrmchlsmth