Skip to content
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

Add pipeline parallel support to TransformersModel #12832

Open
wants to merge 17 commits into
base: main
Choose a base branch
from
Open

Add pipeline parallel support to TransformersModel #12832

wants to merge 17 commits into from
+244 −83

Conversation

hmellor
Copy link
Collaborator

@hmellor hmellor commented Feb 6, 2025 •
edited by github-actions bot
Loading

Depends on changes made by huggingface/transformers#36091.

Tested with Llama 3.1 70B in pp=4 and pp2,tp2 configurations.

The following command can be used for testing:

CUDA_VISIBLE_DEVICES=0,1 vllm serve meta-llama/Llama-3.2-1B-Instruct --disable-log-requests --model-impl transformers --gpu-memory-utilization 0.25 --pipeline-parallel-size 2

@github-actions GitHub Actions
Copy link

github-actions bot commented Feb 6, 2025

👋 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.

🚀

andoorve
andoorve reviewed Feb 7, 2025
View reviewed changes
vllm/model_executor/models/transformers.py Outdated Show resolved Hide resolved
vllm/model_executor/models/transformers.py Outdated Show resolved Hide resolved
vllm/model_executor/models/transformers.py Show resolved Hide resolved
@hmellor
Update to use _pp_plan and _tp_plan
8eafc6d 
Signed-off-by: Harry Mellor <[email protected]>
@hmellor
Respond to comment
87c395c 
Signed-off-by: Harry Mellor <[email protected]>
@hmellor
Add docstring to init_buffers
3498758 
Signed-off-by: Harry Mellor <[email protected]>
@hmellor
Update some comments
e652d50 
Signed-off-by: Harry Mellor <[email protected]>
@hmellor hmellor marked this pull request as ready for review February 12, 2025 11:58
@mergify Mergify
Copy link

mergify bot commented Feb 12, 2025

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

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 Feb 12, 2025
@hmellor
Copy link
Collaborator Author

hmellor commented Feb 12, 2025

Can only be merged after Transformers v4.49, but marking as ready for review so this can be merged soon after.

@mergify mergify bot removed the needs-rebase label Feb 12, 2025
@hmellor hmellor requested a review from andoorve February 12, 2025 15:47
andoorve
andoorve approved these changes Feb 12, 2025
View reviewed changes
Copy link
Collaborator

@andoorve andoorve left a comment

Choose a reason for hiding this comment

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

Comments addressed, approved!

Isotr0py
Isotr0py approved these changes Feb 13, 2025
View reviewed changes
Copy link
Collaborator

@Isotr0py Isotr0py left a comment

Choose a reason for hiding this comment

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

Overall LGTM! Just a nit, PTAL!

vllm/model_executor/models/transformers.py Outdated Show resolved Hide resolved
vllm/model_executor/models/transformers.py Show resolved Hide resolved
@hmellor
Rename inner tensor parallel method
95cdfcf 
Signed-off-by: Harry Mellor <[email protected]>
@hmellor
Add test
14e84e8 
Signed-off-by: Harry Mellor <[email protected]>
@hmellor hmellor requested a review from youkaichao as a code owner February 13, 2025 21:28
@mergify Mergify
Copy link

mergify bot commented Feb 13, 2025

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

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 Feb 13, 2025
@mergify mergify bot removed the needs-rebase label Feb 13, 2025
@mergify Mergify
Copy link

mergify bot commented Feb 14, 2025

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

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 Feb 14, 2025
@mergify mergify bot removed the needs-rebase label Feb 14, 2025
@Isotr0py Isotr0py added the ready ONLY add when PR is ready to merge/full CI is needed label Feb 14, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@Isotr0py Isotr0py Isotr0py approved these changes

@andoorve andoorve andoorve approved these changes

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

Assignees
No one assigned
Labels
ready ONLY add when PR is ready to merge/full CI is needed
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@hmellor @andoorve @Isotr0py