Skip to content

[V1] Support LLM.apply_model #18465

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
Open
wants to merge 8 commits into
base: main
Choose a base branch
from
Open

[V1] Support LLM.apply_model #18465

wants to merge 8 commits into from
+152 −119

Conversation

DarkLight1337
Copy link
Member

This enables a bunch of tests to be run in V1

@DarkLight1337 DarkLight1337 added the ready ONLY add when PR is ready to merge/full CI is needed label May 21, 2025
@DarkLight1337 DarkLight1337 changed the title [Core] Enable apply_model to be run on V1 [Core] Support LLM.apply_model in V1 May 21, 2025
@mergify mergify bot added frontend multi-modality Related to multi-modality (#4194) v1 labels May 21, 2025
@DarkLight1337 DarkLight1337 changed the title [Core] Support LLM.apply_model in V1 [V1] Support LLM.apply_model May 21, 2025
@DarkLight1337
Copy link
Member Author

@youkaichao can you review this?

DarkLight1337
DarkLight1337 commented May 21, 2025
View reviewed changes
vllm/executor/executor_base.py
Comment on lines -132 to -133
def rpc_func(worker: WorkerBase) -> _R:
return func(worker.get_model())
Copy link
Member Author

Choose a reason for hiding this comment

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

This part has been moved inside WorkerBase

@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.

🚀

@DarkLight1337
Fix
8f732cb 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Update
67de61b 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Copy link
Member Author

And also @mgoin since this touches the quantization tests

@DarkLight1337
Update more tests
068e42a 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Comment
0d4fa16 
Signed-off-by: DarkLight1337 <[email protected]>
youkaichao
youkaichao reviewed May 21, 2025
View reviewed changes
youkaichao
youkaichao approved these changes May 21, 2025
View reviewed changes
Copy link
Member

@youkaichao youkaichao left a comment

Choose a reason for hiding this comment

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

LGTM in general

@DarkLight1337
Move to CPU
a2635f1 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Copy link
Member Author

DarkLight1337 commented May 21, 2025 •
edited
Loading

@njhill I'm unable to get tests/models/multimodal/generation/test_qwen2_vl.py::test_qwen2_vl_multiple_image_embeddings_input[10-128-half-size_factors1-Qwen/Qwen2-VL-2B-Instruct] to pass - the output of apply_model only has the tensor's dtype and shape rather than the tensor data. I think this is related to the msgspec encoding/decoding logic. Can you help take a look?

mgoin
mgoin approved these changes May 21, 2025
View reviewed changes
Copy link
Member

@mgoin mgoin left a comment

Choose a reason for hiding this comment

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

This looks reasonable to me. A section in the docs or example script would be useful to demonstrate the interface

@DarkLight1337 DarkLight1337 removed the ready ONLY add when PR is ready to merge/full CI is needed label May 22, 2025
@DarkLight1337
Copy link
Member Author

A section in the docs or example script would be useful to demonstrate the interface

Currently this is only used for testing purposes. It is basically a thin wrapper over LLM.collective_rpc which is already documented in the RLHF examples.

@DarkLight1337
Add note
41d73a7 
Signed-off-by: DarkLight1337 <[email protected]>
@mergify Mergify
Copy link

mergify bot commented May 27, 2025

This pull request has merge conflicts that must be resolved before it can be
merged. Please rebase the PR, @DarkLight1337.

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 27, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@youkaichao youkaichao youkaichao approved these changes

@mgoin mgoin mgoin approved these changes

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

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

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

@njhill njhill Awaiting requested review from njhill njhill 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

@zhuohan123 zhuohan123 Awaiting requested review from zhuohan123 zhuohan123 is a code owner

Assignees
No one assigned
Labels
frontend multi-modality Related to multi-modality (#4194) needs-rebase v1
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@DarkLight1337 @mgoin @youkaichao