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.

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

[V1] Refactor model executable interface for all text-only language models #10374

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

Conversation

ywang96
Copy link
Member

@ywang96 ywang96 commented Nov 15, 2024

This PR refactors the interface of all text-only decoder language models for V1 VLM re-arch and torch.compile support. In particular, all model implementations on vLLM will need to meet the following requirements:

  • get_input_embeddings(input_ids) implemented in XYZModel
  • get_input_embeddings(input_ids) implemented in XYZForCausalLM, XYZForConditionalGeneration, and/or XYZForClassification
  • inputs_embeds is a required (with default None) parameter in the forward function signature of XYZModel and XYZForCausalLM, XYZForConditionalGeneration, and/or XYZForClassification

This PR is a prerequisite of applying #9871 to all multimodal models on vLLM.

Signed-off-by: Roger Wang <[email protected]>
Copy link

👋 Hi! Thank you for contributing to the vLLM project.
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 do one of these:

  • Add ready label to the PR
  • Enable auto-merge.

🚀

Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
@ywang96 ywang96 marked this pull request as ready for review November 16, 2024 04:01
Copy link
Member

@DarkLight1337 DarkLight1337 left a comment

Choose a reason for hiding this comment

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

LGTM!

After you refactor the multi-modal models, can you update the base interface for vLLM models (class VllmModel) to define get_input_embeddings and also update the required arguments of forward, then add a test to ensure that all of our models implement it?

@DarkLight1337 DarkLight1337 enabled auto-merge (squash) November 16, 2024 06:10
@github-actions github-actions bot added the ready ONLY add when PR is ready to merge/full CI is needed label Nov 16, 2024
@ywang96
Copy link
Member Author

ywang96 commented Nov 16, 2024

LGTM!

After you refactor the multi-modal models, can you update the base interface for vLLM models (class VllmModel) to define get_input_embeddings and also update the required arguments of forward, then add a test to ensure that all of our models implement it?

@DarkLight1337 Thanks for the review! Yes eventually if we're going to enforce this interface, then I will update those model interfaces once the refactoring is done for all related models.

I also want others to take a look at this PR before we proceed so I disabled auto-merge and CI for now.

@ywang96 ywang96 removed the ready ONLY add when PR is ready to merge/full CI is needed label Nov 16, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants