Skip to content

[Model] Add Ernie4.5 VL Model Support #22514

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

Open
wants to merge 9 commits into
base: main
Choose a base branch
from

Conversation

CSWYF3634076
Copy link
Contributor

@CSWYF3634076 CSWYF3634076 commented Aug 8, 2025

Purpose

Support Baidu Ernie4.5 VL model for vllm

Note: torch.compile is not supported. Due to the model limitations of multimodal experts and text experts, using torch.compile may fail to start

Copy link

github-actions bot commented Aug 8, 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.

🚀

@mergify mergify bot added documentation Improvements or additions to documentation new-model Requests to new models labels Aug 8, 2025
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

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

Code Review

This pull request adds support for the Baidu Ernie4.5 VL model. The changes include new model implementation files, rotary embedding logic, and a custom processor. While the overall structure seems correct, there are several critical issues that need to be addressed. These include hardcoded values that make the code brittle, unsafe tensor operations that could lead to runtime errors, incorrect function calls in the processor, and some incomplete logic indicated by TODOs. Addressing these points will significantly improve the robustness and maintainability of the new model support.

Copy link
Member

@ywang96 ywang96 left a comment

Choose a reason for hiding this comment

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

Thanks for the contritbution! Is this PR ready for review? If not, could you please convert this to a draft PR?

@CSWYF3634076 CSWYF3634076 marked this pull request as draft August 9, 2025 07:21
@CSWYF3634076 CSWYF3634076 marked this pull request as ready for review August 12, 2025 08:41
@CSWYF3634076
Copy link
Contributor Author

Thanks for the contritbution! Is this PR ready for review? If not, could you please convert this to a draft PR?

@ywang96 Hi, the PR is ready for review. Could you help review it?

@CSWYF3634076 CSWYF3634076 requested a review from ywang96 August 12, 2025 08:46
@CSWYF3634076 CSWYF3634076 changed the title [WIP][Model] Add Ernie4.5 VL Model Support [Model] Add Ernie4.5 VL Model Support Aug 12, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
documentation Improvements or additions to documentation new-model Requests to new models
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants