Skip to content

[Model] Support Skywork-R1V #15397

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

Merged
merged 1 commit into from
Mar 29, 2025
Merged

Conversation

pengyuange
Copy link
Contributor

@pengyuange pengyuange commented Mar 24, 2025

fix vllm's support for skyworkr1v SkyworkAI/Skywork-R1V#6
FIX #15186

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 frontend label Mar 24, 2025
@pengyuange pengyuange force-pushed the skywork81 branch 2 times, most recently from fd29e4a to 6a8f898 Compare March 24, 2025 13:25
@jeejeelee jeejeelee changed the title skyworkr1v update [Model] Support Skywork-R1V Mar 24, 2025
@jeejeelee jeejeelee added the new-model Requests to new models label Mar 24, 2025
@DarkLight1337
Copy link
Member

Thanks for implementing this! Can you apply the fix #15086 to this model so it can work correctly in V1?

@DarkLight1337
Copy link
Member

DarkLight1337 commented Mar 24, 2025

Also, please add this model to the following files so CI can pass:

  • Supported Models page
  • tests/models/registry.py
  • tests/models/multimodal/processing/test_common.py
  • tests/models/decoder_only/vision_language/test_models.py

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.

Hmmm, with a quick glance, this model is quite similar to original InternVL2 models...

If the difference is minor, I prefer to inherit from existing InternVL2 implementation instead of making a highly similar code copy...

@Isotr0py Isotr0py moved this to In Progress in Multi-modal Model Requests Mar 25, 2025
@mergify mergify bot added the multi-modality Related to multi-modality (#4194) label Mar 26, 2025
@pengyuange pengyuange force-pushed the skywork81 branch 3 times, most recently from ff0d3b2 to e84cb1e Compare March 26, 2025 08:24
@DarkLight1337
Copy link
Member

Can you merge in the changes from latest main and apply the changes from #15443?

@pengyuange pengyuange force-pushed the skywork81 branch 3 times, most recently from 30e87c9 to 19a139e Compare March 26, 2025 13:00
@Isotr0py Isotr0py changed the base branch from v0.8.1 to main March 27, 2025 03:37
Copy link

mergify bot commented Mar 27, 2025

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

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

@DarkLight1337
Copy link
Member

I think the code looks pretty good now. Finally, can you add this model to the List of Supported Models page in the docs as well?

@DarkLight1337
Copy link
Member

And also add it to examples/offline_inference/vision_language*.py

@mergify mergify bot added the documentation Improvements or additions to documentation label Mar 28, 2025
@pengyuange
Copy link
Contributor Author

I think the code looks pretty good now. Finally, can you add this model to the List of Supported Models page in the docs as well?

And also add it to examples/offline_inference/vision_language*.py

I have added these information.

@DarkLight1337
Copy link
Member

There is a trailing comma after chat template field in https://huggingface.co/Skywork/Skywork-R1V-38B/blob/main/tokenizer_config.json which prevents the JSON from being loaded

@pengyuange
Copy link
Contributor Author

There is a trailing comma after chat template field in https://huggingface.co/Skywork/Skywork-R1V-38B/blob/main/tokenizer_config.json which prevents the JSON from being loaded

It should be fixed right now.

@DarkLight1337
Copy link
Member

I can successfully run the example script, thanks for your effort and let's get this merged!

@DarkLight1337 DarkLight1337 enabled auto-merge (squash) March 28, 2025 16:02
@github-actions github-actions bot added the ready ONLY add when PR is ready to merge/full CI is needed label Mar 28, 2025
@pengyuange
Copy link
Contributor Author

image
Ci has failed. how should I fix this?

@DarkLight1337
Copy link
Member

I can force merge

@vllm-bot vllm-bot merged commit de1cb38 into vllm-project:main Mar 29, 2025
42 of 44 checks passed
@github-project-automation github-project-automation bot moved this from In Progress to Done in Multi-modal Model Requests Mar 29, 2025
lengrongfu pushed a commit to lengrongfu/vllm that referenced this pull request Apr 2, 2025
Signed-off-by: jiacai.liu <[email protected]>
Co-authored-by: jiacai.liu <[email protected]>
kylesayrs pushed a commit to neuralmagic/vllm that referenced this pull request Apr 2, 2025
Signed-off-by: jiacai.liu <[email protected]>
Co-authored-by: jiacai.liu <[email protected]>
Signed-off-by: Kyle Sayers <[email protected]>
Alex4210987 pushed a commit to LeiWang1999/vllm-bitblas that referenced this pull request Apr 5, 2025
Signed-off-by: jiacai.liu <[email protected]>
Co-authored-by: jiacai.liu <[email protected]>
Signed-off-by: xinyuxiao <[email protected]>
lulmer pushed a commit to lulmer/vllm that referenced this pull request Apr 7, 2025
Signed-off-by: jiacai.liu <[email protected]>
Co-authored-by: jiacai.liu <[email protected]>
Signed-off-by: Louis Ulmer <[email protected]>
nishith-fujitsu pushed a commit to nishith-fujitsu/vllm that referenced this pull request Apr 9, 2025
Signed-off-by: jiacai.liu <[email protected]>
Co-authored-by: jiacai.liu <[email protected]>
lk-chen pushed a commit to lk-chen/vllm that referenced this pull request Apr 29, 2025
Signed-off-by: jiacai.liu <[email protected]>
Co-authored-by: jiacai.liu <[email protected]>
shreyankg pushed a commit to shreyankg/vllm that referenced this pull request May 3, 2025
Signed-off-by: jiacai.liu <[email protected]>
Co-authored-by: jiacai.liu <[email protected]>
RichardoMrMu pushed a commit to RichardoMrMu/vllm that referenced this pull request May 12, 2025
Signed-off-by: jiacai.liu <[email protected]>
Co-authored-by: jiacai.liu <[email protected]>
Signed-off-by: Mu Huai <[email protected]>
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 frontend multi-modality Related to multi-modality (#4194) new-model Requests to new models ready ONLY add when PR is ready to merge/full CI is needed
Projects
Status: Done
Development

Successfully merging this pull request may close these issues.

[New Model]: please surport model https://huggingface.co/Skywork/Skywork-R1V-38B
6 participants