Skip to content

[Model] Merged multimodal processor for Paligemma #13584

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

Closed
wants to merge 12 commits into from

Conversation

kylehh
Copy link
Contributor

@kylehh kylehh commented Feb 20, 2025

  1. Created merged MM processor for Paligemma
  2. Issue to be solved:
    • need newline at prompt (solved by overriding BaseMultiModalProcessor.apply())
    • paligemma 2 support (solved by adding <bos> token)

Signed-off-by: Kyle Huang <kylhuang@nvidia.com>
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.

🚀

Copy link

mergify bot commented Feb 20, 2025

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

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

@mergify mergify bot removed the needs-rebase label Feb 22, 2025
@kylehh
Copy link
Contributor Author

kylehh commented Feb 22, 2025

Newline issue is solved by overriding _apply_prompt_replacements

@DarkLight1337 DarkLight1337 self-assigned this Feb 22, 2025
@kylehh
Copy link
Contributor Author

kylehh commented Feb 24, 2025

paligemma2 is not adding "<bos>" token according to tokenizer config ( compare to paligemma's config here)
So add bos token to adapt with prompt replacment

Copy link

mergify bot commented Feb 25, 2025

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

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 25, 2025
@DarkLight1337
Copy link
Member

Please remember to test this by adding the model to tests/models/multimodal/processing/test_common.py

@kylehh kylehh requested a review from ywang96 as a code owner February 26, 2025 05:10
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.

Thanks for your hard work!

@DarkLight1337
Copy link
Member

Can you fix the merge conflicts?

@mergify mergify bot removed the needs-rebase label Feb 27, 2025
Signed-off-by: Kyle Huang <kylhuang@nvidia.com>
@DarkLight1337 DarkLight1337 enabled auto-merge (squash) February 27, 2025 04:26
@github-actions github-actions bot added the ready ONLY add when PR is ready to merge/full CI is needed label Feb 27, 2025
Signed-off-by: Kyle Huang <kylhuang@nvidia.com>
auto-merge was automatically disabled February 27, 2025 05:09

Head branch was pushed to by a user without write access

@DarkLight1337
Copy link
Member

It looks like the model isn't outputting Spanish correctly.

@kylehh
Copy link
Contributor Author

kylehh commented Feb 28, 2025

continue work in #14015 to update code w PromptUpdate

@kylehh kylehh closed this Feb 28, 2025
@kylehh kylehh deleted the pali-mm-processor branch March 16, 2025 17:59
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ready ONLY add when PR is ready to merge/full CI is needed
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants