Fix vLLM Gemma, add vLLM extra

[Amar3tto]

Fixes #30644
Successful run: https://github.com/apache/beam/actions/runs/18772754371/job/53560435392

This PR also contains changes from #36420

---

Thank you for your contribution! Follow this checklist to help us incorporate your contribution quickly and easily:

• Mention the appropriate issue in your description (for example: addresses #123), if applicable. This will automatically add a link to the pull request in the issue. If you would like the issue to automatically close on merging the pull request, comment fixes #<ISSUE NUMBER> instead.
• Update CHANGES.md with noteworthy changes.
• If this contribution is large, please file an Apache Individual Contributor License Agreement.

See the Contributor Guide for more tips on how to make review process smoother.

To check the build health, please visit https://github.com/apache/beam/blob/master/.test-infra/BUILD_STATUS.md

GitHub Actions Tests Status (on master branch)

See CI.md for more information about GitHub Actions CI or the workflows README to see a list of phrases to trigger workflows.

[gemini-code-assist]

Summary of Changes

Hello @Amar3tto, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request by Amar3tto addresses a vLLM Gemma issue (#30644) and introduces a vllm extra to the Apache Beam Python SDK. Key changes include defining the vllm extra and its dependencies in setup.py, updating the vllm.dockerfile to leverage this extra, adding dill to test requirements, and modifying build scripts (common.gradle, run_generate_requirements.sh) to properly handle vllm dependencies, including a conditional torch installation to prevent known issues. The PR also integrates changes from #36420.

Highlights

• Intent: This pull request aims to fix an issue related to vLLM Gemma (addressing The Inference Python Benchmarks Dataflow job is flaky #30644) and introduce a new vllm extra for the Apache Beam Python SDK. It also incorporates changes from a related pull request (Use vLLM extra to generate GPU requirements files #36420).
• Changes Overview: The changes primarily focus on integrating vLLM support more robustly into the Beam Python SDK. This includes defining a new vllm extra in setup.py with its specific dependencies (openai, vllm, triton). The vllm.dockerfile for test resources is updated to use this new extra, simplifying dependency installation. Additionally, dill is added to vllm_tests_requirements.txt, and the common.gradle script is modified to generate gpu_image_requirements.txt that includes the vllm extra. A conditional torch installation is added to run_generate_requirements.sh to mitigate a known issue when vllm extra is used.
• Reviewer Activity: No specific reviewer activity has been noted yet for this pull request.

Ignored Files

• Ignored by pattern: .github/workflows/** (1)
  • .github/workflows/load-tests-pipeline-options/beam_Inference_Python_Benchmarks_Dataflow_VLLM_Gemma_Batch.txt

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[codecov]

Codecov Report

❌ Patch coverage is 0% with 22 lines in your changes missing coverage. Please review.
✅ Project coverage is 36.20%. Comparing base (c52cb21) to head (83ba4ff).
⚠️ Report is 94 commits behind head on master.

Files with missing lines	Patch %	Lines
.../python/apache_beam/ml/inference/vllm_inference.py	0.00%	22 Missing ⚠️

Additional details and impacted files

@@              Coverage Diff              @@
##             master   #36451       +/-   ##
=============================================
- Coverage     55.04%   36.20%   -18.84%     
  Complexity     1667     1667               
=============================================
  Files          1058     1059        +1     
  Lines        165211   165358      +147     
  Branches       1190     1190               
=============================================
- Hits          90939    59874    -31065     
- Misses        72096   103308    +31212     
  Partials       2176     2176               

Flag	Coverage Δ
python	40.50% <0.00%> (-40.45%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[github-actions]

Checks are failing. Will not request review until checks are succeeding. If you'd like to override that behavior, comment assign set of reviewers

[github-actions]

Assigning reviewers:

R: @claudevdm for label python.
R: @Abacn for label build.
R: @damccorm for label website.

Note: If you would like to opt out of this review, comment assign to next reviewer.

Available commands:

• stop reviewer notifications - opt out of the automated review tooling
• remind me after tests pass - tag the comment author after tests pass
• waiting on author - shift the attention set back to the author (any comment or push by the author will return the attention set to the reviewers)

The PR bot will only process comments in the main thread (not review comments).

[damccorm]

Thanks, generally LGTM, just had some minor comments

[damccorm]

Lets revert the pieces inside sdks/python/container for now (this and run_generate_requirements.sh) - they aren't working yet in a CI environment

[Amar3tto]

Removed

[damccorm]

Is this related to the vllm pieces? Rather than removing it entirely, we could also just flip the default to false

[Amar3tto]

I found that this parameter was added by mistake and never used

[Amar3tto]

@damccorm fixed comments

[damccorm]

Thanks!