Fix vLLM Gemma benchmark and PyTorch language modeling tests

[aIbrahiim]

Fixes: #30644
Successful run: https://github.com/aIbrahiim/beam/actions/runs/23171618018/job/67324520640

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, 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 addresses and resolves issues within the vLLM Gemma benchmark and PyTorch language modeling tests. The changes ensure compatibility with updated library APIs and stabilize the testing environment by pinning specific dependency versions, leading to successful test runs and improved reliability of the inference examples.

Highlights

• PyTorch Language Modeling Example: Updated the bert_tokenizer method call from encode_plus to a direct call, aligning with recent transformers library API changes.
• vLLM Gemma Benchmark: Removed an unnecessary blank line in the run function, addressing a minor formatting issue.
• Dependency Updates: Pinned the transformers library version to 4.57.1 and added sentencepiece version 0.2.1 to the vllm_tests_requirements.txt.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog

• sdks/python/apache_beam/examples/inference/pytorch_language_modeling.py
  • Updated the bert_tokenizer method call from encode_plus to a direct call, aligning with recent transformers library API changes.
• sdks/python/apache_beam/examples/inference/vllm_gemma_batch.py
  • Removed an unnecessary blank line in the run function.
• sdks/python/apache_beam/ml/inference/vllm_tests_requirements.txt
  • Pinned the transformers library version to 4.57.1.
  • Added sentencepiece version 0.2.1 to the test requirements.

Ignored Files

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

Activity

• The author, aIbrahiim, has provided a link to a successful GitHub Actions run, indicating that the proposed fixes have passed initial testing.

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. ↩

[Amar3tto]

Please fix formatting