[bvolpato]

The inference benchmark workflow submits with Python 3.11, but its vLLM image still installs Python 3.10 and copies that version's SDK harness. The SDK rejects the mismatch, so later benchmarks are skipped (failure).

Use Python 3.11 and its matching Beam harness throughout the image, following the existing deadsnakes installation recipe for the Ubuntu base.

Validated a full image build from a fresh SDK source distribution at this PR head. The image runs Python 3.11.18, the SDK compatibility check accepts a Python 3.11 descriptor and rejects a Python 3.10 control, the worker pool responds to its gRPC API, and the vLLM server CLI starts successfully. Container smoke checks used no network access or model downloads. pip check reports the same existing PyGObject/pycairo dependency issue on the original Python 3.10 Dockerfile prefix and the updated image. GPU model inference and Dataflow were not run.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 79.90%. Comparing base (2213e54) to head (5ed919d).
⚠️ Report is 89 commits behind head on master.

Additional details and impacted files

@@             Coverage Diff             @@
##           master   #40838       +/-   ##
===========================================
+ Coverage        0   79.90%   +79.90%     
===========================================
  Files           0      493      +493     
  Lines           0    83479    +83479     
===========================================
+ Hits            0    66703    +66703     
- Misses          0    16776    +16776     

Flag	Coverage Δ
python	79.90% <ø> (?)

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

☔ View full report in Codecov by Harness.
📢 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]

Assigning reviewers:

R: @damccorm for label python.
Backup reviewer: jrmccluskey (if the main reviewer is unresponsive, you can escalate to them by tagging their username)

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).

[github-actions]

📋 Review Summary

This PR updates vllm.dockerfile to install Python 3.11 via the deadsnakes PPA and copy the Python 3.11 Beam SDK harness, aligning the container runtime with the Python 3.11 environment used by the Dataflow inference benchmark workflow (beam_Inference_Python_Benchmarks_Dataflow.yml).

🔍 General Feedback

• The changes are clean, minimal, and directly resolve the SDK version mismatch between the job submission environment and the worker container.
• The image build, symlink configuration, and SDK harness path (gcr.io/apache-beam-testing/beam-sdk/beam_python3.11_sdk:latest) are all consistent with Python 3.11.

---

💡 Tip: Comment /gemini review on this pull request to trigger a new Gemini code review.