[CI/Build] Enlarge tolerance for a CPU multi-modal test

[bigPYJ1151]

Essential Elements of an Effective PR Description Checklist

• The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
• The test plan, such as providing test command.
• The test results, such as pasting the results comparison before and after, or e2e results
• (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.

Purpose

After migrated the CPU CI agents to a new machine, test_multi_image_models[qwen2_5_omni-test_case51] can't pass, even with same codebase and dependencies.

Slightly enlarging the number of candidate logprobs can make it pass.

Test Plan

Test Result

(Optional) Documentation Update

[gemini-code-assist]

Summary of Changes

Hello @bigPYJ1151, 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 introduces a targeted fix for a failing multi-modal CPU CI test (test_multi_image_models[qwen2_5_omni-test_case51]) that began failing after a recent migration of CPU CI agents. The primary change involves adjusting a numerical tolerance within the test configuration for CPU platforms. Additionally, the CI script has been modified to isolate and run only this specific problematic test, allowing for focused validation of the proposed solution.

Highlights

• CI Test Fix for CPU Platforms: Modified the test_multi_image_models[qwen2_5_omni-test_case51] configuration to increase the num_logprobs tolerance from 5 to 8 specifically for CPU environments. This change aims to resolve a test failure observed on new CPU CI agents.
• CI Script Adjustments: Updated the run-cpu-test.sh script to temporarily disable a range of general language generation and pooling tests. The script now specifically targets and runs only the test_multi_image_models[qwen2_5_omni-test_case51] test, facilitating focused debugging and validation of the fix. An offline inference example run was also commented out.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 is currently in preview and 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 to provide feedback.

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. ↩

[gemini-code-assist]

Code Review

This PR addresses a CPU-specific test failure for qwen2_5_omni by increasing the number of logprobs checked. The review includes a reminder to revert the temporary changes in the CI script and a suggestion to add a comment in the test configuration to document why the num_logprobs value is different for CPU.

[gemini-code-assist]

Several tests have been commented out to isolate a specific failing test case. Please remember to revert these changes and re-enable the full suite of CPU tests before merging. Merging this as-is would drastically reduce CI test coverage for CPU environments.

[gemini-code-assist]

The num_logprobs value is different for CPU platforms. Add a brief comment explaining why this value is different for CPU platforms to improve maintainability.

Suggested change

	num_logprobs= 8 if current_platform.is_cpu() else 5,
	num_logprobs= 8 if current_platform.is_cpu() else 5, # Increased for CPU to be more tolerant to minor floating point variations

[github-actions]

👋 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.

🚀