fix: bench_serving error with PD disaggregation

[Yi-sir]

Motivation

Fix bench_serving error with PD disaggregation.

related issue: #6497

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.

[gemini-code-assist]

Summary of Changes

Hello @Yi-sir, 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 a specific bug within the bench_serving module that manifested when 'PD disaggregation' was active. The core issue involved an incorrect attempt to retrieve a specific server metric (avg_spec_accept_length) under conditions where it was not guaranteed to be present. The fix introduces a safeguard, ensuring that this metric is only queried when the system is configured for PD disaggregation, thereby enhancing the stability and reliability of the benchmarking process.

Highlights

• Benchmarking Fix: Resolved an error in the bench_serving utility that occurred when 'PD disaggregation' was enabled, specifically related to accessing server information.
• Conditional Logic: Implemented a conditional check to ensure that the avg_spec_accept_length field is only accessed when pd_separated is true, preventing crashes due to its absence in other configurations.

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. ↩

[gemini-code-assist]

Code Review

This pull request addresses a bug in bench_serving.py related to PD disaggregation by adjusting how avg_spec_accept_length is retrieved from the server info. The logic appears sound and correctly handles the different JSON structures for disaggregated and non-disaggregated modes. I have one suggestion to refactor the code for improved conciseness and maintainability.

[lizhiqihhh]

Hi there,
I met a similar problem. This PR really helps a lot. @zhyncs