fix compile_deep_gemm.py warmup

[Alcanderian]

Motivation

wait for verify

Modifications

Accuracy Test

Benchmark & Profiling

Checklist

• Format your code according to the Code Formatting with Pre-Commit.
• Add unit tests as outlined in the Running Unit Tests.
• Update documentation / docstrings / example tutorials as needed, according to Writing Documentation.
• Provide throughput / latency benchmark results and accuracy evaluation results as needed, according to Benchmark and Profiling and Accuracy Results.
• For reviewers: If you haven't made any contributions to this PR and are only assisting with merging the main branch, please remove yourself as a co-author when merging the PR.
• Please feel free to join our Slack channel at https://slack.sglang.ai to discuss your PR.

[gemini-code-assist]

Summary of Changes

Hello @Alcanderian, 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!

I've addressed an issue in compile_deep_gemm.py to ensure the warmup process functions correctly, especially when operating in disaggregation mode. This change introduces necessary parameters and logic to properly configure warmup requests for distributed environments.

Highlights

• Dependency Update: I've added an import for FAKE_BOOTSTRAP_HOST from sglang.srt.disaggregation.utils to support disaggregation-specific configurations.
• Function Signature Change: I've updated the warm_up_compile function to accept a new disaggregation_mode argument, allowing for conditional logic based on the system's operational mode.
• Warmup Request Configuration: I've implemented logic within warm_up_compile to set bootstrap_room to 0 and bootstrap_host to FAKE_BOOTSTRAP_HOST for the GenerateReqInput when disaggregation_mode is not "null", ensuring proper warmup behavior in disaggregated setups.

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 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 or fill out our survey 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 pull request fixes the warmup process for compile_deep_gemm.py to correctly handle disaggregation mode. The changes involve passing the disaggregation_mode to the warm_up_compile function and setting the necessary bootstrap parameters on the warmup request. My feedback focuses on improving code clarity and maintainability by using an enum for comparison instead of a string literal.

[gemini-code-assist]

For better type safety and readability, it's recommended to use the DisaggregationMode enum for comparison instead of the string literal "null". This helps prevent potential typos and makes the code's intent clearer.

To apply this suggestion, you'll also need to modify the import on line 20:

from sglang.srt.disaggregation.utils import DisaggregationMode, FAKE_BOOTSTRAP_HOST

Suggested change

	if disaggregation_mode != "null":
	if disaggregation_mode != DisaggregationMode.NULL.value:

[lbh2001]

hello, I fixed this bug in #8618

[zhyncs]

Baron Liu first submitted that PR, merged that PR first, closed this one first, thank you!