Skip to content

Conversation

@fzyzcjy
Copy link
Collaborator

@fzyzcjy fzyzcjy commented Dec 1, 2025

Motivation

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @fzyzcjy, 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 enhances the system's profiling capabilities by introducing a new parameter that enables selective profiling of specific inference stages. This allows for more focused performance analysis by letting users choose to profile only the 'prefill' stage, only the 'decode' stage, or any combination thereof, providing greater flexibility and efficiency in performance debugging and optimization efforts.

Highlights

  • Granular Profiling Control: Introduced a new profile_stages parameter that allows users to specify which specific stages of the inference process (e.g., 'prefill', 'decode') should be profiled, offering more targeted performance analysis.
  • API and Data Structure Extension: Extended the ProfileReqInput and ProfileReq data structures, as well as relevant function signatures across the system, to accommodate the new profile_stages parameter.
  • Core Profiling Logic Update: Modified the ProfileManager to utilize the provided profile_stages when configuring the stage_based_trigger, defaulting to profiling both 'prefill' and 'decode' if no specific stages are provided.
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.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request introduces a profile_stages option to allow profiling specific stages such as 'prefill' or 'decode' selectively. The changes correctly propagate this new parameter through the different layers of the application, from the HTTP endpoint down to the profiler configuration. The core logic to use the specified stages or fall back to the default ones is implemented correctly. My review includes a couple of minor suggestions to remove unused imports for better code hygiene.

from sglang.srt.environ import envs
from sglang.srt.managers.io_struct import ProfileReq, ProfileReqOutput, ProfileReqType
from sglang.srt.model_executor.forward_batch_info import ForwardMode
from sglang.srt.server_args import get_global_server_args
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The get_global_server_args import is unused in this file and can be removed to maintain code cleanliness.


from sglang.srt.managers.io_struct import ProfileReqOutput
from sglang.srt.model_executor.forward_batch_info import ForwardMode
from sglang.srt.server_args import get_global_server_args
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The get_global_server_args import is unused in this file and can be removed to maintain code cleanliness.

@fzyzcjy
Copy link
Collaborator Author

fzyzcjy commented Dec 1, 2025

/tag-and-rerun-ci

@github-actions github-actions bot added the run-ci label Dec 1, 2025
@fzyzcjy fzyzcjy merged commit e8ba5a6 into sgl-project:main Dec 1, 2025
127 of 131 checks passed
harvenstar pushed a commit to harvenstar/sglang that referenced this pull request Dec 4, 2025
tonyluj pushed a commit to openanolis/sglang that referenced this pull request Dec 5, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant