Skip to content

Conversation

@lambert0312
Copy link
Contributor

@lambert0312 lambert0312 commented Dec 19, 2025

Motivation

  File "/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py", line 2855, in run_scheduler_process
    scheduler = Scheduler(
                ^^^^^^^^^^
  File "/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py", line 322, in __init__
    self.init_model_worker()
  File "/sgl-workspace/sglang/python/sglang/srt/managers/scheduler.py", line 505, in init_model_worker
    nccl_port=self.port_args.nccl_port,
              ^^^^^^^^^^^^^^
AttributeError: 'Scheduler' object has no attribute 'port_args'

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @lambert0312, 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 critical runtime error where the Scheduler class failed to properly initialize its port_args attribute, leading to an AttributeError when subsequent methods attempted to access it. The fix ensures that the port_args passed during object creation is correctly stored, preventing the application from crashing due to this missing attribute.

Highlights

  • Bug Fix: Resolved an AttributeError: 'Scheduler' object has no attribute 'port_args' by ensuring the port_args argument is correctly assigned as an instance attribute within the Scheduler's initialization method.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

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 correctly fixes an AttributeError that occurs when initializing the scheduler with MTP enabled. By adding self.port_args = port_args in the Scheduler's __init__ method, the init_model_worker function can now access self.port_args.nccl_port without crashing. The fix is direct and effective.

self.pp_size = server_args.pp_size
self.dp_size = server_args.dp_size
self.nccl_port = port_args.nccl_port
self.port_args = port_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

While this change correctly fixes the AttributeError, it introduces a small redundancy. The self.port_args attribute appears to be used only to access nccl_port, but self.nccl_port is already initialized from port_args.nccl_port on the preceding line.

For better code clarity and to avoid storing the entire port_args object, a potential follow-up refactoring could be to consistently use self.nccl_port throughout the class. For instance, in init_model_worker, the calls to MTPWorkerV2 and MTPWorker could be changed to use nccl_port=self.nccl_port. This would align with how TpModelWorker and draft_worker_kwargs are handled in the same method and would allow removing self.port_args.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant