-
Notifications
You must be signed in to change notification settings - Fork 2.8k
[fix] Fix divide by zero error for llama4. #8683
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[fix] Fix divide by zero error for llama4. #8683
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Summary of Changes
Hello @shenoyvvarun, 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 a critical ZeroDivisionError
that occurred when sglang attempted to load pure dense models, specifically affecting the llama4
model. The error stemmed from a division by zero in the _is_moe_layer
function. My change introduces a safeguard to prevent this specific runtime error, ensuring the stability of the model loading process.
Highlights
- Error Handling: I've introduced a conditional check within the
_is_moe_layer
method inpython/sglang/srt/models/llama4.py
. This check ensures thatself.config.interleave_moe_layer_step
is greater than zero before the modulo operation is performed.
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
-
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. ↩
There was a problem hiding this 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 addresses a ZeroDivisionError
that occurs when self.config.interleave_moe_layer_step
is zero. The fix introduces a check to ensure self.config.interleave_moe_layer_step
is positive before performing the modulo operation. This change is correct, concise, and effectively prevents the crash for non-MoE models. The implementation is clean and follows good practices.
954f93c
to
95abfb7
Compare
Motivation
Modifications
Checklist