Skip to content

Conversation

fzyzcjy
Copy link
Collaborator

@fzyzcjy fzyzcjy commented Aug 17, 2025

Motivation

Since it is nontrivial to compute the real max_num_extend_tokens on D at startup, here I add an assertion and let users manually modify it, thus it looks like an assertion instead of code change.

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

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.

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 introduces a new assertion within the memory allocator to proactively detect potential issues related to extending memory for tokens. Specifically, it checks if the requested number of tokens for extension exceeds the maximum allowed, aiming to prevent or diagnose memory pool leak errors as indicated by the PR title.

Highlights

  • Memory Allocation Validation: An assertion has been added to the alloc_extend function in python/sglang/srt/mem_cache/allocator.py. This assertion verifies that the number of tokens requested for extension (extend_num_tokens) does not exceed the pre-calculated maximum (max_num_extend_tokens_next_power_of_2). This helps in catching invalid memory extension requests early.
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. 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 adds an assertion to PagedTokenToKVPoolAllocator.alloc_extend to prevent a potential memory corruption issue, which is a good defensive measure. My feedback focuses on improving the clarity of the new assertion message for better maintainability.

@zhyncs zhyncs merged commit b3c1f2e into sgl-project:main Aug 17, 2025
119 of 132 checks passed
narutolhy pushed a commit to narutolhy/sglang that referenced this pull request Aug 17, 2025
fzyzcjy added a commit to fzyzcjy/sglang that referenced this pull request Aug 18, 2025
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.

2 participants