Skip to content

Conversation

@hnyls2002
Copy link
Collaborator

No description provided.

@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @hnyls2002, 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 test suite designed to verify the constrained decoding capabilities when utilizing the EAGLE speculative decoding algorithm within the spec-v2 framework. It sets up a dedicated SGLang server instance with specific configurations, including the xgrammar backend, to ensure that constrained generation functions correctly under these advanced decoding conditions.

Highlights

  • New Test File Added: A new test file, test/srt/test_eagle_constrained_decoding.py, has been introduced to validate constrained decoding functionality.
  • EAGLE Speculative Decoding Test: The new test specifically targets the EAGLE speculative decoding algorithm, ensuring its compatibility with constrained decoding.
  • xgrammar Backend Configuration: The test configures the SGLang server to use the xgrammar backend for constrained decoding, verifying its integration with the speculative decoding setup.
  • SGLANG_ENABLE_SPEC_V2: The test explicitly enables the SGLANG_ENABLE_SPEC_V2 environment variable, indicating its relevance to the new speculative decoding framework.
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.

@hnyls2002 hnyls2002 marked this pull request as draft November 4, 2025 17:38
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 a base test class for constrained decoding tests with EAGLE speculative decoding. My review identifies a critical issue that would prevent the tests from running due to incorrect argument types for the server launch process. I have also included a suggestion to rename the test base class to align with common testing practices and prevent the test runner from discovering this base class, which contains no tests.

Comment on lines +39 to +44
"--speculative-num-steps",
cls.spec_steps,
"--speculative-eagle-topk",
cls.spec_topk,
"--speculative-num-draft-tokens",
cls.spec_draft_tokens,
Copy link
Contributor

Choose a reason for hiding this comment

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

critical

The command-line arguments for the server launch must all be strings. The integer values for spec_steps, spec_topk, and spec_draft_tokens are not converted to strings, which will cause a TypeError when the server process is launched. They should be converted using str().

Suggested change
"--speculative-num-steps",
cls.spec_steps,
"--speculative-eagle-topk",
cls.spec_topk,
"--speculative-num-draft-tokens",
cls.spec_draft_tokens,
"--speculative-num-steps",
str(cls.spec_steps),
"--speculative-eagle-topk",
str(cls.spec_topk),
"--speculative-num-draft-tokens",
str(cls.spec_draft_tokens),

)


class TestEagleServerBase(CustomTestCase, TestRegexConstrainedMixin):
Copy link
Contributor

Choose a reason for hiding this comment

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

medium

To prevent the unittest test runner from discovering this base class (which contains no tests), it's a good practice to not prefix its name with Test. I suggest renaming it to EagleServerTestBase. Subclasses intended for testing can then inherit from it and be named with a Test prefix.

Suggested change
class TestEagleServerBase(CustomTestCase, TestRegexConstrainedMixin):
class EagleServerTestBase(CustomTestCase, TestRegexConstrainedMixin):

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.

3 participants