[Env] centralize some env vars in environ.py

[alphabetc1]

Motivation

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.
• Follow the SGLang code style guidance.

Review Process

1. Ping Merge Oncalls to start the PR flow. See the PR Merge Process.
2. Get approvals from CODEOWNERS and other reviewers.
3. Trigger CI tests with comments (/tag-run-ci-label, /rerun-failed-ci, /tag-and-rerun-ci) or contact authorized users to do so.
4. After green CI and required approvals, ask Merge Oncalls to merge.

[gemini-code-assist]

Summary of Changes

Hello @alphabetc1, 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 refactors how environment variables are accessed and managed within the SGLang project. By centralizing their definitions in environ.py and adopting a consistent access method, the changes aim to improve code readability, maintainability, and type safety for configuration parameters. This ensures that all environment-dependent settings are managed from a single, well-defined location.

Highlights

• Environment Variable Centralization: Moved various environment variable definitions and their default values into python/sglang/srt/environ.py for centralized management.
• Consistent Access Pattern: Replaced direct os.getenv and get_int_env_var calls with a unified envs.<VAR_NAME>.get() pattern across multiple files, improving consistency and readability.
• New Environment Variables: Introduced new environment variables for disaggregation settings, logging configuration, detokenizer state limits, networking parameters, health check timeouts, and CPU affinity binding within environ.py.

🧠 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. ↩

[gemini-code-assist]

Code Review

This pull request effectively centralizes environment variable access into sglang.srt.environ.py, which is a significant improvement for maintainability and consistency. The changes correctly replace direct os.getenv and os.environ.get calls with the new envs object across multiple files. The logic for handling default values, especially dynamically computed ones, appears to be preserved. I have one suggestion to simplify a condition, but overall the refactoring is well-executed.

[gemini-code-assist]

This check can be simplified. The get() method on EnvStr with a default of "" will return an empty string if the environment variable is not set or is set to an empty string. An empty string evaluates to False in a boolean context. Therefore, a simple if envs.SGLANG_CPU_OMP_THREADS_BIND.get(): is sufficient and more concise.

    if envs.SGLANG_CPU_OMP_THREADS_BIND.get():

[ShangmingCai]

Why use not is_set here, and use is None in other places? Is there any difference?

[alphabetc1]

Based on the existing code, this is related to the default value:

• When the default is not None and we still need to distinguish between “not set” and “set but empty/zero”, use .is_set().
• When the default itself is None and None means “use the default logic”, use is None.

[alphabetc1]

/tag-run-ci-label

[alphabetc1]

/tag-and-rerun-ci