[sgl-route] Optimize the use of constant slices and retain to simplif…

[lengrongfu]

…y SGLang field removal

Motivation

There are similar operations in the chart and response APIs, so this field is extracted.

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.

[gemini-code-assist]

Summary of Changes

Hello @lengrongfu, 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 optimizes and simplifies the handling of SGLang-specific fields within the router. It consolidates the list of fields that need to be removed from request payloads into a single, lazily initialized constant. This change streamlines the code responsible for filtering these fields before requests are forwarded to OpenAI-compatible endpoints, enhancing code clarity and maintainability across similar operations.

Highlights

• Centralized SGLang Field Definition: A new static Lazy<HashSet> named SGLANG_FIELDS has been introduced to centralize the definition of SGLang-specific fields that need to be stripped from requests. This replaces duplicated hardcoded lists, improving maintainability and reducing redundancy.
• Optimized Field Removal Logic: The logic for removing SGLang-specific fields from request payloads has been refactored. Instead of iterating and removing individual keys, the code now utilizes the obj.retain method in conjunction with the new SGLANG_FIELDS constant, simplifying the removal process in both the chart and response API handling.

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 refactors the removal of SGLang-specific fields from request payloads by introducing a static HashSet of field names. This is a good improvement, as it centralizes the list of fields, eliminates duplicated code, and uses a more performant retain method instead of repeated remove calls. The code is cleaner and more efficient. I have one minor suggestion to make the HashSet initialization even more concise.

[slin1237]

thanks for the contribution
pr lgtm, just some minor fmt error
we used

rustup run nightly cargo fmt

for better fmt

[lengrongfu]

rustup run nightly cargo fmt

thanks ~, I noticed that we have a pre-commit function. Can we add these basic operations to pre-commit?

[slin1237]

rustup run nightly cargo fmt

thanks ~, I noticed that we have a pre-commit function. Can we add these basic operations to pre-commit?

we should, and we tried
current router requires protobuf, it has a lot of dependencies and we paused the work, but we 100% should