[misc] depdencies & enviroment flag

[hnyls2002]

• Remove gguf in optional dependency (already in dependency)
• Remove --enable-beta-spec and introduce SGLANG_ENABLE_SPEC_V2 environment vairable.

[gemini-code-assist]

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 refines the project's dependency management by removing a redundant entry and streamlines the configuration of speculative decoding. It transitions a specific feature flag from a command-line argument to an environment variable, SGLANG_ENABLE_SPEC_V2, which enhances flexibility and consistency in how this feature is enabled across different environments. The changes also include necessary updates to the server argument parsing and the relevant test cases to reflect this new configuration approach.

Highlights

• Dependency Cleanup: The gguf package has been removed from the optional test dependencies in pyproject.toml as it was already included in the main dependencies, avoiding redundancy.
• Environment Variable for Speculative Decoding: The --enable-beta-spec command-line argument has been replaced by a new environment variable, SGLANG_ENABLE_SPEC_V2, to control the enabling of Spec V2 for speculative decoding.
• Configuration Streamlining: The logic for handling speculative decoding, specifically the 'beta spec' feature, has been updated to utilize the new SGLANG_ENABLE_SPEC_V2 environment variable, centralizing configuration management.
• Test Suite Adaptation: The test suite for Eagle speculative inference has been updated to set the SGLANG_ENABLE_SPEC_V2 environment variable programmatically, ensuring proper testing of the new configuration method.

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 correctly replaces the --enable-beta-spec command-line flag with the SGLANG_ENABLE_SPEC_V2 environment variable, which is a good move for configuration management. The dependency cleanup in pyproject.toml is also appropriate. I've added a couple of suggestions: one for improving code readability in server_args.py and another to clarify an unrelated change in a test file.