Add Grammar Cache for XGrammar Backend

[flyinglandlord]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @flyinglandlord, 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 significant performance optimization for the XGrammar backend by implementing a caching layer for grammar and JSON schema compilation. By memoizing the results of these compilation processes, the system avoids re-compiling identical grammars or schemas, leading to more efficient processing, especially in scenarios with repetitive grammar usage.

Highlights

• Grammar Compilation Caching: Implemented a caching mechanism using functools.lru_cache for xgrammar and JSON schema compilation. This aims to reduce redundant compilation work and improve performance by storing up to 200 recently compiled grammars/schemas.
• Refactored Grammar Compilation Logic: Centralized the grammar and JSON schema compilation calls into a new dispatch_grammar method within the init_custom function. Existing calls to compile_grammar and compile_json_schema in _init_req_xgrammer_matcher_infos have been updated to utilize this new cached dispatcher.

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 is currently in preview and 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 to provide feedback.

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

The pull request introduces a grammar cache for the XGrammar backend using functools.lru_cache to optimize grammar compilation. The changes involve adding a dispatch_grammar function with caching and updating the _init_req_xgrammer_matcher_infos method to use the cache. I've suggested adding error handling for grammar compilation and considering typed=True for the lru_cache decorator.

[gemini-code-assist]

The lru_cache decorator is used without specifying a typed=True argument. If the type argument to dispatch_grammar can vary in type but represent the same value (e.g., "grammar" vs str("grammar")), the cache may not function as expected. Consider adding typed=True to the decorator to differentiate cache entries by argument type.

Suggested change

	@functools.lru_cache(maxsize=200)
	@functools.lru_cache(maxsize=200, typed=True)
	def dispatch_grammar(type: str, grammar: str):