gemini-code-assist[bot] commented on PR #18611: URL: https://github.com/apache/tvm/pull/18611#issuecomment-3690829279
## Summary of Changes Hello @junrushao, I'm Gemini Code Assist[^1]! 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 implements a comprehensive breaking change by standardizing the naming convention for all FFI-exposed type keys and global function names within the TVM project. By consistently adding a 'tvm.' prefix, the change aims to improve clarity, prevent potential naming collisions, and establish a well-defined namespace for TVM's internal and external API components across C++ and Python interfaces. This is a foundational change affecting numerous core components and bindings. ### Highlights * **FFI Type Key Standardization**: All FFI-exposed type keys declared using `TVM_FFI_DECLARE_OBJECT_INFO` and `TVM_FFI_DECLARE_OBJECT_INFO_FINAL` macros across various modules (IR, Relax, MetaSchedule, TIR, Runtime) have been consistently prefixed with 'tvm.' to ensure a unified naming convention. * **Global Function Name Prefixing**: Global functions registered via `refl::GlobalDef().def`, `tvm.register_global_func`, and accessed through `get_runtime_func` or `tvm.get_global_func` are now uniformly prefixed with 'tvm.'. This impacts RPC server creation, device API functions, module loaders, and various utility functions. * **Python FFI Initialization Alignment**: The `tvm_ffi.init_ffi_api` calls in Python bindings have been updated to reflect the new 'tvm.' prefix for their respective modules, ensuring seamless integration and consistency between C++ and Python FFI registrations. * **Structural Equality and Hash Function Renaming**: Custom structural equality (`__s_equal__`) and hash (`__s_hash__`) functions for `IRModuleNode` and `VarNode` are now explicitly prefixed with 'tvm.' to align with the new naming scheme. 🧠**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](https://codeassist.google/code-review/login) to enable Memory in your admin console.** <details> <summary><b>Using Gemini Code Assist</b></summary> <br> The full guide for Gemini Code Assist can be found on our [documentation page](https://developers.google.com/gemini-code-assist/docs/review-github-code), here are some quick tips. <b>Invoking Gemini</b> 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. <b>Customization</b> 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](https://developers.google.com/gemini-code-assist/docs/customize-gemini-behavior-github). <b>Limitations & Feedback</b> Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with :thumbsup: and :thumbsdown: 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](https://google.qualtrics.com/jfe/form/SV_2cyuGuTWsEw84yG). <b>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](https://cloud.google.com/products/gemini/code-assist).</b> </details> [^1]: Review the [Privacy Notices](https://policies.google.com/privacy), [Generative AI Prohibited Use Policy](https://policies.google.com/terms/generative-ai/use-policy), [Terms of Service](https://policies.google.com/terms), and learn how to configure Gemini Code Assist in GitHub [here](https://developers.google.com/gemini-code-assist/docs/customize-gemini-behavior-github). Gemini can make mistakes, so double check it and [use code with caution](https://support.google.com/legal/answer/13505487). -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
