gemini-code-assist[bot] commented on PR #18676: URL: https://github.com/apache/tvm/pull/18676#issuecomment-3779140434
## Summary of Changes Hello @guan404ming, 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 significantly enhances the Non-Maximum Suppression (NMS) operator within the Relax framework by implementing dynamic output trimming. This improvement ensures that the NMS output tensors contain only relevant detection data, thereby optimizing memory usage and streamlining integration with ONNX runtime environments. The change removes the burden of manual output trimming for users and aligns the operator's behavior with expected dynamic output standards. ### Highlights * **Dynamic Output Trimming for NMS**: The Non-Maximum Suppression (NMS) operator now dynamically trims its output to include only valid detections, eliminating trailing garbage data and improving memory efficiency. * **ONNX Compatibility**: This change directly addresses ONNX compatibility issues by ensuring the NMS operator produces clean, dynamically sized outputs, removing the need for manual post-processing. * **Legalization Implementation**: The `_all_class_non_max_suppression` legalization function has been updated to use `relax.op.dynamic_strided_slice` for trimming. Slicing parameters (`begin`, `end`, `strides`) are constructed using `TE compute` to prevent high-level Relax operator legalization issues. * **Code Simplification**: The previously existing `_create_onnx_nms_te` helper function, which handled fixed-size output slicing, has been removed as its functionality is now integrated into the main legalization logic. * **New Test Coverage**: New tests (`test_all_class_non_max_suppression_legalize_dynamic_trim` and `test_all_class_non_max_suppression_legalize_e2e`) have been added to verify the correct behavior of dynamic trimming and end-to-end execution of the legalized NMS operator. 🧠**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]
