[Relax][PyTorch] Fix the segfault in from_exported_program when model returns (Tensor, None) tuple

[tlopex]

As per title, this PR resolves the issue #18337

[gemini-code-assist]

Summary of Changes

Hello @tlopex, 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 enhances the stability of the PyTorch frontend for TVM Relax by addressing a critical segfault. The issue arose when from_exported_program encountered None values in a model's output tuple. The change introduces explicit handling for these None values, mapping them to a null_value representation, thereby preventing unexpected program termination and ensuring more robust model export processes.

Highlights

• Segfault Fix: Resolved a segfault in the from_exported_program function within the PyTorch frontend for TVM Relax. This occurred when a model returned a tuple containing a Tensor and None.
• None Value Handling: The _retrieve_args method in base_fx_graph_translator.py now explicitly handles None values, converting them to relax.op.null_value() to prevent crashes.

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 introduces a fix for a segmentation fault that occurs when importing an exported PyTorch program that returns a tuple containing a None value. The change correctly handles None values encountered during argument retrieval in the FX graph translator by converting them to relax.op.null_value(). This ensures that None is properly represented in the Relax IR, preventing the crash. The fix is concise, targeted, and correctly addresses the issue.

[cchung100m]

LGTM, thanks to @tlopex 😄

[mshr-h]

@tlopex
Thanks! Please include unittest under https://github.com/apache/tvm/blob/main/tests/python/relax/test_frontend_from_exported_program.py.

[tlopex]

cc @mshr-h