Implement a runtime fix for the Hugging Face export that addresses th…

[abeeha123]

This PR introduces a temporary runtime patch to add missing non-persistent buffers (position_ids, token_type_ids) into the exported program’s state_dict. This resolves the KeyError that occurs during the Hugging Face to TVM import. Note: Still under testing; AssertionError (_assert_tensor_metadata.default) needs to be addressed.ds, token_type_ids) in the Relax frontend.

[gemini-code-assist[bot]]

Summary of Changes

Hello @abeeha123, 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 provides a temporary runtime solution to a KeyError encountered when importing Hugging Face models into TVM. The fix involves dynamically injecting non-persistent buffers, specifically position_ids and token_type_ids, into the exported program's state_dict to ensure they are available during the TVM import process. While this addresses the immediate KeyError, further work is noted to resolve an AssertionError related to tensor metadata.

Highlights

• Problem Resolution: Addresses a KeyError that occurs during the Hugging Face to TVM import process by ensuring that missing non-persistent buffers are included in the exported program's state_dict.
• Runtime Patch Implementation: Introduces a temporary runtime patch using StateDictWrapper and EPWrapper classes to dynamically inject position_ids and token_type_ids into the exported program's state_dict.
• New Script Added: A new Python script, position_id_fix.py, has been added to demonstrate and implement this temporary fix for the buffer injection.
• Known Limitation: The current implementation is still under testing and has a known AssertionError (_assert_tensor_metadata.default) that needs to be resolved.

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 :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.

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.

[^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.