Reintroduce memory usage fix

[fzyzcjy]

Motivation

original: #8413
seems to be accidentally removed at: #8552

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

• Format your code according to the Format code with pre-commit.
• Add unit tests according to the Run and add unit tests.
• Update documentation according to Write documentations.
• Provide accuracy and speed benchmark results according to Test the accuracy and Benchmark the speed.

[gemini-code-assist]

Summary of Changes

Hello @fzyzcjy, 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 aims to reintroduce a critical memory optimization that was inadvertently removed in a previous change. The core purpose is to reduce overall memory consumption by ensuring that temporary weight scale tensors are explicitly deallocated once their data has been utilized. This change helps maintain efficient resource usage within the system.

Highlights

• Memory Optimization Reintroduction: This pull request reintroduces a previously existing memory optimization that was accidentally removed. It explicitly deletes intermediate weight scale tensors (w13_weight_scale and w2_weight_scale) after they have been processed and their data copied to their swizzled counterparts.
• Resource Management: By adding explicit 'del' statements, the PR ensures that temporary weight scale data is promptly released from memory, preventing unnecessary memory retention during the model's weight processing phase.

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 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 reintroduces a memory usage fix by deleting w13_weight_scale and w2_weight_scale attributes from the layer object after they are used in ModelOptNvFp4FusedMoEMethod.process_weights_after_loading. This is a good practice for memory optimization, especially during model loading, as it frees up memory from tensors that are no longer needed. The change is correct and well-contained.