torch.compile with dynamic=False

[akaitsuki-ii]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @akaitsuki-ii, 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 streamlines the torch.compile integration across various Diffusion Transformer (DiT) models and their respective pipelines. The core objective is to standardize the compilation behavior by removing explicit dynamic=True flags, thereby leveraging dynamic=False by default, which can lead to more optimized graph compilation. Additionally, it ensures that model-specific components, such as single_blocks in FluxDiT, are correctly included or excluded from the compilation process based on their architectural relevance.

Highlights

• Compilation Strategy Update: The explicit dynamic=True argument has been removed from torch.compile calls in several pipeline files (flux_image.py, qwen_image.py, wan_video.py), defaulting to dynamic=False for potentially more stable or performant compilation.
• Flux DiT Compilation Scope Adjustment: The compile_repeated_blocks method in flux_dit.py now correctly includes self.single_blocks in its compilation loop, ensuring all relevant components of the Flux DiT model are compiled.
• WAN DiT Compilation Scope Refinement: The compile_repeated_blocks method in wan_dit.py has been updated to no longer attempt to compile self.single_blocks, aligning with the model's structure where these blocks are not relevant for compilation.
• Minor Formatting Improvement: A small formatting change was made in flux_dit.py by adding a trailing comma to a nn.Linear layer definition for consistency.

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 modifies several files to remove the dynamic=True argument from calls to compile_repeated_blocks. It also adds a loop to compile single blocks in flux_dit.py.