Skip to content

[diffusion] chore: automatically enable dit_layerwise_offload for Wan#16499

Merged
mickqian merged 3 commits intomainfrom
diffusion-server-args
Jan 7, 2026
Merged

[diffusion] chore: automatically enable dit_layerwise_offload for Wan#16499
mickqian merged 3 commits intomainfrom
diffusion-server-args

Conversation

@mickqian
Copy link
Copy Markdown
Collaborator

@mickqian mickqian commented Jan 5, 2026

Motivation

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

Review Process

  1. Ping Merge Oncalls to start the PR flow. See the PR Merge Process.
  2. Get approvals from CODEOWNERS and other reviewers.
  3. Trigger CI tests with comments (/tag-run-ci-label, /rerun-failed-ci, /tag-and-rerun-ci) or contact authorized users to do so.
  4. After green CI and required approvals, ask Merge Oncalls to merge.

@mickqian mickqian requested a review from yhyang201 as a code owner January 5, 2026 14:23
@mickqian
Copy link
Copy Markdown
Collaborator Author

mickqian commented Jan 5, 2026

/tag-and-rerun-ci

@github-actions github-actions Bot added the diffusion SGLang Diffusion label Jan 5, 2026
@gemini-code-assist
Copy link
Copy Markdown
Contributor

Summary of Changes

Hello @mickqian, 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 configuration for "Wan" diffusion models by automatically activating layer-wise CPU offloading when "SGLANG_CACHE_DIT_ENABLED" is not in use. This change aims to improve the out-of-the-box performance for these models by intelligently applying an optimization strategy, while also refining how environment variables are accessed within the system.

Highlights

  • Automatic Performance Optimization: The pull request introduces logic to automatically enable "dit_layerwise_offload" for "Wan" models, improving performance without requiring manual configuration, specifically when "SGLANG_CACHE_DIT_ENABLED" is not active.
  • Environment Variable Handling: The method for checking the "SGLANG_CACHE_DIT_ENABLED" environment variable has been updated to use a dedicated "envs" module, centralizing environment variable access.
  • Code Readability: Minor formatting adjustments were made to multi-line help messages for command-line arguments, enhancing readability.

🧠 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 to enable Memory in your admin console.

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.

@github-actions github-actions Bot added the run-ci label Jan 5, 2026
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request introduces an automatic optimization by enabling dit_layerwise_offload for Wan models, which should improve performance. It also refactors the access to the SGLANG_CACHE_DIT_ENABLED environment variable to use a centralized helper.

My review focuses on improving the maintainability of the new logic. I've suggested a more robust way to identify the model type instead of relying on class name inspection. I've also included a stylistic recommendation to improve the readability of multi-line help strings for command-line arguments.

Comment thread python/sglang/multimodal_gen/runtime/server_args.py Outdated
Comment thread python/sglang/multimodal_gen/runtime/server_args.py
@mickqian mickqian merged commit badcd02 into main Jan 7, 2026
175 of 184 checks passed
@mickqian mickqian deleted the diffusion-server-args branch January 7, 2026 02:22
@lauri9
Copy link
Copy Markdown

lauri9 commented Jan 12, 2026

Hi! It is fine to enable this feature by default, but please provide an option to override from CLI - now Wan models are forced to use layerwise DiT offloading even if user specifies --dit-layerwise-offload false.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

diffusion SGLang Diffusion run-ci

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants