Skip to content

Inference module to utilize CFZ CUDNN Toggle Node in ComfyUI-Zluda#1441

Merged
mohnjiles merged 16 commits intoLykosAI:mainfrom
NeuralFault:comfyui-zluda-cudnnfix2
Oct 26, 2025
Merged

Inference module to utilize CFZ CUDNN Toggle Node in ComfyUI-Zluda#1441
mohnjiles merged 16 commits intoLykosAI:mainfrom
NeuralFault:comfyui-zluda-cudnnfix2

Conversation

@NeuralFault
Copy link
Copy Markdown
Contributor

For real this time.

Adds a module to SM Inference's optional Steps listing. This, when toggled on, will add the CFZ Cudnn Toggle node in ComfyUI-Zluda to SM Inference's workflow disabling Cudnn before VAE Decode to prevent "RuntimeError: GET was unable to find an engine to execute this computation" when MIOpen kicks in.

Is only a simple toggle that needs to be placed above FaceDetailer (since it itself invokes a conv2d function) in Inference's parameters, but otherwise to be the last Step module at the bottom of the list.

@gemini-code-assist
Copy link
Copy Markdown
Contributor

Summary of Changes

Hello @NeuralFault, 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 integrates a specialized module into the StabilityMatrix inference workflow to address CUDNN-related runtime errors that can occur during image generation, especially for users with AMD GPUs leveraging Zluda. By providing a new UI component and a corresponding backend module, users can now explicitly control CUDNN enablement and benchmarking, effectively preventing specific computation errors and improving overall stability and compatibility.

Highlights

  • New CUDNN Toggle Module: Introduces a new module, CfzCudnnToggleModule, to manage CUDNN settings within the inference workflow, specifically for ComfyUI-Zluda.
  • Runtime Error Prevention: Designed to prevent RuntimeError: GET was unable to find an engine to execute this computation errors, particularly on AMD cards using Zluda, by allowing CUDNN to be disabled before VAE Decode.
  • User Interface Integration: Adds a new UI card (CfzCudnnToggleCard) to the inference steps, providing toggle switches for 'Enable CUDNN' and 'CUDNN Benchmark'.
  • Workflow Integration: The module inserts a CUDNNToggleAutoPassthrough node into the ComfyUI workflow, specifically between the sampler's latent output and the VAE decode step.
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.

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 a new inference module to toggle CUDNN for ComfyUI-Zluda, which is useful for preventing errors on AMD cards. The implementation is solid and adds the necessary UI, view models, and logic to insert the CUDNN toggle node into the inference workflow.

My review focuses on improving the clarity and consistency of the new feature. I've suggested renaming a view model property and updating the UI text to make the CUDNN toggle's behavior more intuitive for the user. I've also recommended a more descriptive title for the module and a minor code cleanup. These changes should enhance the user experience and maintainability of the new code.

Copy link
Copy Markdown
Contributor Author

@NeuralFault NeuralFault left a comment

Choose a reason for hiding this comment

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

made some suggested changes.

Copy link
Copy Markdown
Contributor Author

@NeuralFault NeuralFault left a comment

Choose a reason for hiding this comment

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

completed suggested change that got left unresolved.

Copy link
Copy Markdown
Contributor Author

@NeuralFault NeuralFault left a comment

Choose a reason for hiding this comment

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

Remove unused 'System.Linq' using directive

@mohnjiles mohnjiles merged commit f777b9a into LykosAI:main Oct 26, 2025
2 of 3 checks passed
@github-actions github-actions bot locked and limited conversation to collaborators Oct 26, 2025
@NeuralFault NeuralFault deleted the comfyui-zluda-cudnnfix2 branch October 26, 2025 22:26
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants