Skip to content

[Docs] Add documentation about using ParaAttention to optimize FLUX and HunyuanVideo #10544

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 30 commits into from
Jan 16, 2025

Conversation

chengzeyi
Copy link
Contributor

What does this PR do?

This PR implements the proposal for #10383

Fixes # (issue)

Before submitting

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@chengzeyi chengzeyi changed the title Add para_attn_flux.md and para_attn_hunyuan_video.md Add Documentation about using ParaAttention to Optimize FLUX and HunyuanVideo Jan 13, 2025
@chengzeyi chengzeyi changed the title Add Documentation about using ParaAttention to Optimize FLUX and HunyuanVideo Add documentation about using ParaAttention to optimize FLUX and HunyuanVideo Jan 13, 2025
@chengzeyi chengzeyi changed the title Add documentation about using ParaAttention to optimize FLUX and HunyuanVideo [Docs] Add documentation about using ParaAttention to optimize FLUX and HunyuanVideo Jan 13, 2025
@hlky hlky linked an issue Jan 13, 2025 that may be closed by this pull request
@hlky hlky requested a review from stevhliu January 13, 2025 08:49
Copy link
Member

@stevhliu stevhliu left a comment

Choose a reason for hiding this comment

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

Great start and thanks so much again! ❤️

You don't need to add the code that generates the baseline. Users are probably already familiar with the code for that and are more interested in seeing how to apply the practical stuff. A table with the baseline numbers is sufficient!

@yiyixuxu yiyixuxu added the roadmap Add to current release roadmap label Jan 13, 2025
@chengzeyi
Copy link
Contributor Author

@stevhliu Thank your for your professional advice!

I have refactored the documentation according to your advice. And here is the PR for the included images: https://huggingface.co/datasets/huggingface/documentation-images/discussions/416

Hope to see it get merged!

Copy link
Member

@stevhliu stevhliu left a comment

Choose a reason for hiding this comment

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

Left some more mostly minor comments, but everything looks to be in great shape and ready to merge soon! 🚀

chengzeyi and others added 11 commits January 15, 2025 14:26
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
@chengzeyi
Copy link
Contributor Author

@stevhliu Updated, hope to see it get merged soon!

@stevhliu
Copy link
Member

Hey, looks like there are still some unresolved comments (for example, updating the links)!

chengzeyi and others added 2 commits January 16, 2025 10:56
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
chengzeyi and others added 11 commits January 16, 2025 10:58
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
@chengzeyi
Copy link
Contributor Author

@stevhliu Thank you for your detailed guidance. I missed some comments and now they should have been all resolved!

Copy link
Member

@stevhliu stevhliu left a comment

Choose a reason for hiding this comment

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

Thanks so much again for adding these docs! 🤗

@stevhliu stevhliu merged commit 17d99c4 into huggingface:main Jan 16, 2025
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
roadmap Add to current release roadmap
Projects
Archived in project
Development

Successfully merging this pull request may close these issues.

[Request] Optimize HunyuanVideo Inference Speed with ParaAttention
3 participants