Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Document usage of tae for VRAM reduction using wan#1108

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 ourterms of service andprivacy statement. We’ll occasionally send you account related emails.

Already on GitHub?Sign in to your account

Open
CarlGao4 wants to merge3 commits intoleejet:master
base:master
Choose a base branch
Loading
fromCarlGao4:master

Conversation

@CarlGao4
Copy link
Contributor

Added details on using tae to reduce VRAM requirements with links to relevant safetensors

Added details on using tae to reduce VRAM requirements with links to relevant safetensors
@Green-Sky
Copy link
Contributor

It will likely only be slower until upstream merges the convolution kernels for cuda. For vulkan it should already be faster.

@CarlGao4
Copy link
ContributorAuthor

Do we need to mention CISC for reviewing that PR?

@wbruna
Copy link
Contributor

I think it'd be enough to mention that--vae-conv-direct "could be slower", since we don't know what will happen on every backend out there.

And maybe these docs should point to a (renamed and updated)docs/taesd.md instead?

stduhpf, Green-Sky, and CarlGao4 reacted with thumbs up emoji

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

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@CarlGao4@Green-Sky@wbruna

[8]ページ先頭

©2009-2025 Movatter.jp