Skip to content
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.

Sign up for GitHub

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

Jump to bottom

[Dance Diffusion] FP16 #980

Merged
merged 2 commits into from
Oct 25, 2022
Merged

[Dance Diffusion] FP16 #980

merged 2 commits into from
Oct 25, 2022

Conversation

patrickvonplaten
Copy link
Contributor

Allow for FP16

@HuggingFaceDocBuilderDev
Copy link

HuggingFaceDocBuilderDev commented Oct 25, 2022 •
edited
Loading

The documentation is not available anymore as the PR was closed or merged.

@patrickvonplaten
Copy link
Contributor Author

Merging this as it reduces memory usage by 50% .

However inference speed is only increased by ~10% on a V100 (cc @NouamaneTazi not sure exactly why)

@patrickvonplaten
Copy link
Contributor Author

Also there seems to be a loss in quality

@patrickvonplaten patrickvonplaten merged commit 365ff8f into main Oct 25, 2022
@patrickvonplaten patrickvonplaten deleted the add_fp16_for_dance_diffusion branch October 25, 2022 17:33
PhaneeshB pushed a commit to nod-ai/diffusers that referenced this pull request Mar 1, 2023
@yzhang93
Modify the annotation OTF to return bytecode module (huggingface#980)
e9864cb
yoonseokjin pushed a commit to yoonseokjin/diffusers that referenced this pull request Dec 25, 2023
@patrickvonplaten
[Dance Diffusion] FP16 (huggingface#980)
2db92f8 
* add in fp16

* up
Sign up for free to 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.
2 participants
@patrickvonplaten @HuggingFaceDocBuilderDev