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.

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

Continuation of #942: additional float64 failure #996

Merged
merged 10 commits into from
Oct 27, 2022
Merged

Continuation of #942: additional float64 failure #996

merged 10 commits into from
Oct 27, 2022

Conversation

pcuenca
Copy link
Member

@pcuenca pcuenca commented Oct 26, 2022

No description provided.

@pcuenca pcuenca requested a review from anton-l October 26, 2022 15:24
@HuggingFaceDocBuilderDev
Copy link

HuggingFaceDocBuilderDev commented Oct 26, 2022

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

@patrickvonplaten
Copy link
Contributor

Looks good to me, but @anton-l is the expert here :-)

Copy link
Member

@anton-l anton-l left a comment

Choose a reason for hiding this comment

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

Oof, even I got confused by self.timesteps vs timesteps for a minute here, we'll probably need a better name at some point 😅

Going back to the PR's purpose: looks good, thanks Pedro!

@pcuenca
Copy link
Member Author

pcuenca commented Oct 26, 2022

Oof, even I got confused by self.timesteps vs timesteps for a minute here, we'll probably need a better name at some point 😅

Yes, the same thing happened to me :) We have timesteps, self.timesteps and then schedule_timesteps a few lines later, wasn't sure how to untangle them.

@pcuenca pcuenca merged commit 1d04e1b into main Oct 27, 2022
@pcuenca pcuenca deleted the fix-lms-mps branch October 27, 2022 09:08
yoonseokjin pushed a commit to yoonseokjin/diffusers that referenced this pull request Dec 25, 2023
…ace#996)

* Add failing test for huggingface#940.

* Do not use torch.float64 in mps.

* style

* Temporarily skip add_noise for IPNDMScheduler.

Until huggingface#990 is addressed.

* Fix additional float64 error in mps.

* Improve add_noise test

* Slight edit – I think it's clearer this way.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants