-
Notifications
You must be signed in to change notification settings - Fork 62
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
Refactoring Diffusers pipelines #711
Conversation
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Very nice ! Just a small nit, but otherwise LGTM.
@@ -791,7 +894,7 @@ def _export( | |||
batch size during the compilation, but it comes with a potential tradeoff in terms of latency. | |||
output_hidden_states (`bool`, defaults to `False`): | |||
Whether or not for the traced text encoders to return the hidden states of all layers. | |||
data_parallel_mode (`Optional[Literal["none", "unet", "all"]]`, defaults to `None`): | |||
data_parallel_mode (`Optional[Literal["none", "unet", "transformer", "all"]]`, defaults to `None`): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Maybe you should document this new mode also (although it is not difficult to guess what will happen).
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yeah, will do that in the next PR for completing the dit support!
What does this PR do?
.from_pipe
to solve Cannot use.from_pipe
forNeuronStableDiffusionXLPipeline
#701Before submitting