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

Lora unload #55

Merged
merged 13 commits into from
May 21, 2024
Merged

Lora unload #55

merged 13 commits into from
May 21, 2024

Conversation

daanelson
Copy link
Collaborator

Unloads loras when folks are making a prediction w/out one.

@@ -12,7 +12,7 @@ build:
- "libxext6"
- "wget"
python_packages:
- "diffusers==0.19.3"
- "diffusers<=0.25"
Copy link
Member

Choose a reason for hiding this comment

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

Why the <=?

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

this throws an error if we get to 0.25 or higher b/c the attention processor we're using (though fine) is deprecated. compared to the most recent version and we aren't taking a latency hit so this can keep. suppose I could have looked up what the latest 0.24.x patch was but I did not!

@daanelson daanelson merged commit b4aaa90 into main May 21, 2024
@daanelson daanelson deleted the lora_unload branch May 21, 2024 22:39
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.

2 participants