-
Notifications
You must be signed in to change notification settings - Fork 5.6k
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] allow big CUDA tests to run properly for LoRA (and others) #9845
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. |
@DN6 comments addressed. @a-r-r-o-w could you also check if we should consider other pipeline tests in this PR (Allegro, etc.)? Okay if we do that in a separate PR. LMK. |
Gently pinging @DN6 and @a-r-r-o-w. I think these tests are important to run nightly. |
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.
Thanks, LGTM! Off to @DN6
@@ -293,7 +297,7 @@ def test_mochi(self): | |||
).frames | |||
|
|||
video = videos[0] | |||
expected_video = torch.randn(1, 16, 480, 848, 3).numpy() | |||
expected_video = torch.randn(1, 19, 480, 848, 3).numpy() |
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.
Thanks for catching!
@DN6 a gentle ping here. |
What does this PR do?
Some comments in-line.