-
Notifications
You must be signed in to change notification settings - Fork 6k
Fix temb attention #3607
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
Fix temb attention #3607
Conversation
The documentation is not available anymore as the PR was closed or merged. |
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.
Thank you!
Do we need to add a test for this?
|
||
|
||
def disable_full_determinism(): | ||
os.environ["CUDA_LAUNCH_BLOCKING"] = "0" |
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.
Is this for preventing memory problems?
@@ -366,6 +368,56 @@ def test_stable_diffusion_pndm(self): | |||
|
|||
assert np.abs(image_slice.flatten() - expected_slice).max() < 1e-2 | |||
|
|||
@unittest.skipIf(not torch.cuda.is_available(), reason="xformers requires cuda") | |||
def test_stable_diffusion_attn_processors(self): |
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.
Savior!
* Fix temb attention * Apply suggestions from code review * make style * Add tests and fix docker * Apply suggestions from code review
* Fix temb attention * Apply suggestions from code review * make style * Add tests and fix docker * Apply suggestions from code review
Fixes: #3576