-
Notifications
You must be signed in to change notification settings - Fork 6.5k
[CI] Add quantization #9832
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
[CI] Add quantization #9832
Conversation
| ).images | ||
| out_slice = output[0, -3:, -3:, -1].flatten() | ||
| expected_slice = np.array([0.0149, 0.0322, 0.0073, 0.0134, 0.0332, 0.011, 0.002, 0.0232, 0.0193]) | ||
| expected_slice = np.array([0.0376, 0.0359, 0.0015, 0.0449, 0.0479, 0.0098, 0.0083, 0.0295, 0.0295]) |
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.
Because of the machine change.
| group: aws-g6e-xlarge-plus | ||
| container: | ||
| image: diffusers/diffusers-pytorch-cuda | ||
| options: --shm-size "20gb" --ipc host --gpus 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.
Using a large shared memory here.
| matrix: | ||
| config: | ||
| - backend: "bitsandbytes" | ||
| test_location: "bnb" |
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.
Decided to go with a matrix strategy to accommodate for future backends.
|
@DN6 a gentle ping |
* add quantization to nightly CI. * prep. * fix lib name. * remove deps that are not needed. * fix slice.
* add quantization to nightly CI. * prep. * fix lib name. * remove deps that are not needed. * fix slice.
What does this PR do?
As discussed.