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

attempts to improve speed #35

Open
wants to merge 8 commits into
base: main
Choose a base branch
from
Open

attempts to improve speed #35

wants to merge 8 commits into from

Conversation

rotarzen
Copy link

This branch attempts:

  • to create a simple test (benchmark.py) to evaluate generation speed
  • to reduce unnecessary computations in UNet3DModel
  • to enable torch compile w/ cudagraphs in UNet3DModel

These changes do not (currently) produce significant speed improvements on eager execution. I find this odd and will attempt to profile the model later.

When compilation over UNet3DModel.forward is enabled with, e.g. python3 gradio_app.py 640 512, process_video() performance is improved by 10% (i.e. 300s video generation -> 270s) on a 3090.

@huzpsb
Copy link

huzpsb commented Jan 5, 2025

Thank you for your work -- that helped me alot

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