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

AMD Rocm/Ubuntu building my own venv folder results in better performance #402

Closed
schmedes2 opened this issue Jan 14, 2024 · 3 comments
Closed
Labels
stale Stale issue or inactive for long period of time

Comments

@schmedes2
Copy link

I was having issues in comfyui where the first run of a model would take a long time to load and things like sd upscale were very slow. If I installed comfy manually, I didn't have the problems and it was very fast but it was much more unstable. After building my own venv folder in packages/comfyui, its been working great

I'm not sure what the difference between the 2 builds entails. It might be that I uninstall torchvision first then reinstall rocm but, again, not really sure

@ionite34
Copy link
Member

Hm, which pytorch version did you install in your version? And do you have any special env vars set for rocm? If you have more info we can look to improve our rocm install steps

Pent pushed a commit to Pent/StabilityMatrix that referenced this issue Jan 31, 2024
Copy link

This issue is stale because it has been open 30 days with no activity. Remove the stale label or comment, else this will be closed in 5 days.

@github-actions github-actions bot added the stale Stale issue or inactive for long period of time label Jul 17, 2024
Copy link

This issue was closed because it has been stale for 5 days with no activity.

@github-actions github-actions bot closed this as not planned Won't fix, can't repro, duplicate, stale Jul 22, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
stale Stale issue or inactive for long period of time
Projects
None yet
Development

No branches or pull requests

2 participants