You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm trying to run manipulation notebook on an A100 40 GB GPU but I'm getting out of memory error.
Can you share your insight on this? What did you use for running manipulation process and how can I make it work? I have 4 A100s and as far as I understand the network can't be run parallel.
Thanks!
The text was updated successfully, but these errors were encountered:
You're right that the network cannot be run in parallel for manipulation tasks. I doubt that the OOM comes from the manipulation. Naive question. Have you used torch.no_grad during DDIM generation?
Hi,
I'm trying to run manipulation notebook on an A100 40 GB GPU but I'm getting out of memory error.
Can you share your insight on this? What did you use for running manipulation process and how can I make it work? I have 4 A100s and as far as I understand the network can't be run parallel.
Thanks!
The text was updated successfully, but these errors were encountered: