Hey @justin6626!
There have been a couple other posts about this same issue:
- Quantum Transfer Learning - #8 by isaacdevlugt
- Pennylane and Pytorch running on GPU - #17 by Daniel_Wang
It looks like this issue might be due to the fact that putting torch tensors on a gpu is problematic when lightning-gpu is being used as well. Lightning-gpu and torch’s gpu pipeline are entirely differerent, and lightning-gpu expects the data to be on the host right now, so that should fix it!