(documentation) How do I know if generate.py is running on GPU / GPU configuration
maathieu opened this issue · comments
Hi, I have a NVidia Quadro P5200 with 32GB of VRAM, yet when I run the codes for a test they perform extremely slowly and in the task manager the GPU's used ram stays near 0. I think the code is not using my GPU. Is there special configuration to do beyond pip install -r requirements.txt to get this running on GPU?
In general, if you start a new Python session, does
import torch
print(torch.cuda.is_available())
show True
?