Also, have you considered perhaps creating a Docker image with all the tools already included, as it
Also, have you considered perhaps creating a Docker image with all the tools already included, as it seems that Massed Compute (and I assume other services like Runpod as well) support Docker images?
It'll both simplify the process (no need to download stuff and install, and users less likely to encounter an error if for example a Python package is updated), and save time (which cost money when renting).
I don't know however if running through a Docker container affects the performance when using a GPU
It'll both simplify the process (no need to download stuff and install, and users less likely to encounter an error if for example a Python package is updated), and save time (which cost money when renting).
I don't know however if running through a Docker container affects the performance when using a GPU
