how would you do it in Python? if you can write the pipeline for it in Python, you can orchestrate and operationalize it with Prefect.
For GPU, an easy way would be to spin up an agent with EKS-managed nodegroups that have embedded GPUs and a preinstalled
NVIDIA Kubernetes device plugin. This can be created with a single
eksctl
command:
eksctl create cluster --name=prefect-eks-gpu --node-type=p2.xlarge --nodes=2