Good morning,

I would like to deploy AI applications in my Kubernetes cluster.

Currently, my Kubernetes cluster has the following configuration:

• 3 master nodes

• 3 worker nodes

I was thinking of adding two GPU worker nodes equipped with GPU cards and scheduling the AI model pods on those nodes. However, I'm not sure if this is the cleanest, most scalable, and best-practice approach for deploying AI workloads in Kubernetes.

Could you advise me on the most suitable architecture and deployment strategy?