According to https://kubernets.io:
Kubernetes is an open-source system for automating deployment, scaling, and management of containerized applications.
TensorFlow models can be scaled to be served from hundreds or thousands of TF Serving services using Kubernetes clusters in the production environment. Kubernetes clusters can be run on all popular public clouds, such as GCP, AWS, Azure, as well as in your on-premises private cloud. So let us dive right in to learn to install Kubernetes and then deploy the MNIST model on Kubernetes Cluster.