Deploying ML Models into Production

MLOps has become a trendy topic lately as managing ML in production has become challenging for teams and organizations. One of the components of MLOps is model deployment. Once a model is trained, it doesn't really have any value until is is deployed in production. One way that people deploy ML models is by containerizing them using docker and exposing the model via a REST endpoint. This works ok, but containerizing a model every time can be a bit cumbersome.