Deployment Guide#

Currently, UnionML apps support two core types of machine learning microservices: model training and model serving.

Production Backend Deployment#

UnionML uses flytekit under the hood to execute your training and prediction workflows locally, but you can benefit from the reproducibility and scalability benefits of UnionML by deploying your workflows to a production-grade flyte cluster.

Serving Predictions#

Once you have a trained model object that you want to serve in production, you can: