Databricks MLflow Model Serving provides a turnkey solution to host machine learning (ML) models as REST endpoints that are updated automatically, enabling data science teams to own the end-to-end lifecycle of a real-time machine learning model from training to production.

In this video from a Data + AI Summit Europe 2020 Meetup, Andre Mesarovic introduces MLflow model serving, talks about scoring models with MLflow (including online with MLflow scoring server and offline with Apache Spark), and custom model deployment and scoring.