fastscore/engine repository overview

⁠Description

The FastScore Engine eliminates the need for custom built, “by-hand” approaches to model deployment. Delivered as a Docker image, Engine is built to enable robust model operations for the large enterprise. Our customers have shown Engine allows modeling, data engineering and IT teams to align to a common, flexible approach for deploying their critical machine learning assets. Via its core abstractions, Engine provides a path to rapid deployment, iteration and scale for any application that drives the lines of business.

Please visit the FastScore Engine Product Manual⁠ for a detailed review of how to get FastScore Engine up and running.

⁠FastScore Engine Demo

In order to deploy the FastScore Engine microservice demo execute the following docker command:

docker run -it --rm --name fastscore-rest fastscore/engine:demo

⁠Overview

FastScore Engine is composed of a group of microservices, which can run anywhere in your infrastructure.

The FastScore Engine lives inside a Docker container and contains the various runners for the various languages and model types that FastScore supports.

As of 1.9, there are now two official flavors of the Engine: one based on Alpine linux, and the other based on Ubuntu.

⁠FastScore Microservices Dashboard⁠

Optionally, the FastScore Microservices Dashboard⁠ can be deployed which will provide a visual interface to interact with FastScore Engine and other FastScore fleet components.