Get Started #

Welcome to the HPE Machine Learning Inferencing Software documentation! Here you will find everything you need to get started with HPE Machine Learning Inferencing Software.

How to Approach Getting Started #

Set up your developer system.
Set up HPE MSC Docker Registry credentials.
Complete the Platform Deployment Quickstart guide or connect to an existing instance.
Complete the Service Deployment Quickstart guide.

Developer System Setup

Set up your developer system with the necessary tools and libraries.

HPE MSC Docker Registry Setup

Create HPE MSC Docker Registry credentials to pull images for platform installation.

Connect to Existing Instance

Connect to an existing instance of the platform.

Platform Setup Quickstart

Deploy the inferencing platform on a Kubernetes cluster.

Inference Service Deployment Quickstart

Deploy an inference service using a pre-existing model image.

Glossary

Artifact
Bento
Canary Rollout
Deployment
Deployment Token
Inference Service
Model Image
Model Token
openllm