This document is relevant for: Inf1, Inf2, Trn1, Trn2, Trn3

Get Started with AWS Neuron#

Get up and running with the AWS Neuron SDK on Inferentia and Trainium. Pick a quickstart by task or by component below.

Note

First time using AWS Neuron? These quickstarts assume you have:

An active AWS account with EC2 access
Basic familiarity with your chosen ML framework (PyTorch or JAX)
SSH access to launch and connect to EC2 instances

For detailed installation instructions, see the Setup Guide.

Choose your path#

Start here if you want an end-to-end first workload.

🚀 Training quickstart

Train your first model on Trainium.

Time: ~15 minutes

Trn1 Trn2 Trn3

🎯 Inference quickstart

Run your first inference on Inferentia.

Time: ~10 minutes

Inf2 Trn1

LLM serving and agentic tooling#

💬 LLM serving with vLLM

Deploy large language models for production inference:

Inf2 Trn1 Trn2

🤖 Amazon AI helper tools

Use AI-powered code assistance for Neuron development — code suggestions, debugging, and optimization.

Quickstarts by component#

Neuron Kernel Interface (NKI)

Deployment (DLC and DLAMI)

Developer tools

Neuron Runtime

Generate a Neuron runtime core dump

Framework setup guides#

Need framework-specific setup instructions?

PyTorch

PyTorch 2.9+ setup

JAX

JAX 0.7+ setup

Additional resources#

Model samples and tutorials - Pre-tested model samples and tutorials
Amazon EC2 - Detailed EC2 deployment workflows
Deploy on AWS - Use Deep Learning Containers
Neuron GitHub Samples - GitHub sample repositories