Welcome to AWS Neuron

AWS Neuron is the SDK for AWS Inferentia, the custom designed machine learning chips enabling high-performance deep learning inference applications on EC2 Inf1 instances. Neuron includes a deep learning compiler, runtime and tools that are natively integrated into TensorFlow, PyTorch and Apache MXNet (Incubating). With Neuron, you can develop, profile, and deploy high-performance inference applications on top of EC2 Inf1 instances.

Check Release Details, Neuron Performance page and What’s New in Neuron 1.19.0 (04/29/2022) release.

Getting Started

• QuickStart
• PyTorch
• TensorFlow
• Apache MXNet (Incubating)
• Tutorials
• Performance
• What’s New

Learning Neuron

• Neuron Features
• Neuron Developer Flows
• Containers
• Application Notes
• Neuron FAQ

Neuron SDK

• Setup Guide
• Neuron Compiler
• Neuron Runtime
• Neuron Tools
• NeuronPerf (Beta)
• Release Details
• Roadmap
• Support