PyTorch Neuron (torch-neuron) — Archived

Warning

This document is archived. torch-neuron (Inf1) is no longer actively developed. For new workloads, use TorchNeuron Native or torch-neuronx. See PyTorch Support on Neuron for current PyTorch support.

PyTorch Neuron (torch-neuron) was the original PyTorch integration for AWS Inferentia (Inf1) instances. This package supported inference workloads on NeuronCores v1 architecture.

API Reference

• API Reference Guide (torch-neuron)
• PyTorch-Neuron trace python API
• PyTorch Neuron (torch-neuron) Core Placement API
• torch.neuron.DataParallel API

Developer Guide

• Developer Guide (torch-neuron)
• Troubleshooting Guide for PyTorch Neuron (torch-neuron)

Tutorials

• Tutorials for Inference with torch-neuron (Inf1)

Setup

• Install PyTorch Neuron (torch-neuron)
• Update to latest PyTorch Neuron (torch-neuron)

Misc

• Additional Examples (torch-neuron)
• Misc (torch-neuron)