This document is relevant for: Inf1

PyTorch Neuron Tutorials#

Before running a tutorial#

You will run the tutorials on an inf1.6xlarge instance running Deep Learning AMI (DLAMI) to enable both compilation and deployment (inference) on the same instance. In a production environment we encourage you to try different instance sizes to optimize to your specific deployment needs.

Follow instructions at PyTorch Tutorial Setup before running a PyTorch tutorial on Inferentia . We recommend new users start with the ResNet-50 tutorial.

Computer Vision#

ResNet-50 tutorial [html] [notebook]
PyTorch YOLOv4 tutorial [html] [notebook]

Natural Language Processing#

HuggingFace pretrained BERT tutorial [html] [notebook]
HuggingFace pretrained BERT tutorial with shared weights [html] [notebook]
Bring your own HuggingFace pretrained BERT container to Sagemaker Tutorial [html] [notebook]
LibTorch C++ tutorial [html]
TorchServe tutorial [html]
HuggingFace MarianMT tutorial [html] [notebook]

Utilizing Neuron Capabilities#

BERT TorchServe tutorial [html]
NeuronCore Pipeline tutorial [html] [notebook]