Skip to content

Latest commit

 

History

History
5 lines (5 loc) · 380 Bytes

README.md

File metadata and controls

5 lines (5 loc) · 380 Bytes

This repository contains examples for deep learning inference deployment using AI accelerators:

* Amazon EC2 G4 instances with NVIDIA T4 GPUs and NVIDIA TensorRT

* Amazon EC2 Inf1 instances with AWS Inferentia and AWS Neuron SDK

* Amazon EC2 CPU instances with Amazon Elastic Inference

* Amazon SageMaker deployment hosting for CPUs, GPUs and AWS Inferentia