This repository contains labs and instructions for deploying ML models on AWS inferentia instances using EC2 and Amazon SageMaker. AWS inferentia instances provide signficant cost/performance benefits compared to other GPU instances while performing inference on large and complex models requiring GPU.
This repository has two sections:
- Inferentia on EC2
- Inferentia on SageMaker
You can choose to complete either or both of the sections. The sections contain further detailed instructions to complete the labs.
See CONTRIBUTING for more information.
For licensing information, check LICENSE