Using the DLAMI with Amazon Neuron
A typical workflow with the Amazon Neuron SDK is to compile a previously trained machine learning model on a compilation server. After this, distribute the artifacts to the Inf1 instances for execution. Amazon Deep Learning AMIs (DLAMI) comes pre-installed with everything you need to compile and run inference in an Inf1 instance that uses Inferentia.
The following sections describe how to use the DLAMI with Inferentia.