Amazon Elastic Inference
Developer Guide

Using AWS Deep Learning Containers With Elastic Inference

AWS Deep Learning Containers with Amazon Elastic Inference (Elastic Inference) are a set of Docker images for serving models in TensorFlow and Apache MXNet (MXNet). Deep Learning Containers can include a wide variety of options for deep learning. With Deep Learning Containers with Elastic Inference, you can create serving containers for TensorFlow 1.14 and later and Apache MXNet (MXNet) 1.4.1 and later. These containers are only available for inference jobs and should not be used for training. See Deep Learning Containers Images for training images. For community discussion, see the Deep Learning Containers Discussion Forum

You can use Deep Learning Containers with Elastic Inference on Amazon Elastic Compute Cloud (Amazon EC2) and Amazon Elastic Container Service (Amazon ECS).