Posted On: Apr 4, 2018
Apache MXNet Model Server (MMS) is an open source model-serving tool designed to simplify the deployment of deep learning models at scale. MMS version 0.3 allows developers to set up a scalable serving infrastructure for production, using pre-built container images pre-configured and optimized for deep learning workloads on Amazon EC2 instances.
The container images are published to Docker Hub and are pre-configured and optimized for both CPU hosts (EC2 C5.2xlarge instance) and multi-GPU hosts (EC2 P3.8xlarge instance). MMS also provides tooling to package MXNet and ONNX neural network models into a single “model archive,” which includes all of the artifacts needed to serve the model.
To learn more about MMS, visit the model zoo and documentation.