Amazon Technologies, Inc.

Maxwell Edward Chapman Nuyens

Vivek Chawda

Keshav Sethi Attrey

Ravish Hastantram

Chao Zhou

Vivek Menon

Techniques for machine learning prediction using edge devices are described. In some examples a method of use includes receiving a request to load a second model onto an edge device while a first model has already been loaded on the edge device, wherein the second model and the first model share an external handle; loading at least one instance the second model into memory of the edge device; and after the second model has been loaded into memory of the edge device, directing a prediction request to the shared external handle to the second model instead of the first model.

Machine learning model replacement on edge devices

Techniques for automated application footprint discovery for application migration to containers are described. A snapshot of an application instance can be stored, the snapshot including the application instance and resources used by the application instance at runtime. The application instance can be run in an intermediate virtual machine, the intermediate virtual machine including at least one interceptor. At least one dependency of the application instance can be determined using the at least one interceptor while the application instance executes on the intermediate virtual machine. A template including the at least one dependency can be created and an application environment can be generated using the template.

Growing community of inventors

Redwood City, CA, United States of America

Maxwell Edward Chapman Nuyens