Generating and deploying packages for machine learning at edge devices

A method, comprising:

• performing, by one or more computing devices of a provider network:
• receiving an indication of:
• an inference application, wherein the inference application comprises one or more functions configured to perform one or more actions based on inference data generated by a machine learning model;
• a machine learning framework configured to run at least a portion of a machine learning model;
• the machine learning model configured to generate the inference data;
• and
• at least one connected device;
• and
• generating a package based at least on the inference application, the machine learning model, and the machine learning framework;
• and
• deploying the package to the at least one connected device.

A non-transitory computer-readable storage medium storing program instructions that, when executed by one or more computing devices for a machine learning deployment service of a provider network, cause the one or more computing devices to implement:

• receiving an indication of:
• an inference application, wherein the inference application comprises one or more functions configured to perform one or more actions based on inference data generated by a machine learning model;
• a machine learning framework configured to run at least a portion of a machine learning model;
• the machine learning model configured to generate the inference data;
• and
• at least one connected device;
• and
• generating a package based at least on the inference application, the machine learning framework, and the machine learning model;
• and
• deploying the package to the at least one connected device.