Distributed intelligence delivery system

A method comprising:

• storing information regarding a plurality of compute nodes, including artificial intelligence capabilities and artificial intelligence workload telemetry for each of the plurality of compute nodes, in an enterprise tenant registry;
• receiving an artificial intelligence model session request from an application executing on a client;
• based on the information regarding the plurality of compute nodes, selecting one or more compute nodes of the plurality of compute nodes for execution of the artificial intelligence model session;
• and
• loading a model for the artificial intelligence model session to the one or more compute nodes selected to establish a model session, wherein the model session receives streamed input from the application and returns streamed output to the application.

An article of manufacture comprising:

• a non-transitory computer-readable medium;
• and
• computer-executable instructions carried on the computer-readable medium, the instructions readable by a processor, the instructions, when read and executed, for causing the processor to:
• store information regarding a plurality of compute nodes, including artificial intelligence capabilities and artificial intelligence workload telemetry for each of the plurality of compute nodes, in an enterprise tenant registry;
• receive an artificial intelligence model session request from an application executing on a client;
• based on the information regarding the plurality of compute nodes, select one or more compute nodes of the plurality of compute nodes for execution of the artificial intelligence model session;
• and
• load a model for the artificial intelligence model session to the one or more compute nodes selected to establish a model session, wherein the model session receives streamed input from the application and returns streamed output to the application.