Information handling system with a quality of service model contract pipeline

A method comprising:

• storing, in a memory of an information handling system, a plurality of machine learning (ML) models and quality of service (QoS) data;
• performing, by a processor of the information handling system, a registration operation for a plurality of model management frame (MMF) core contracts and a plurality of supporting MMF converted modules (MCMs), wherein each different one of the MMF core contracts is supported by a corresponding different one of the MCMs;
• receiving an application programming interface (API) request including a first ML model;
• in response to the API request, performing a learn operation for the first ML model and determining that a first MCM of the plurality of MCMs is to be used to respond to the API request;
• and
• executing, by the processor, the first ML model via the first MCM to generate output data as a response to the API request.

An information handling system comprising:

• a memory to store a plurality of machine learning (ML) models and quality of service (QoS) data;
• and
• a processor to:
• perform a registration operation for a plurality of model management frame (MMF) core contracts and a plurality of supporting MMF converted modules (MCMs), wherein each different one of the MMF core contracts is supported by a corresponding different one of the MCMs;
• receive an application programming interface (API) request including a first ML model and accuracy of the first ML model as a QoS parameter;
• in response to the API request, perform a learn operation for the first ML model and determine that a first MCM of the plurality of MCMs is to be used to respond to the API request, wherein the first MCM provides a highest level of accuracy for the first ML;
• and
• execute the first ML model via the first MCM to generate output data as a response to the API request.