User-configurable optimizations of agentic ai system
AssigneeNVIDIA Corporation
InventorsAndrew Wang, Kyle Kranen, Biswa Ranjan Panda, Maksim Khadkevich
Life of this patent
Estimating the term…
Abstract
Apparatuses, systems, and techniques to optimize an agentic artificial intelligence (AI) system, based at least in part on one or more user-configurable parameters. In at least one embodiment, at least one user-configurable parameter is used by one or more compilers to cause generation of at least one optimized graph representation of at least a portion of an agentic AI systems based, at least in part, on at least one performance metric associated with the one or more portions of the one or more agentic AI systems.
Claims20
A processor comprising:
- one or more circuits to use one or more user-configurable parameters to cause one or more compilers to generate one or more optimized graph representations of one or more portions of one or more agentic artificial intelligence (AI) systems based, at least in part, on one or more performance metrics associated with the one or more portions of the one or more agentic AI systems.
A method comprising:
- using one or more user-configurable parameters to cause one or more compilers to generate one or more optimized graph representations of one or more portions of one or more agentic artificial intelligence (AI) systems based, at least in part, on one or more performance metrics associated with the one or more portions of the one or more agentic AI systems.
A system comprising:
- one or more computer devices to use one or more user-configurable parameters to cause one or more compilers to generate one or more optimized graph representations of one or more portions of one or more agentic artificial intelligence (AI) systems based, at least in part, on one or more performance metrics associated with the one or more portions of the one or more agentic AI systems.
Dependencies are inferred from the claim text.