US Patent Issued to Intel on Oct. 7 for "Autonomous allocation of deep neural network inference requests in a cluster with heterogeneous devices" (California, Oregon Inventors)

ALEXANDRIA, Va., Oct. 8 -- United States Patent no. 12,437,233, issued on Oct. 7, was assigned to Intel Corp. (Santa Clara, Calif.).

"Autonomous allocation of deep neural network inference requests in a cluster with heterogeneous devices" was invented by Suryaprakash Shanmugam (Santa Clara, Calif.), Yamini Nimmagadda (Portland, Ore.) and Akhila Vidiyala (Beaverton, Ore.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems, apparatuses and methods include technology that identifies compute capacities of edge nodes and memory capacities of the edge nodes. The technology further identifies a first variant of an Artificial Intelligence (AI) model, and assigns the first variant to a first edge node of the edge ...