ALEXANDRIA, Va., March 5 -- United States Patent no. 12,242,564, issued on March 4, was assigned to HyperAccel Co. Ltd. (Hwaseong-si, South Korea).

"Method and system for performing multi-device based inference for large language model" was invented by Seongmin Hong (Hwaseong-si, South Korea), Junsoo Kim (Hwaseong-si, South Korea) and Gyubin Choi (Hwaseong-si, South Korea).

According to the abstract* released by the U.S. Patent & Trademark Office: "Provided is a method and system for performing multi-device-based inference for a large language model. A multi-device-based inference performance system may include a plurality of devices configured to map to partitions that separate a large language model (LLM) according to an intra-layer par...