公开(公告)号：US20250148769A1

公开(公告)日：2025-05-08

申请号：US18504889

申请日：2023-11-08

Applicant: QUALCOMM Incorporated

Inventor： Alexander BEYKUN ,  Sahil GUPTA ,  Jian WANG ,  Prathamesh Prakash PRABHUDESAI ,  Lin WANG ,  Nathan William LEE ,  Veluppillai ARULESAN ,  Jeffrey Baginsky GEHLHAAR

IPC: G06V10/82 ,  G05D1/08 ,  G06V20/58

Abstract: Certain aspects provide techniques and apparatuses for efficient operation of a machine learning model based on partitioning the machine learning model. An example method generally includes receiving a graph for a machine learning model. The graph for the machine learning model generally includes a plurality of subgraphs representing different portions of the machine learning model. The machine learning model is instantiated across a plurality of process domains associated with a same application based on the plurality of subgraphs in the graph for the machine learning model. An inference is generated based on executing the machine learning model across the plurality of process domains, and one or more actions are taken based on the generated inference.

公开(公告)号：US20230164072A1

公开(公告)日：2023-05-25

申请号：US17455882

申请日：2021-11-19

Applicant: QUALCOMM Incorporated

Inventor： Prathamesh Prakash PRABHUDESAI ,  Gaurav Gopal KATHURIA ,  Rohit TRIPATHI ,  Reddy Surendra Prasad BANGALORE VENKATASWAMY

IPC: H04L12/741 ,  H04L29/12 ,  H04W28/06

CPC classification number: H04L45/74 ,  H04L61/256 ,  H04W28/06

Abstract: A CPE receives, over a first connection with a wireless network, a network-assigned prefix for the CPE. The CPE creates a prefix based on a subset of bits from the network assigned prefix. The CPE transmits, over a second connection with a LAN router device, the prefix created by the CPE as a WAN prefix for the LAN router device and the network assigned prefix as a LAN prefix for the LAN router device.