公开(公告)号：US20240119301A1

公开(公告)日：2024-04-11

申请号：US18464996

申请日：2023-09-11

Applicant: QUALCOMM Incorporated

Inventor： Wonseok JEON ,  Mukul GAGRANI ,  Weiliang ZENG ,  Edward TEAGUE ,  Burak BARTAN ,  Piero ZAPPI ,  Christopher LOTT

IPC: G06N3/092

CPC classification number: G06N3/092

Abstract: A processor-implemented method includes sampling, according to a priority sampling policy, a set of node priorities from a computation graph. Each node priority of the set of node priorities may be associated with a respective node on the computation graph. Additionally, each node may represent an operation of a task performed by an artificial neural network. The method also includes converting, via a list scheduling function, the node priorities to a schedule that associates each node of the computation graph with a processor of a group of processors of a device associated with the artificial neural network, the schedule associated with a makespan. The method further includes performing the task in accordance with the schedule.

公开(公告)号：US20240354346A1

公开(公告)日：2024-10-24

申请号：US18538965

申请日：2023-12-13

Applicant: QUALCOMM Incorporated

Inventor： Christopher LOTT ,  Mingu LEE ,  Wonseok JEON ,  Roland MEMISEVIC

IPC: G06F16/901 ,  G06F40/284

CPC classification number: G06F16/9027 ,  G06F40/284

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for generating a response to a query input in a generative artificial intelligence model. An example method generally includes receiving a plurality of sets of tokens generated based on an input prompt and a first generative artificial intelligence model, each set of tokens in the plurality of sets of tokens corresponding to a candidate response to the input prompt; selecting, using a second generative artificial intelligence model and recursive adjustment of a target distribution associated with the received plurality of sets of tokens, a set of tokens from the plurality of sets of tokens; and outputting the selected set of tokens as a response to the input prompt.

公开(公告)号：US20240118923A1

公开(公告)日：2024-04-11

申请号：US18459277

申请日：2023-08-31

Applicant: QUALCOMM Incorporated

Inventor： Corrado RAINONE ,  Wei David ZHANG ,  Roberto BONDESAN ,  Markus PESCHL ,  Mukul GAGRANI ,  Wonseok JEON ,  Edward TEAGUE ,  Piero ZAPPI ,  Weiliang ZENG ,  Christopher LOTT

IPC: G06F9/48

CPC classification number: G06F9/4881 ,  G06N5/04

Abstract: A processor-implemented method includes generating, by a scheduling model, a group of schedules from a computation graph associated with a task, each node on the computation graph being associated with an operation of an artificial neural network, each schedule of the group of schedules associating each node of the computation graph with a processor of a group of processors of a hardware device. The processor-implemented method also includes testing one or more schedules of the group of schedules on the hardware device or a model of the hardware device. The processor-implemented method further includes selecting a schedule of the one or more schedules based on testing the one or more schedules, the selected schedule satisfying a selection condition.

公开(公告)号：US20230376735A1

公开(公告)日：2023-11-23

申请号：US18103757

申请日：2023-01-31

Applicant: QUALCOMM Incorporated

Inventor： Corrado RAINONE ,  Mukul GAGRANI ,  Yang YANG ,  Roberto BONDESAN ,  Edward TEAGUE ,  Christopher LOTT ,  Wonseok JEON ,  Weiliang ZENG ,  Piero ZAPPI ,  Herke VAN HOOF

IPC: G06N3/047 ,  G06N3/10

CPC classification number: G06N3/047 ,  G06N3/10

Abstract: A processor-implemented method for generating a topological order using an artificial neural network (ANN) includes receiving a set of tasks to be performed. The tasks are represented in a graph including multiple nodes connected by edges. Each node corresponds to a task in the set of tasks. A scheduling priority is assigned to each node in the graph. A next node of potential next nodes is selected according to a probability of each of the potential next nodes based on the assigned scheduling priorities and a topology of the graph. A topological order of the tasks is generated by repeating the selection of the next node.

公开(公告)号：US20250148015A1

公开(公告)日：2025-05-08

申请号：US19012626

申请日：2025-01-07

Applicant: QUALCOMM Incorporated

Inventor： Christopher LOTT ,  Mingu LEE ,  Wonseok JEON ,  Roland MEMISEVIC

IPC: G06F16/901 ,  G06F40/284

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for generating a response to a query input in a generative artificial intelligence model. An example method generally includes receiving a plurality of sets of tokens generated based on an input prompt and a first generative artificial intelligence model, each set of tokens in the plurality of sets of tokens corresponding to a candidate response to the input prompt; selecting, using a second generative artificial intelligence model and recursive adjustment of a target distribution associated with the received plurality of sets of tokens, a set of tokens from the plurality of sets of tokens; and outputting the selected set of tokens as a response to the input prompt.

公开(公告)号：US20240354345A1

公开(公告)日：2024-10-24

申请号：US18538912

申请日：2023-12-13

Applicant: QUALCOMM Incorporated

Inventor： Christopher LOTT ,  Mingu LEE ,  Wonseok JEON ,  Roland MEMISEVIC

IPC: G06F16/901 ,  G06F40/284

CPC classification number: G06F16/9027 ,  G06F40/284

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for generating a response to a query input in a generative artificial intelligence model. An example method generally includes receiving a plurality of sets of tokens generated based on an input prompt and a first generative artificial intelligence model, each set of tokens in the plurality of sets of tokens corresponding to a candidate response to the input prompt; selecting, using a second generative artificial intelligence model and recursive adjustment of a target distribution associated with the received plurality of sets of tokens, a set of tokens from the plurality of sets of tokens; and outputting the selected set of tokens as a response to the input prompt.

公开(公告)号：US20240211312A1

公开(公告)日：2024-06-27

申请号：US18086611

申请日：2022-12-21

Applicant: QUALCOMM Incorporated

Inventor： Weiliang ZENG ,  Christopher LOTT ,  Edward TEAGUE ,  Yang YANG ,  Wonseok JEON ,  Muntasir Amin MALLICK ,  Mukul GAGRANI ,  Piero ZAPPI ,  Joseph Binamira SORIAGA

IPC: G06F9/50

CPC classification number: G06F9/5027

Abstract: A processor-implemented method for compiler optimization using node symmetry includes receiving a representation of an artificial neural network (ANN) include multiple nodes coupled via multiple edges. One or more symmetric sets of nodes are determined based on one or more of a set of attributes for each node or a connectivity of the nodes via the edges. One or more of an order or a schedule for executing the nodes is generated based on the one or more symmetric sets of nodes.

公开(公告)号：US20240037150A1

公开(公告)日：2024-02-01

申请号：US17878677

申请日：2022-08-01

Applicant: QUALCOMM Incorporated

Inventor： Yang YANG ,  Mukul GAGRANI ,  Wonseok JEON ,  Edward TEAGUE ,  Weiliang ZENG ,  Piero ZAPPI ,  Corrado RAINONE ,  Christopher LOTT

IPC: G06F16/901 ,  G06N5/02

CPC classification number: G06F16/9024 ,  G06N5/022

Abstract: A processor-implemented method for generating a schedule for executing operations of a compute graph includes receiving a graph including multiples nodes connected by edges. Each of the multiple nodes represents an operation to be executed. A set of sequences for executing the nodes is determined based on one or more precedence constraints. One or more sequences are selected from the set of sequences based on a memory constraint associated with a device for executing the nodes. A schedule for executing the nodes on the device is generated based on the selected one or more sequences.