公开(公告)号：US10963301B2

公开(公告)日：2021-03-30

申请号：US16932581

申请日：2020-07-17

Applicant: Google LLC

Inventor： Erik Nathan Vee ,  Manish Deepak Purohit ,  Joshua Ruizhi Wang ,  Shanmugasundaram Ravikumar ,  Zoya Svitkina

IPC: G06F9/48 ,  G06F16/901 ,  G06N3/02

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scheduling operations represented on a computation graph. One of the methods receiving, by a computation graph system, a request to generate a schedule for processing a computation graph, obtaining data representing the computation graph generating a separator of the computation graph; and generating the schedule to perform the operations represented in the computation graph, wherein generating the schedule comprises: initializing the schedule with zero nodes; for each node in the separator: determining whether the node has any predecessor nodes in the computation graph, when the node has any predecessor nodes, adding the predecessor nodes to the schedule, and adding the node in the schedule, and adding to the schedule each node in each subgraph that is not a predecessor to any node in the separator on the computation graph.

公开(公告)号：US20210019184A1

公开(公告)日：2021-01-21

申请号：US16932581

申请日：2020-07-17

Applicant: Google LLC

Inventor： Erik Nathan Vee ,  Manish Deepak Purohit ,  Joshua Ruizhi Wang ,  Shanmugasundaram Ravikumar ,  Zoya Svitkina

IPC: G06F9/48 ,  G06N3/02 ,  G06F16/901

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scheduling operations represented on a computation graph. One of the methods receiving, by a computation graph system, a request to generate a schedule for processing a computation graph, obtaining data representing the computation graph generating a separator of the computation graph; and generating the schedule to perform the operations represented in the computation graph, wherein generating the schedule comprises: initializing the schedule with zero nodes; for each node in the separator: determining whether the node has any predecessor nodes in the computation graph, when the node has any predecessor nodes, adding the predecessor nodes to the schedule, and adding the node in the schedule, and adding to the schedule each node in each subgraph that is not a predecessor to any node in the separator on the computation graph.

公开(公告)号：US20240232686A1

公开(公告)日：2024-07-11

申请号：US18012292

申请日：2022-07-29

Applicant: Google LLC

Inventor： Yicheng Fan ,  Jingyue Shen ,  Deqiang Chen ,  Peter Shaosen Young ,  Dana Alon ,  Erik Nathan Vee ,  Shanmugasundaram Ravikumar ,  Andrew Tomkins

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: Systems and methods of the present disclosure are directed to portion-specific compression and optimization of machine-learned models. For example, a method for portion-specific compression and optimization of machine-learned models includes obtaining data descriptive of one or more respective sets of compression schemes for one or more model portions of a plurality of model portions of a machine-learned model. The method includes evaluating a cost function to respectively select one or more candidate compression schemes from the one or more sets of compression schemes. The method includes respectively applying the one or more candidate compression schemes to the one or more model portions to obtain a compressed machine-learned model comprising one or more compressed model portions that correspond to the one or more model portions.

公开(公告)号：US20210216367A1

公开(公告)日：2021-07-15

申请号：US17214699

申请日：2021-03-26

Applicant: Google LLC

Inventor： Erik Nathan Vee ,  Manish Deepak Purohit ,  Joshua Ruizhi Wang ,  Shanmugasundaram Ravikumar ,  Zoya Svitkina

IPC: G06F9/48 ,  G06F16/901 ,  G06N3/02

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scheduling operations represented on a computation graph. One of the methods receiving, by a computation graph system, a request to generate a schedule for processing a computation graph, obtaining data representing the computation graph generating a separator of the computation graph; and generating the schedule to perform the operations represented in the computation graph, wherein generating the schedule comprises: initializing the schedule with zero nodes; for each node in the separator: determining whether the node has any predecessor nodes in the computation graph, when the node has any predecessor nodes, adding the predecessor nodes to the schedule, and adding the node in the schedule, and adding to the schedule each node in each subgraph that is not a predecessor to any node in the separator on the computation graph.

公开(公告)号：US12141605B2

公开(公告)日：2024-11-12

申请号：US18223495

申请日：2023-07-18

Applicant: Google LLC

Inventor： Erik Nathan Vee ,  Manish Deepak Purohit ,  Joshua Ruizhi Wang ,  Shanmugasundaram Ravikumar ,  Zoya Svitkina

IPC: G06F9/48 ,  G06F16/901 ,  G06N3/02

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scheduling operations represented on a computation graph. One of the methods receiving, by a computation graph system, a request to generate a schedule for processing a computation graph, obtaining data representing the computation graph generating a separator of the computation graph; and generating the schedule to perform the operations represented in the computation graph, wherein generating the schedule comprises: initializing the schedule with zero nodes; for each node in the separator: determining whether the node has any predecessor nodes in the computation graph, when the node has any predecessor nodes, adding the predecessor nodes to the schedule, and adding the node in the schedule, and adding to the schedule each node in each subgraph that is not a predecessor to any node in the separator on the computation graph.

公开(公告)号：US20240370717A1

公开(公告)日：2024-11-07

申请号：US18313189

申请日：2023-05-05

Applicant: Google LLC

Inventor： Qifei Wang ,  Yicheng Fan ,  Wei Xu ,  Jiayu Ye ,  Lu Wang ,  Chuo-Ling Chang ,  Dana Alon ,  Erik Nathan Vee ,  Hongkun Yu ,  Matthias Grundmann ,  Shanmugasundaram Ravikumar ,  Andrew Stephen Tomkins

IPC: G06N3/08

Abstract: A method for a cross-platform distillation framework includes obtaining a plurality of training samples. The method includes generating, using a student neural network model executing on a first processing unit, a first output based on a first training sample. The method also includes generating, using a teacher neural network model executing on a second processing unit, a second output based on the first training sample. The method includes determining, based on the first output and the second output, a first loss. The method further includes adjusting, based on the first loss, one or more parameters of the student neural network model. The method includes repeating the above steps for each training sample of the plurality of training samples.

公开(公告)号：US20240126596A1

公开(公告)日：2024-04-18

申请号：US18223495

申请日：2023-07-18

Applicant: Google LLC

Inventor： Erik Nathan Vee ,  Manish Deepak Purohit ,  Joshua Ruizhi Wang ,  Shanmugasundaram Ravikumar ,  Zoya Svitkina

IPC: G06F9/48 ,  G06F16/901 ,  G06N3/02

CPC classification number: G06F9/4881 ,  G06F16/9024 ,  G06N3/02

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scheduling operations represented on a computation graph. One of the methods receiving, by a computation graph system, a request to generate a schedule for processing a computation graph, obtaining data representing the computation graph generating a separator of the computation graph; and generating the schedule to perform the operations represented in the computation graph, wherein generating the schedule comprises: initializing the schedule with zero nodes; for each node in the separator: determining whether the node has any predecessor nodes in the computation graph, when the node has any predecessor nodes, adding the predecessor nodes to the schedule, and adding the node in the schedule, and adding to the schedule each node in each subgraph that is not a predecessor to any node in the separator on the computation graph.

公开(公告)号：US11755367B2

公开(公告)日：2023-09-12

申请号：US17214699

申请日：2021-03-26

Applicant: Google LLC

Inventor： Erik Nathan Vee ,  Manish Deepak Purohit ,  Joshua Ruizhi Wang ,  Shanmugasundaram Ravikumar ,  Zoya Svitkina

IPC: G06F9/48 ,  G06F16/901 ,  G06N3/02

CPC classification number: G06F9/4881 ,  G06F16/9024 ,  G06N3/02

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scheduling operations represented on a computation graph. One of the methods receiving, by a computation graph system, a request to generate a schedule for processing a computation graph, obtaining data representing the computation graph generating a separator of the computation graph; and generating the schedule to perform the operations represented in the computation graph, wherein generating the schedule comprises: initializing the schedule with zero nodes; for each node in the separator: determining whether the node has any predecessor nodes in the computation graph, when the node has any predecessor nodes, adding the predecessor nodes to the schedule, and adding the node in the schedule, and adding to the schedule each node in each subgraph that is not a predecessor to any node in the separator on the computation graph.