-
公开(公告)号:US11436524B2
公开(公告)日:2022-09-06
申请号:US16146331
申请日:2018-09-28
Applicant: Amazon Technologies, Inc.
Inventor: Nikhil Kandoi , Ganesh Kumar Gella , Rama Krishna Sandeep Pokkunuri , Sudhakar Rao Puvvadi , Stefano Stefani , Kalpesh N. Sutaria , Enrico Sartorello , Tania Khattar
IPC: G06N20/00 , G06N5/04 , G06F9/50 , H04L67/1001
Abstract: Techniques for hosting machine learning models are described. In some instances, a method of receiving a request to perform an inference using a particular machine learning model; determining a group of hosts to route the request to, the group of hosts to host a plurality of machine learning models including the particular machine learning model; determining a path to the determined group of hosts; determining a particular host of the group of hosts to perform an analysis of the request based on the determined path, the particular host having the particular machine learning model in memory; routing the request to the particular host of the group of hosts; performing inference on the request using the particular host; and providing a result of the inference to a requester is performed.
-
公开(公告)号:US20250021884A1
公开(公告)日:2025-01-16
申请号:US18775912
申请日:2024-07-17
Applicant: Amazon Technologies, Inc.
Inventor: Leo Parker Dirac , Nicolle M. Correa , Aleksandr Mikhaylovich Ingerman , Sriram Krishnan , Jin Li , Sudhakar Rao Puvvadi , Saman Zarandioon
IPC: G06N20/00
Abstract: A machine learning service implements programmatic interfaces for a variety of operations on several entity types, such as data sources, statistics, feature processing recipes, models, and aliases. A first request to perform an operation on an instance of a particular entity type is received, and a first job corresponding to the requested operation is inserted in a job queue. Prior to the completion of the first job, a second request to perform another operation is received, where the second operation depends on a result of the operation represented by the first job. A second job, indicating a dependency on the first job, is stored in the job queue. The second job is initiated when the first job completes.
-
公开(公告)号:US11386351B2
公开(公告)日:2022-07-12
申请号:US16159441
申请日:2018-10-12
Applicant: Amazon Technologies, Inc.
Inventor: Leo Parker Dirac , Nicolle M. Correa , Aleksandr Mikhaylovich Ingerman , Sriram Krishnan , Jin Li , Sudhakar Rao Puvvadi , Saman Zarandioon
Abstract: A machine learning service implements programmatic interfaces for a variety of operations on several entity types, such as data sources, statistics, feature processing recipes, models, and aliases. A first request to perform an operation on an instance of a particular entity type is received, and a first job corresponding to the requested operation is inserted in a job queue. Prior to the completion of the first job, a second request to perform another operation is received, where the second operation depends on a result of the operation represented by the first job. A second job, indicating a dependency on the first job, is stored in the job queue. The second job is initiated when the first job completes.
-
公开(公告)号:US12073298B2
公开(公告)日:2024-08-27
申请号:US17811555
申请日:2022-07-08
Applicant: Amazon Technologies, Inc.
Inventor: Leo Parker Dirac , Nicolle M. Correa , Aleksandr Mikhaylovich Ingerman , Sriram Krishnan , Jin Li , Sudhakar Rao Puvvadi , Saman Zarandioon
IPC: G06N20/00
CPC classification number: G06N20/00
Abstract: A machine learning service implements programmatic interfaces for a variety of operations on several entity types, such as data sources, statistics, feature processing recipes, models, and aliases. A first request to perform an operation on an instance of a particular entity type is received, and a first job corresponding to the requested operation is inserted in a job queue. Prior to the completion of the first job, a second request to perform another operation is received, where the second operation depends on a result of the operation represented by the first job. A second job, indicating a dependency on the first job, is stored in the job queue. The second job is initiated when the first job completes.
-
公开(公告)号:US10102480B2
公开(公告)日:2018-10-16
申请号:US14319902
申请日:2014-06-30
Applicant: Amazon technologies, Inc.
Inventor: Leo Parker Dirac , Nicolle M. Correa , Aleksandr Mikhaylovich Ingerman , Sriram Krishnan , Jin Li , Sudhakar Rao Puvvadi , Saman Zarandioon
IPC: G06N99/00
Abstract: A machine learning service implements programmatic interfaces for a variety of operations on several entity types, such as data sources, statistics, feature processing recipes, models, and aliases. A first request to perform an operation on an instance of a particular entity type is received, and a first job corresponding to the requested operation is inserted in a job queue. Prior to the completion of the first job, a second request to perform another operation is received, where the second operation depends on a result of the operation represented by the first job. A second job, indicating a dependency on the first job, is stored in the job queue. The second job is initiated when the first job completes.
-
公开(公告)号:US20220391763A1
公开(公告)日:2022-12-08
申请号:US17811555
申请日:2022-07-08
Applicant: Amazon Technologies, Inc.
Inventor: Leo Parker Dirac , Nicolle M. Correa , Aleksandr Mikhaylovich Ingerman , Sriram Krishnan , Jin Li , Sudhakar Rao Puvvadi , Saman Zarandioon
IPC: G06N20/00
Abstract: A machine learning service implements programmatic interfaces for a variety of operations on several entity types, such as data sources, statistics, feature processing recipes, models, and aliases. A first request to perform an operation on an instance of a particular entity type is received, and a first job corresponding to the requested operation is inserted in a job queue. Prior to the completion of the first job, a second request to perform another operation is received, where the second operation depends on a result of the operation represented by the first job. A second job, indicating a dependency on the first job, is stored in the job queue. The second job is initiated when the first job completes.
-
公开(公告)号:US20190050756A1
公开(公告)日:2019-02-14
申请号:US16159441
申请日:2018-10-12
Applicant: Amazon Technologies, Inc.
Inventor: Leo Parker Dirac , Nicolle M. Correa , Aleksandr Mikhaylovich Ingerman , Sriram Krishnan , Jin Li , Sudhakar Rao Puvvadi , Saman Zarandioon
IPC: G06N99/00
Abstract: A machine learning service implements programmatic interfaces for a variety of operations on several entity types, such as data sources, statistics, feature processing recipes, models, and aliases. A first request to perform an operation on an instance of a particular entity type is received, and a first job corresponding to the requested operation is inserted in a job queue. Prior to the completion of the first job, a second request to perform another operation is received, where the second operation depends on a result of the operation represented by the first job. A second job, indicating a dependency on the first job, is stored in the job queue. The second job is initiated when the first job completes.
-
-
-
-
-
-