The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Dec. 01, 2020

Filed:

Mar. 19, 2019
Applicant:

Amazon Technologies, Inc., Seattle, WA (US);

Inventors:

Sudipta Sengupta, Sammamish, WA (US);

Haifeng He, Bellevue, WA (US);

Pejus Manoj Das, Shoreline, WA (US);

Poorna Chand Srinivas Perumalla, Seattle, WA (US);

Wei Xiao, Bellevue, WA (US);

Shirley Xue Yi Leung, Vancouver, CA;

Vladimir Mitrovic, Seattle, WA (US);

Yongcong Luo, Seattle, WA (US);

Jiacheng Guo, Seattle, WA (US);

Stefano Stefani, Issaquah, WA (US);

Matthew Shawn Wilson, Bainbridge Island, WA (US);

Assignee:

Amazon Technologies, Inc., Seattle, WA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 9/46 (2006.01); G06F 9/48 (2006.01); G06N 20/00 (2019.01); G06N 5/04 (2006.01); G06F 9/50 (2006.01); G06N 3/08 (2006.01); G06F 9/455 (2018.01);
U.S. Cl.
CPC ...
G06F 9/4856 (2013.01); G06F 9/5027 (2013.01); G06N 3/08 (2013.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01); G06F 2009/45575 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01);
Abstract

Implementations detailed herein include description of a computer-implemented method to migrate a machine learning model from one accelerator portion (such as a portion of a graphical processor unit (GPU)) to a different accelerator portion. In some instances, a state of the first accelerator portion is persisted, the second accelerator portion is configured, the first accelerator portion is then detached from a client application instance, and at least a portion of an inference request is performed using the loaded at least a portion of the machine learning model on the second accelerator portion that had been configured.


Find Patent Forward Citations

Loading…