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:
Mar. 10, 2026

Filed:

Aug. 20, 2025
Applicant:

Snowflake Inc., Bozeman, MT (US);

Inventors:

Jaeseong Lee, Seoul, KR;

Gabriele Oliaro, Pittsburgh, PA (US);

Aurick Qiao, Pittsburgh, PA (US);

Samyam Rajbhandari, Sammamish, WA (US);

Ye Wang, San Jose, CA (US);

Assignee:

Snowflake Inc., Bozeman, MT (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 40/284 (2020.01); G06F 16/901 (2019.01);
U.S. Cl.
CPC ...
G06F 40/284 (2020.01); G06F 16/9027 (2019.01);
Abstract

Various example embodiments described herein provide for systems, methods, devices, instructions, and the like for suffix-based speculative token decoding for an artificial intelligence model, such as a language model (e.g., large language model). In particular, some example embodiments provide an AI model system with hybrid speculative token decoding, which combines suffix-based speculative token decoding with a draft AI model approach to speculative token decoding. With this hybrid decoding approach, various example embodiments can accelerate inference throughput while adapting to different types of workloads, particularly agentic applications that exhibit repetitive token generation patterns.


Find Patent Forward Citations

Loading…