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:
Jun. 23, 2026

Filed:

Oct. 28, 2021
Applicant:

Kwai Inc., Palo Alto, CA (US);

Inventors:

Zhendong Wang, Plano, TX (US);

Yongxiong Ren, San Jose, CA (US);

Yang Liu, San Jose, CA (US);

Lingzhi Liu, San Jose, CA (US);

Attorneys:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06N 3/063 (2023.01); G06F 17/16 (2006.01); G06N 3/0495 (2023.01);
U.S. Cl.
CPC ...
G06N 3/063 (2013.01); G06F 17/16 (2013.01); G06N 3/0495 (2023.01);
Abstract

A method and an apparatus for accelerating a transformer with a sparse attention pattern are provided. The method includes that a heterogeneous device including one or more GPUs loads a first matrix, a second matrix, and a transformed sparsity mask into a first sampled dense-dense matrix multiplication (SDDMM) kernel in a sparse attention module in the transformer and generates a first output based on the first matrix, the second matrix, and the transformed sparsity mask by the first SDDMM kernel, generates a second output by a softmax kernel in the sparse attention module based on the first output, loads the second output, a third matrix, and the transformed sparsity mask into a matrix multiplication kernel in the sparse attention module, and generates an output of the sparse attention module.


Find Patent Forward Citations

Loading…