US 2026/0010784 A1 · COMPUTE-EFFICIENT VECTOR QUANTIZATION IN MACHINE LEARNING MODELS

Compute-efficient vector quantization in machine learning models

AssigneeQUALCOMM Incorporated

InventorsWeiliang ZENG, Marinus Willem VAN BAALEN, Markus NAGEL, Paul Nicholas WHATMOUGH, An CHEN, Liang ZHANG, Chirag Sureshbhai PATEL, Nilesh Prasad PANDEY, Jun MA, Kevin Lishing HSIEH, Abhijit KHOBARE, Joseph Binamira SORIAGA, Muralidhar Reddy AKULA, Peter John COUPERUS, Cedric BASTOUL

Life of this patent

Estimating the term…

Abstract

Certain aspects of the present disclosure provide techniques and apparatus for machine learning. In an example method, a weight tensor for a layer of a machine learning model is determined, where the weight tensor comprises per-block values in a first precision encoding. The weight tensor is upscaled to a second precision encoding having a higher precision than the first precision encoding to generate an upscaled weight tensor, and an input tensor for the layer of the machine learning model is accessed. An output tensor for the layer of the machine learning model is generated based on multiplying the upscaled weight tensor with the input tensor.

Claims20

Dependent claims

A processing system for machine learning comprising:

one or more memories comprising processor-executable instructions;
and
one or more processors coupled to the one or more memories and configured to execute the processor-executable instructions and cause the processing system to:
determine a weight tensor for a layer of a machine learning model, wherein the weight tensor comprises per-block values in a first precision encoding;
upscale the weight tensor to a second precision encoding having a higher precision than the first precision encoding to generate an upscaled weight tensor;
access an input tensor for the layer of the machine learning model;
and
generate an output tensor for the layer of the machine learning model based on multiplying the upscaled weight tensor with the input tensor.

5 more elements

Dependencies are inferred from the claim text.