MUMBAI, India, June 19 -- Intellectual Property India has published a patent application (202647068048 A) filed by Qualcomm Incorporated on May 30, 2026, for Codebook Compression For Vector Quantized Neural Networks.
Inventors include Van Baalen, Marinus Willem; Mahurin, Eric Wayne; Whatmough, Paul Nicholas; Kuzmin, Andrey; Nagel, Markus; and Blankevoort, Tijmen Pieter Frederik.
The application for the patent was published on June 05, 2026, under issue no. 23/2026.
Abstract: Systems and techniques are described herein for quantizing a codebook used in the context of quantizing post-training parameters (e.g., vectors of weights) of a pre- trained model. For example, a device can perform rank reduction on a tensor of a codebook associated with parameters of a layer of a pre-trained machine learning model to generate a first tensor factor having a first shape and a second tensor factor having a second shape. The device can perform an optimization technique on the first tensor factor and the second tensor factor to minimize an output reconstruction error of the layer. The device can quantize the first tensor factor to generate a reduced size codebook.
Disclaimer: Curated by HT Syndication.
