This inventor holds 1 USPTO granted patent and 1 published patent application. Top assignee: Character Technologies Inc.. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2026
Title: Noam Mordechai Shazeer: Inventor in Large Language Model Inference
Introduction
Noam Mordechai Shazeer is an inventor based in Palo Alto, California. His patent work addresses techniques for improving large language model inference.
Latest Patents
Shazeer is associated with 1 patent, titled “Optimizing Key Value Cache for Large Language Model Inference.” The invention describes processing an input sequence through transformer layers to generate tokens using hybrid attention, multi-query attention, and cross-layer key-value sharing. The generated tokens are then provided to the client device.
Career Highlights
Shazeer works at Character Technologies Inc. His patent focuses on key-value cache optimization and attention methods for language model inference.
Collaborations
His listed coworkers include Bowen Liang and Myle Ott.
Conclusion
Noam Mordechai Shazeer’s patent highlights his work on techniques designed to support efficient large language model inference.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile