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: Myle Ott and His Work on Language Model Inference
Introduction
Myle Ott is an inventor based in New York, NY, United States. His patent work addresses methods for improving inference in large language models.
Latest Patents
Ott is associated with one patent, titled “Optimizing Key Value Cache for Large Language Model Inference.” The invention describes receiving an input sequence from a client device and processing it through transformer layers to generate tokens. Its approach combines hybrid attention, multi-query attention, and cross-layer key-value sharing, after which the generated tokens are provided to the client device.
Career Highlights
Ott works at Character Technologies Inc. His patent reflects work on optimizing key-value caching and attention mechanisms for large language model inference.
Collaborations
The provided information identifies Bowen Liang and Noam Mordechai Shazeer as Ott’s coworkers. It does not specify their roles in the patent.
Conclusion
Myle Ott’s patent focuses on combining attention techniques and cross-layer key-value sharing to support large language model inference.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile