Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Efficient key-value cache management for large language models

Efficient key-value cache management for large language models

US Patent 12346252 · Granted Jul 1, 2025

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Dynamic communication architecture for decentralized heterogenous accelerators2025
Dynamic communication architecture for decentralized heterogenous accelerators2025
Automated program conversion for heterogeneous and FaaS computing with minimal h2025
Automated program conversion for heterogeneous and FaaS computing with minimal h2025
Automated program conversion for heterogeneous and FaaS computing with minimal h2025
Self-adaptable accelerators having alternating production/optimizing modes2025
Self-adaptable accelerators having alternating production/optimizing modes2025
Graph cache2025
Smart network interface card control plane for distributed machine learning work2025
Dynamically modular and customizable computing environments2025
Acceleration of model/weight programming in memristor crossbar arrays2025
Acceleration of model/weight programming in memristor crossbar arrays2025