Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Method and apparatus to cache key-value data in low-precision numerics for efficient generative transformer execution

Method and apparatus to cache key-value data in low-precision numerics for efficient generative transformer execution

US Patent 12182028 · Granted Dec 31, 2024

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Deepfake detection models utilizing subject-specific libraries2025
AI accelerator apparatus using full mesh connectivity chiplet devices for transf2025
Region pattern-matching hardware prefetcher2025
Server system with AI accelerator apparatuses using in-memory compute chiplet de2025
Server system with AI accelerator apparatuses using in-memory compute chiplet de2025
Hardware and software co-designed system for efficient distributed control of ex2025
Selective speculative prefetch requests for a last-level cache2025
Authenticator-integrated generative adversarial network (GAN) for secure deepfak2025
Video smoothing mechanism2025
Apparatus, system, and method for throttling prefetchers to prevent training on 2024
Generator exploitation for deepfake detection2024
Relaxed invalidation for cache coherence2024