Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Reducing training times of deep neural networks through efficient hybrid parallelism

Reducing training times of deep neural networks through efficient hybrid parallelism

US Patent 12293298 · Granted May 6, 2025

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Accelerating linear algebra kernels for any processor architecture2025
Data-aware model pruning for neural networks2025
Hierarchical and shared exponent floating point data types2024