DaYou Du

large language model (2) weight quantization (2) model compression (2) efficient inference (1) fault tolerance (1) inference acceleration (1) software-defined networking (1) quantization-aware training (1) ultra-low precision (1) machine learning training (1) floating point (1) floating point quantization (1) supercomputer architecture (1) optical circuit switching (1) system availability (1) model quantization (1) knowledge distillation (1)