[간단리뷰 2주차] Model Quantization Papers
선정논문 Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference, 2017 Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation, 2020 Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation Part 2.1 – Related Works ICLR 2018, Baidu&NVIDIA, Mixed precision training: 기존 FP32 Datatype이 아닌 FP16에서 Training할 수 있도록 하는 Technique 2011, …