block floating point - Robuta Search

https://deepai.org/publication/adaptive-block-floating-point-for-analog-deep-learning-hardware Adaptive Block Floating-Point for Analog Deep Learning Hardware | DeepAI May 12, 2022 - 05/12/22 - Analog mixed-signal (AMS) devices promise faster, more energy-efficient deep neural network (DNN) inference than their digital cou... block floating point analog deep learning adaptive hardware deepai https://openreview.net/forum?id=DbyHDYslM7&referrer=%5Bthe%20profile%20of%20Chen%20Bai%5D(%2Fprofile%3Fid%3D~Chen_Bai1) BiE: Bi-Exponent Block Floating-Point for Large Language Models Quantization | OpenReview Nowadays, Large Language Models (LLMs) mostly possess billions of parameters, bringing significant challenges to hardware platforms. Although quantization is... block floating point large language models