多模型深度学习推理流水线的自动异构低比特量化

Nov, 2023

Automated Heterogeneous Low-Bit Quantization of Multi-Model Deep Learning Inference Pipeline

Jayeeta Mondal, Swarnava Dey, Arijit Mukherjee

TL;DR该论文介绍了一种自动异构量化方法，用于具有多个深度神经网络的深度学习推理流水线。

Abstract

Multiple deep neural networks (DNNs) integrated into single deep learning (DL) inference pipelines e.g. multi-task learning (MTL) or