quantization

Boost Quantization Inference Performance

This artical summaries techniques utilized in convolution optimization for TVM. With AutoTVM empowered auto-tuning, carefully designed schedule algothrims and fine-grain computation manipulation may achieve impressive optimization results.
QNNPACK 实现揭秘

QNNPACK 是 Facebook 开发的专门用于量化神经网络计算的加速库，其卓越的性能表现一经开源就击败了几乎全部已公开的加速算法。
通用矩阵乘（GEMM）优化算法

本文简要介绍通用矩阵乘（General Matrix Multiplication）优化的基本概念和方法、神经网络量化中的优化方法。旨在帮助大家在概念中建立一些直觉，无甚高论。
神经网络量化简介

介绍神经网络量化相关理论、算术、数学、研究和实现。
Neural Network Quantization Resources

List resources on neural network quantization here. Quantization are moving from research to industry (I mean real applications) nowdays (as in the begining of 2019). Hoping that this list may help.
Neural Network Quantization Introduction

Brings Neural Network Quantization related theory, arithmetic, mathmetic, research and implementation to you, in an introduction approach.