Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation. In CVPR 2022.

QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning

BISMO: A Scalable Bit-Serial Matrix Multiplication Overlay for Reconfigurable Computing

Caffe implementation of accurate low-precision neural networks

LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks

From Pytorch model to C++ for Vitis HLS

This repository implements the paper "Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activations"

Simple PYNQ KV260 tutorial: Porting C-based design into FPGA via Xilinx HLS

PYNQ-Torch: a framework to develop PyTorch accelerators on the PYNQ platform

Simulator for BitFusion

AMD University Program HLS tutorial

Quantization of Convolutional Neural networks.

Papers and codes about Quantized Networks for easier survey and reference.

A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-…

cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it

A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks …

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Manually implemented quantization-aware training

PYNQ driver for fpgaconvnet

Official pytorch Implementation of Relational Knowledge Distillation, CVPR 2019

This repository provides an FPGA-based solution for executing object detection, focusing specifically on the popular YOLOv5 model architecture.

Fast low-bit matmul kernels in Triton

BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.

PyTorch implementation of Towards Efficient Training for Neural Network Quantization

BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization (ICLR 2021)