Repository navigation
post-training-quantization
- Website
- Wikipedia
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
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-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.
[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
[EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit".
[ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.
[IJCAI 2022] FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer
A model compression and acceleration toolbox based on pytorch.
This repository contains notebooks that show the usage of TensorFlow Lite for quantizing deep neural networks.
[NeurIPS 2024 Oral🔥] DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs.
[CVPR 2024 Highlight & TPAMI 2025] This is the official PyTorch implementation of "TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models".
Notes on quantization in neural networks
[ICLR 2024] This is the official PyTorch implementation of "QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models"
Post-training static quantization using ResNet18 architecture
Pytorch implementation of our paper accepted by ECCV 2022-- Fine-grained Data Distribution Alignment for Post-Training Quantization
Improved the performance of 8-bit PTQ4DM expecially on FID.
[ASP-DAC 2025] "NeuronQuant: Accurate and Efficient Post-Training Quantization for Spiking Neural Networks" Official Implementation
Post post-training-quantization (PTQ) method for improving LLMs. Unofficial implementation of https://arxiv.org/abs/2309.02784
[CAAI AIR'24] Minimize Quantization Output Error with Bias Compensation