post-training-quantization

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

A curated collection of papers, benchmarks, surveys, and tools for model quantization, covering low-bit networks, LLMs, multimodal and generative models, vector and lattice quantization, and efficient deployment.

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、reg…

TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

[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.

QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning

[NeurIPS 2024 Oral🔥] DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs.

This repository contains notebooks that show the usage of TensorFlow Lite for quantizing deep neural networks.

Gumbel-Softmax post-training quantization for LLMs (1–3 bit scalar, INT/GGUF-compatible).

Notes on quantization in neural networks

[CVPR 2024 Highlight & TPAMI 2025] This is the official PyTorch implementation of "TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models".

STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization

[MIR🎉] Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs

[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

[ICML 2026] NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models

Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization (EMNLP 2026)