Open-source alternatives to Smoothquant

bitsandbytes is a quantization library for large language models that reduces memory footprints using k-bit quantization. It provides a framework for 4-bit low-rank adaptation, tools for 8-bit model compression, and memory-efficient optimizer extensions for PyTorch. The project enables the training of large models on limited hardware through 4-bit quantization and low-rank adaptation weights. It also facilitates faster inference by compressing models to 8-bit precision using vector-wise quantization. The library covers a range of memory optimization capabilities, including optimizer memory r

The official implementation of the EMNLP 2023 paper LLM-FP4

ICML 2024 SqueezeLLM: Dense-and-Sparse Quantization

This project is a quantized fine-tuning framework for large language models. It implements a low-rank adaptation library and a four-bit quantizer to reduce the GPU memory requirements needed to train large models. The framework utilizes four-bit quantization and low-rank adapters to enable model training on consumer-grade hardware. It further reduces the memory footprint through double quantization and a paged optimizer that offloads states to system RAM. The system supports distributed training across multiple GPUs to handle larger parameter scales and includes utilities for custom dataset

Microsoft Automatic Mixed Precision Library

An acceleration library that supports arbitrary bit-width combinatorial quantization operations

ICML 2023 SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

This method identifies a binary weight or binary weight and activation subnetwork within a randomly initialized network that achieves performance comparable to, and sometimes better than, a weight-optimized network. The resulting binarized and pruned networks that achieve comparable performance…