paper-with-me

홈 › Papers

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

2022-11-18 · Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, Song Han

Large language models (LLMs) show excellent performance but are compute- and memory-intensive. Quantization can reduce memory and accelerate inference. However, existing methods cannot maintain accuracy and hardware efficiency at the same time. We propose SmoothQuant, a training-free, accuracy-preserving, and general-purpose post-training quantization (PTQ) solution to enable 8-bit weight, 8-bit activation (W8A8) quantization for LLMs. Based on the fact that weights are easy to quantize while activations are not, SmoothQuant smooths the activation outliers by offline migrating the quantization difficulty from activations to weights with a mathematically equivalent transformation. SmoothQuant enables an INT8 quantization of both weights and activations for all the matrix multiplications in LLMs, including OPT, BLOOM, GLM, MT-NLG, Llama-1/2, Falcon, Mistral, and Mixtral models. We demonstrate up to 1.56x speedup and 2x memory reduction for LLMs with negligible loss in accuracy. SmoothQuant enables serving 530B LLM within a single node. Our work offers a turn-key solution that reduces hardware costs and democratizes LLMs. Code is available at https://github.com/mit-han-lab/smoothquant.

📄 PDF Abstract BibTeX arXiv:2211.10438

Code (5)

mit-han-lab/smoothquant 공식 구현 pytorch
BlinkDL/RWKV-LM pytorch
adlik/smoothquantplus pytorch
cornell-zhang/llm-datatypes tf
nvidia/tensorrt-llm pytorch

Tasks

Quantization

Methods 이 논문이 사용한 방법론

OPT OPT is a suite of decoder-only pre-trained transformers ranging from 125M to 175B parameters. The model uses an AdamW optimizer and weight decay of 0.1. It follows a linear…
BLOOM BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages…
GLM GLM is a bilingual (English and Chinese) pre-trained transformer-based language model that follow the traditional architecture of decoder-only autoregressive language…
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

SmoothQuant+: Accurate and Efficient 4-bit Post-Training WeightQuantization for LLM

2023-12-06 · Jiayi Pan, Chengcan Wang, Kaifu Zheng, Yangguang Li 외

Large language models (LLMs) have shown remarkable capabilities in various tasks. However their huge model size and the consequent demand for computational and memory resources also pose challenges to model deployment. C…

GPUQuantization

An Empirical Study of OpenPangu Quantization on Ascend NPUs

2026-06-19 · Tong Shi, Jiacheng Wang, Hui Xie, Ying Li 외 arxiv

OpenPangu models are attractive targets for private and domestic large-language-model deployment, yet their robustness under aggressive post-training quantization on Ascend NPUs has not been systematically characterized.…

Post Training Quantization of Large Language Models with Microscaling Formats

2024-05-12 · Sayeh Sharify, Utkarsh Saxena, Zifei Xu, Wanzin Yazar 외

Large Language Models (LLMs) have distinguished themselves with outstanding performance in complex language modeling tasks, yet they come with significant computational and storage challenges. This paper explores the pot…

Language ModelingLanguage ModellingQuantization

KroQuant: Kronecker-Structured Block Transforms for Efficient Post-Training Quantization of Diffusion Transformers

2026-07-23 · Yann Bouquet, Alireza Khodamoradi, Kristof Denolf, Mathieu Salzmann arxiv

Post-training quantization (PTQ) of diffusion transformers (DiTs) to W4A4 severely degrades output quality, because activations entering each linear layer contain outliers that 4-bit formats cannot represent. The standar…

ADMM-Q: An Improved Hessian-based Weight Quantizer for Post-Training Quantization of Large Language Models

2026-05-11 · Ryan Lucas, Mehdi Makni, Xiang Meng, Adam Deng 외 arxiv

Quantization is an effective strategy to reduce the storage and computation footprint of large language models (LLMs). Post-training quantization (PTQ) is a leading approach for compressing LLMs. Popular weight quantizat…