paper-with-me

Papers

RPTQ: Reorder-based Post-training Quantization for Large Language Models

2023-04-03 · Zhihang Yuan, Lin Niu, Jiawei Liu, Wenyu Liu, Xinggang Wang, Yuzhang Shang, Guangyu Sun, Qiang Wu, Jiaxiang Wu, Bingzhe Wu

Large-scale language models (LLMs) have demonstrated impressive performance, but their deployment presents challenges due to their significant memory usage. This issue can be alleviated through quantization. In this paper, we identify that the challenge in quantizing activations in LLMs arises from varying ranges across channels, rather than solely the presence of outliers. To address this challenge, we introduce a quantization method called RPTQ, which utilizes a reorder-based approach. By rearranging the channels and quantizing them in clusters, RPTQ effectively mitigates the impact of range differences between channels. To minimize the overhead of the reorder operation, we fuse it into the layer norm operation and weights in linear layers. In our experiments, RPTQ achieved a significant breakthrough by utilizing 3-bit activation in LLMs for the first time, resulting in a substantial reduction in memory usage. For instance, quantizing OPT-175b can lead to a memory consumption reduction of up to 80%.

📄 PDF Abstract BibTeX arXiv:2304.01089

Code (1)

hahnyuan/rptq4llm 공식 구현 pytorch

Tasks

Quantization

Similar Papers 제목 키워드 기반

PTQ-SL: Exploring the Sub-layerwise Post-training Quantization

2021-10-15 · Zhihang Yuan, Yiqi Chen, Chenhao Xue, Chenguang Zhang 외

Network quantization is a powerful technique to compress convolutional neural networks. The quantization granularity determines how to share the scaling factors in weights, which affects the performance of network quanti…

Quantization

Weight Group-wise Post-Training Quantization for Medical Foundation Model

2026-04-09 · Yineng Chen, Peng Huang, Aozhong Zhang, Hui Guo 외 arxiv

Foundation models have achieved remarkable results in medical image analysis. However, its large network architecture and high computational complexity significantly impact inference speed, limiting its application on te…

PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models

2026-05-10 · Yongsen Cheng, Kai Liu, Kaiwen Tao, Junxian Li 외 arxiv

Large-scale visual generative models have achieved remarkable performance. However, their high computational and memory costs make deployment challenging in resource-constrained scenarios, such as interactive application…

PTQ4RIS: Post-Training Quantization for Referring Image Segmentation

2024-09-25 · Xiaoyan Jiang, Hang Yang, Kaiying Zhu, Xihe Qiu 외

Referring Image Segmentation (RIS), aims to segment the object referred by a given sentence in an image by understanding both visual and linguistic information. However, existing RIS methods tend to explore top-performan…

Image SegmentationQuantizationSemantic SegmentationSentence

PT$^2$-LLM: Post-Training Ternarization for Large Language Models

2025-09-27 · Xianglong Yan, Chengzhu Bao, Zhiteng Li, Tianao Zhang 외 arxiv

Large Language Models (LLMs) have shown impressive capabilities across diverse tasks, but their large memory and compute demands hinder deployment. Ternarization has gained attention as a promising compression technique,…

Computational Efficiency