English
Related papers

Related papers: Technical Report: Activation Residual Hessian Quan…

200 papers

Improving the efficiency of inference in Large Language Models (LLMs) is a critical area of research. Post-training Quantization (PTQ) is a popular technique, but it often faces challenges at low-bit levels, particularly in downstream…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Wenjin Ke , Zhe Li , Dong Li , Lu Tian , Emad Barsoum

We study weight-only post-training quantization (PTQ), which quantizes the weights of a large language model (LLM) without retraining, using little or no calibration data. Weight-only PTQ is crucial for reducing the memory footprint and…

Machine Learning · Computer Science 2025-10-23 Deokjae Lee , Hyun Oh Song

Serving Large Language Models (LLMs) is costly. However, post-training weight quantization can address this problem by both compressing their sizes for limited memory and saving bandwidth for acceleration. As not all weight dimensions are…

Machine Learning · Computer Science 2025-03-05 Yuezhou Hu , Weiyu Huang , Zichen Liang , Chang Chen , Jintao Zhang , Jun Zhu , Jianfei Chen

The advancements of hardware technology in recent years has brought many possibilities for low-precision applications. However, the use of low precision can introduce significant computational errors, posing a considerable challenge to…

Mathematical Software · Computer Science 2024-09-30 Hongyaoxing Gu

Large Language Models (LLMs) are proficient in natural language processing tasks, but their deployment is often restricted by extensive parameter sizes and computational demands. This paper focuses on post-training quantization (PTQ) in…

Computation and Language · Computer Science 2024-07-19 Janghwan Lee , Minsoo Kim , Seungcheol Baek , Seok Joong Hwang , Wonyong Sung , Jungwook Choi

Low-bit quantization emerges as one of the most promising compression approaches for deploying deep neural networks on edge devices. Mixed-precision quantization leverages a mixture of bit-widths to unleash the accuracy and efficiency…

Machine Learning · Computer Science 2024-05-24 Wei Huang , Haotong Qin , Yangdong Liu , Jingzhuo Liang , Yulun Zhang , Ying Li , Xianglong Liu

Zero-shot quantization (ZSQ) enables neural network compression without original training data, making it a promising solution for restricted data access scenarios. To compensate for the lack of data, recent ZSQ methods typically rely on…

Computer Vision and Pattern Recognition · Computer Science 2025-10-16 Inpyo Hong , Youngwan Jo , Hyojeong Lee , Sunghyun Ahn , Kijung Lee , Sanghyun Park

The severe on-chip memory limitations are currently preventing the deployment of the most accurate Deep Neural Network (DNN) models on tiny MicroController Units (MCUs), even if leveraging an effective 8-bit quantization scheme. To tackle…

Machine Learning · Computer Science 2020-08-13 Manuele Rusci , Marco Fariselli , Alessandro Capotondi , Luca Benini

Efficiently serving neural network models with low latency is becoming more challenging due to increasing model complexity and parameter count. Model quantization offers a solution which simultaneously reduces memory footprint and compute…

Post-training quantization (PTQ) has become an important technique for reducing the inference cost of Large Language Models (LLMs). While recent mixed-precision methods improve ultra-low bit quantization by preserving critical subspaces in…

Machine Learning · Computer Science 2026-04-30 Zhe Ding , Su Pan , Duowei Pan

Low-precision computation is often used to lower the time and energy cost of machine learning, and recently hardware accelerators have been developed to support it. Still, it has been used primarily for inference - not training. Previous…

Large Language Models (LLMs) face deployment challenges due to high computational costs, and while Post-Training Quantization (PTQ) offers a solution, existing rotation-based methods struggle at very low bit-widths like 2-bit. We introduce…

Machine Learning · Computer Science 2025-08-15 Euntae Choi , Sumin Song , Woosang Lim , Sungjoo Yoo

Post-training quantization (PTQ) methods for large language models rely on heuristics that implicitly estimate which weight channels most strongly influence model behavior. Two dominant paradigms have emerged: activation-aware methods such…

Machine Learning · Computer Science 2026-01-21 Bruce Changlong Xu

Many LLM applications require only narrow capabilities, yet standard post-training quantization (PTQ) methods allocate precision without considering the target task. This can waste bits on layers that are less relevant to the task signal…

Computation and Language · Computer Science 2026-05-19 Amit LeVi , Raz Lapid , Rom Himelstein , Chaim Baskin , Ravid Shwartz Ziv , Avi Mendelson

AutoRegressive Visual Generation (ARVG) models retain an architecture compatible with language models, while achieving performance comparable to diffusion-based models. Quantization is commonly employed in neural networks to reduce model…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Xuewen Liu , Zhikai Li , Jing Zhang , Mengjuan Chen , Qingyi Gu

We introduce a method to train Quantized Neural Networks (QNNs) --- neural networks with extremely low precision (e.g., 1-bit) weights and activations, at run-time. At train-time the quantized weights and activations are used for computing…

Neural and Evolutionary Computing · Computer Science 2016-09-23 Itay Hubara , Matthieu Courbariaux , Daniel Soudry , Ran El-Yaniv , Yoshua Bengio

Large language models (LLMs) are omnipresent, however their practical deployment is challenging due to their ever increasing computational and memory demands. Quantization is one of the most effective ways to make them more compute and…

Machine Learning · Computer Science 2024-09-04 Yelysei Bondarenko , Riccardo Del Chiaro , Markus Nagel

Recently, lightweight methods for single image super-resolution (SISR) have gained significant popularity and achieved impressive performance due to limited hardware resources. These methods demonstrate that adopting residual feature…

Image and Video Processing · Electrical Eng. & Systems 2024-10-15 Weifeng Cao , Xiaoyan Lei , Jun Shi , Wanyong Liang , Jie Liu , Zongfei Bai

Post-training quantization (PTQ) is a widely used approach for reducing the memory and compute costs of large language models (LLMs). Recent studies have shown that applying invertible transformations to activations can significantly…

Machine Learning · Computer Science 2026-04-27 Ofir Gordon , Lior Dikstein , Arnon Netzer , Idan Achituve , Hai Victor Habi

In this paper, we introduce a new post-training compression paradigm for Large Language Models (LLMs) to facilitate their wider adoption. We delve into LLM weight low-rank decomposition, and find that the challenges of this task stem from…

Computation and Language · Computer Science 2025-08-29 Zhihang Yuan , Yuzhang Shang , Yue Song , Dawei Yang , Qiang Wu , Yan Yan , Guangyu Sun