English
Related papers

Related papers: FrameQuant: Flexible Low-Bit Quantization for Tran…

200 papers

Reasoning models excel at complex tasks such as coding and mathematics, yet their inference is often slow and token-inefficient. To improve the inference efficiency, post-training quantization (PTQ) usually comes with the cost of large…

Machine Learning · Computer Science 2026-01-22 Keyu Lv , Manyi Zhang , Xiaobo Xia , Jingchen Ni , Shannan Yan , Xianzhi Yu , Lu Hou , Chun Yuan , Haoli Bai

With the increasing complexity of generative AI models, post-training quantization (PTQ) has emerged as a promising solution for deploying hyper-scale models on edge devices such as mobile and TVs. Existing PTQ schemes, however, consume…

Machine Learning · Computer Science 2024-11-06 Junhan Kim , Chungman Lee , Eulrang Cho , Kyungphil Park , Ho-young Kim , Joonyoung Kim , Yongkweon Jeon

Vision Transformers (ViTs) are essential in computer vision but are computationally intensive, too. Model quantization, particularly to low bit-widths like 4-bit, aims to alleviate this difficulty, yet existing Post-Training Quantization…

Computer Vision and Pattern Recognition · Computer Science 2025-06-16 Guang Liang , Xinyao Liu , Jianxin Wu

Quantization is a widely used compression technique for reducing the memory and computation costs of large pre-trained models. A key challenge in per-channel post-training quantization (PTQ) is selecting appropriate scaling factors to…

Machine Learning · Computer Science 2026-02-18 Shihao Zhang , Rayan Saab

Quantizing model weights is critical for reducing the communication and inference costs of large models. However, quantizing models -- especially to low precisions like int4 or int2 -- requires a trade-off in model quality; int2, in…

Machine Learning · Computer Science 2025-03-04 Pranav Nair , Puranjay Datta , Jeff Dean , Prateek Jain , Aditya Kusupati

As soon as abstract mathematical computations were adapted to computation on digital computers, the problem of efficient representation, manipulation, and communication of the numerical values in those computations arose. Strongly related…

Computer Vision and Pattern Recognition · Computer Science 2021-06-23 Amir Gholami , Sehoon Kim , Zhen Dong , Zhewei Yao , Michael W. Mahoney , Kurt Keutzer

Efficient inference is critical for deploying deep learning models on edge AI devices. Low-bit quantization (e.g., 3- and 4-bit) with fixed-point arithmetic improves efficiency, while low-power memory technologies like analog nonvolatile…

Machine Learning · Computer Science 2025-07-15 Anmol Biswas , Raghav Singhal , Sivakumar Elangovan , Shreyas Sabnis , Udayan Ganguly

Post-training model quantization is a widely adopted technique for reducing the memory and computational costs of large language models (LLMs). However, most existing methods rely on uniform or heuristic bitwidth assignments, failing to…

Machine Learning · Computer Science 2025-06-09 Chao Zhang , Li Wang , Samson Lasaulce , Merouane Debbah

Diffusion models have achieved significant visual generation quality. However, their significant computational and memory costs pose challenge for their application on resource-constrained mobile devices or even desktop GPUs. Recent…

Computer Vision and Pattern Recognition · Computer Science 2024-05-31 Tianchen Zhao , Xuefei Ning , Tongcheng Fang , Enshu Liu , Guyue Huang , Zinan Lin , Shengen Yan , Guohao Dai , Yu Wang

State-of-the-art neural machine translation methods employ massive amounts of parameters. Drastically reducing computational costs of such methods without affecting performance has been up to this point unsuccessful. To this end, we propose…

Computation and Language · Computer Science 2020-03-24 Gabriele Prato , Ella Charlaix , Mehdi Rezagholizadeh

This paper presents a novel network compression framework Kernel Quantization (KQ), targeting to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version without significant…

Machine Learning · Computer Science 2020-03-12 Zhongzhi Yu , Yemin Shi , Tiejun Huang , Yizhou Yu

As large language models (LLMs) become more prevalent, there is a growing need for new and improved quantization methods that can meet the computationalast layer demands of these modern architectures while maintaining the accuracy. In this…

Computation and Language · Computer Science 2023-10-18 Wenhua Cheng , Yiyang Cai , Kaokao Lv , Haihao Shen

Neural networks commonly execute on hardware accelerators such as NPUs and GPUs for their size and computation overhead. These accelerators are costly and it is hard to scale their resources to handle real-time workload fluctuations. We…

Machine Learning · Computer Science 2025-10-06 Jaemin Kim , Hongjun Um , Sungkyun Kim , Yongjun Park , Jiwon Seo

Diffusion models have shown superior performance in real-world video super-resolution (VSR). However, the slow processing speeds and heavy resource consumption of diffusion models hinder their practical application and deployment.…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Bowen Chai , Zheng Chen , Libo Zhu , Wenbo Li , Yong Guo , Yulun Zhang

The burgeoning computational demands for training large language models (LLMs) necessitate efficient methods, including quantized training, which leverages low-bit arithmetic operations to reduce costs. While FP8 precision has shown…

Machine Learning · Computer Science 2025-02-18 Jiecheng Zhou , Ding Tang , Rong Fu , Boni Hu , Haoran Xu , Yi Wang , Zhilin Pei , Zhongling Su , Liang Liu , Xingcheng Zhang , Weiming Zhang

The inherent heavy computation of deep neural networks prevents their widespread applications. A widely used method for accelerating model inference is quantization, by replacing the input operands of a network using fixed-point values.…

Computer Vision and Pattern Recognition · Computer Science 2020-05-28 Hongwei Xie , Shuo Zhang , Huanghao Ding , Yafei Song , Baitao Shao , Conggang Hu , Ling Cai , Mingyang Li

In this paper, we address the problem of reducing the memory footprint of convolutional network architectures. We introduce a vector quantization method that aims at preserving the quality of the reconstruction of the network outputs rather…

Computer Vision and Pattern Recognition · Computer Science 2020-11-10 Pierre Stock , Armand Joulin , Rémi Gribonval , Benjamin Graham , Hervé Jégou

The model quantization technique of deep neural networks has garnered significant attention and has proven to be highly useful in compressing model size, reducing computation costs, and accelerating inference. Many researchers employ fake…

Machine Learning · Computer Science 2024-07-17 Dezan Zhao

Pruning is an effective way to reduce the huge inference cost of Transformer models. However, prior work on pruning Transformers requires retraining the models. This can add high training cost and high complexity to model deployment, making…

Computation and Language · Computer Science 2022-10-18 Woosuk Kwon , Sehoon Kim , Michael W. Mahoney , Joseph Hassoun , Kurt Keutzer , Amir Gholami

Increasing the number of parameters in large language models (LLMs) usually improves performance in downstream tasks but raises compute and memory costs, making deployment difficult in resource-limited settings. Quantization techniques,…

Computation and Language · Computer Science 2024-06-07 Renren Jin , Jiangcun Du , Wuwei Huang , Wei Liu , Jian Luan , Bin Wang , Deyi Xiong