English
Related papers

Related papers: decoupleQ: Towards 2-bit Post-Training Uniform Qua…

200 papers

Transformer-based large language models (LLMs) have achieved remarkable success as model sizes continue to grow, yet their deployment remains challenging due to significant computational and memory demands. Quantization has emerged as a…

Machine Learning · Computer Science 2024-11-26 Yu Zhang , Mingzi Wang , Lancheng Zou , Wulong Liu , Hui-Ling Zhen , Mingxuan Yuan , Bei Yu

Large language models (LLMs) have revolutionized numerous applications, yet their deployment remains challenged by memory constraints on local devices. While scaling laws have enhanced LLM capabilities, the primary bottleneck has shifted…

Computation and Language · Computer Science 2025-02-18 Xinghao Wang , Pengyu Wang , Bo Wang , Dong Zhang , Yunhua Zhou , Xipeng Qiu

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…

Computation and Language · Computer Science 2024-04-03 Guangxuan Xiao , Ji Lin , Mickael Seznec , Hao Wu , Julien Demouth , Song Han

Post-training compression is currently divided into two contrasting regimes. On the one hand, fast, data-free, and model-agnostic methods (e.g., NF4 or HQQ) offer maximum accessibility but suffer from functional collapse at extreme…

Machine Learning · Computer Science 2026-02-02 Patrick Putzky , Martin Genzel , Mattes Mollenhauer , Sebastian Schulze , Thomas Wollmann , Stefan Dietzel

How can we quantize large language models while preserving accuracy? Quantization is essential for deploying large language models (LLMs) efficiently. Binary-coding quantization (BCQ) and uniform quantization (UQ) are promising quantization…

Computation and Language · Computer Science 2025-06-17 Seungcheol Park , Jeongin Bae , Beomseok Kwon , Minjun Kim , Byeongwook Kim , Se Jung Kwon , U Kang , Dongsoo Lee

We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We leverage weight normalization as a means of constraining parameters during…

Machine Learning · Computer Science 2023-02-01 Ian Colbert , Alessandro Pappalardo , Jakoba Petri-Koenig

Generative Pre-trained Transformer models, known as GPT or OPT, set themselves apart through breakthrough performance across complex language modelling tasks, but also by their extremely high computational and storage costs. Specifically,…

Machine Learning · Computer Science 2023-03-23 Elias Frantar , Saleh Ashkboos , Torsten Hoefler , Dan Alistarh

Weight quantisation is an essential technique for enabling efficient training and deployment of modern deep learning models. However, the recipe book of quantisation formats is large and formats are often chosen empirically. In this paper,…

Machine Learning · Computer Science 2026-02-16 Douglas Orr , Luka Ribar , Carlo Luschi

The growing computational demands of training large language models (LLMs) necessitate more efficient methods. Quantized training presents a promising solution by enabling low-bit arithmetic operations to reduce these costs. While FP8…

Machine Learning · Computer Science 2026-05-18 Ruizhe Wang , Yeyun Gong , Xiao Liu , Guoshuai Zhao , Ziyue Yang , Baining Guo , Zhengjun Zha , Peng Cheng

Recently, large language models (LLMs) have shown surprising performance in task-specific workloads as well as general tasks with the given prompts. However, to achieve unprecedented performance, recent LLMs use billions to trillions of…

Machine Learning · Computer Science 2024-06-21 Geonhwa Jeong , Po-An Tsai , Stephen W. Keckler , Tushar Krishna

Large Language Models (LLMs) face significant deployment challenges due to their substantial resource requirements. While low-bit quantized weights can reduce memory usage and improve inference efficiency, current hardware lacks native…

Machine Learning · Computer Science 2025-06-10 Pengxiang Zhao , Xiaoming Yuan

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

Diffusion models have demonstrated remarkable capabilities in image synthesis and related generative tasks. Nevertheless, their practicality for real-world applications is constrained by substantial computational costs and latency issues.…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Yefei He , Jing Liu , Weijia Wu , Hong Zhou , Bohan Zhuang

Learned image compression (LIC) has reached the traditional hand-crafted methods such as JPEG2000 and BPG in terms of the coding gain. However, the large model size of the network prohibits the usage of LIC on resource-limited embedded…

Image and Video Processing · Electrical Eng. & Systems 2020-07-10 Heming Sun , Zhengxue Cheng , Masaru Takeuchi , Jiro Katto

Model quantization reduces neural network parameter precision to achieve compression, but often compromises accuracy. Existing post-training quantization (PTQ) methods employ iterative parameter updates to preserve accuracy under high…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Zekang Zheng , Haokun Li , Yaofo Chen , Mingkui Tan , Qing Du

Quantization has gained attention as a promising solution for the cost-effective deployment of large and small language models. However, most prior work has been limited to perplexity or basic knowledge tasks and lacks a comprehensive…

Computation and Language · Computer Science 2025-06-05 Jemin Lee , Sihyeong Park , Jinse Kwon , Jihun Oh , Yongin Kwon

Large language models(LLMs) exhibit excellent performance across a variety of tasks, but they come with significant computational and storage costs. Quantizing these models is an effective way to alleviate this issue. However, existing…

Machine Learning · Computer Science 2023-11-14 Baisong Li , Xingwang Wang , Haixiao Xu

In the era of large language models (LLMs), weight-activation quantization helps fit models on edge device by reducing memory and compute bit-widths. However, three challenges persist for energy constrained hardware: (1) even after…

Machine Learning · Computer Science 2025-10-23 Chenyu Wang , Zhanglu Yan , Zhi Zhou , Xu Chen , Weng-Fai Wong

The growing scale of large language models (LLMs) not only demands extensive computational resources but also raises environmental concerns due to their increasing carbon footprint. Model quantization emerges as an effective approach that…

Software Engineering · Computer Science 2025-07-15 Saima Afrin , Bowen Xu , Antonio Mastropaolo

Model quantization reduces the bit-width of weights and activations, improving memory efficiency and inference speed in diffusion models. However, achieving 4-bit quantization remains challenging. Existing methods, primarily based on…

Machine Learning · Computer Science 2025-05-29 Maosen Zhao , Pengtao Chen , Chong Yu , Yan Wen , Xudong Tan , Tao Chen