中文
相关论文

相关论文: The Cost of Compression: Investigating the Impact …

200 篇论文

Large Language Models (LLMs) have transformed natural language processing tasks successfully. Yet, their large size and high computational needs pose challenges for practical use, especially in resource-limited settings. Model compression…

计算与语言 · 计算机科学 2024-07-31 Xunyu Zhu , Jian Li , Yong Liu , Can Ma , Weiping Wang

Deep learning models have achieved tremendous success in most of the industries in recent years. The evolution of these models has also led to an increase in the model size and energy requirement, making it difficult to deploy in production…

机器学习 · 计算机科学 2024-07-24 Aayush Saxena , Arit Kumar Bishwas , Ayush Ashok Mishra , Ryan Armstrong

Large language models (LLMs) exhibit excellent performance in various tasks. However, the memory requirements of LLMs present a great challenge when deploying on memory-limited devices, even for quantized LLMs. This paper introduces a…

计算与语言 · 计算机科学 2025-02-24 Weilan Wang , Yu Mao , Dongdong Tang , Hongchao Du , Nan Guan , Chun Jason Xue

Due to the substantial scale of Large Language Models (LLMs), the direct application of conventional compression methodologies proves impractical. The computational demands associated with even minimal gradient updates present challenges,…

机器学习 · 计算机科学 2023-12-13 Arnav Chavan , Nahush Lele , Deepak Gupta

How can we compress language models without sacrificing accuracy? The number of compression algorithms for language models is rapidly growing to benefit from remarkable advances of recent language models without side effects due to the…

计算与语言 · 计算机科学 2024-01-30 Seungcheol Park , Jaehyeon Choi , Sojin Lee , U Kang

We introduce compression laws for language language models (LLMs). While recent scaling laws have sought to understand how LLMs scale with respect to model size, pre-training data, and computational resources, we focus on understanding how…

计算与语言 · 计算机科学 2025-04-08 Ayan Sengupta , Siddhant Chaudhary , Tanmoy Chakraborty

Increasingly, model compression techniques enable large language models (LLMs) to be deployed in real-world applications. As a result of this momentum towards local deployment, compressed LLMs will interact with a large population. Prior…

计算与语言 · 计算机科学 2024-10-15 Zhichao Xu , Ashim Gupta , Tao Li , Oliver Bentham , Vivek Srikumar

Transformer based large language models have achieved tremendous success. However, the significant memory and computational costs incurred during the inference process make it challenging to deploy large models on resource-constrained…

计算与语言 · 计算机科学 2024-02-16 Wenxiao Wang , Wei Chen , Yicong Luo , Yongliu Long , Zhengkai Lin , Liye Zhang , Binbin Lin , Deng Cai , Xiaofei He

Language models have proven successful across a wide range of software engineering tasks, but their significant computational costs often hinder their practical adoption. To address this challenge, researchers have begun applying various…

软件工程 · 计算机科学 2024-12-19 Giordano d'Aloisio , Luca Traini , Federica Sarro , Antinisca Di Marco

Prompt engineering enables Large Language Models (LLMs) to perform a variety of tasks. However, lengthy prompts significantly increase computational complexity and economic costs. To address this issue, we study six prompt compression…

计算与语言 · 计算机科学 2025-05-02 Zheng Zhang , Jinyi Li , Yihuai Lan , Xiang Wang , Hao Wang

Large Language Models are growing in size, and we expect them to continue to do so, as larger models train quicker. However, this increase in size will severely impact inference costs. Therefore model compression is important, to retain the…

机器学习 · 计算机科学 2024-04-10 Georgy Tyukin

Transformer plays a vital role in the realms of natural language processing (NLP) and computer vision (CV), specially for constructing large language models (LLM) and large vision models (LVM). Model compression methods reduce the memory…

机器学习 · 计算机科学 2024-04-09 Yehui Tang , Yunhe Wang , Jianyuan Guo , Zhijun Tu , Kai Han , Hailin Hu , Dacheng Tao

Although large language models (LLMs) have demonstrated their strong intelligence ability, the high demand for computation and storage hinders their practical application. To this end, many model compression techniques are proposed to…

计算与语言 · 计算机科学 2024-11-01 Ge Yang , Changyi He , Jinyang Guo , Jianyu Wu , Yifu Ding , Aishan Liu , Haotong Qin , Pengliang Ji , Xianglong Liu

Recent large language models (LLMs) employ billions of parameters to enable broad problem-solving capabilities. Such language models also tend to be memory-bound because of the dominance of matrix-vector and matrix-matrix multiplications…

机器学习 · 计算机科学 2024-10-24 Chakshu Moar , Faraz Tahmasebi , Michael Pellauer , Hyoukjun Kwon

Leveraging large language models (LLMs) for complex natural language tasks typically requires long-form prompts to convey detailed requirements and information, which results in increased memory usage and inference costs. To mitigate these…

计算与语言 · 计算机科学 2024-10-18 Zongqian Li , Yinhong Liu , Yixuan Su , Nigel Collier

Large Language Models (LLMs) require substantial computational resources, making model compression essential for efficient deployment in constrained environments. Among the dominant compression techniques: knowledge distillation, structured…

机器学习 · 计算机科学 2025-11-26 Shivansh Chhawri , Rahul Mahadik , Suparna Rooj

Large language models (LLMs) have been applied in various applications due to their astonishing capabilities. With advancements in technologies such as chain-of-thought (CoT) prompting and in-context learning (ICL), the prompts fed to LLMs…

计算与语言 · 计算机科学 2023-12-07 Huiqiang Jiang , Qianhui Wu , Chin-Yew Lin , Yuqing Yang , Lili Qiu

We conceptualize the process of understanding as information compression, and propose a method for ranking large language models (LLMs) based on lossless data compression. We demonstrate the equivalence of compression length under…

人工智能 · 计算机科学 2024-06-21 Peijia Guo , Ziguang Li , Haibo Hu , Chao Huang , Ming Li , Rui Zhang

Deploying Large Language Models (LLMs) on edge or mobile devices offers significant benefits, such as enhanced data privacy and real-time processing capabilities. However, it also faces critical challenges due to the substantial memory…

机器学习 · 计算机科学 2024-05-07 Yu Mao , Weilan Wang , Hongchao Du , Nan Guan , Chun Jason Xue

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,…

计算与语言 · 计算机科学 2024-06-07 Renren Jin , Jiangcun Du , Wuwei Huang , Wei Liu , Jian Luan , Bin Wang , Deyi Xiong
‹ 上一页 1 2 3 10 下一页 ›