English
Related papers

Related papers: Finch: Prompt-guided Key-Value Cache Compression

200 papers

As the field of Large Language Models (LLMs) continues to evolve, the context length in inference is steadily growing. Key-Value Cache (KVCache), the intermediate representations of tokens within LLM inference, has now become the primary…

Computation and Language · Computer Science 2025-04-01 Hailin Zhang , Xiaodong Ji , Yilin Chen , Fangcheng Fu , Xupeng Miao , Xiaonan Nie , Weipeng Chen , Bin Cui

The growing popularity of Large Language Models has sparked interest in context compression for Large Language Models (LLMs). However, the performance of previous methods degrades dramatically as compression ratios increase, sometimes even…

Computation and Language · Computer Science 2024-06-18 Zhiwei Cao , Qian Cao , Yu Lu , Ningxin Peng , Luyang Huang , Shanbo Cheng , Jinsong Su

Large language models (LLMs) represent a groundbreaking advancement in the domain of natural language processing due to their impressive reasoning abilities. Recently, there has been considerable interest in increasing the context lengths…

Machine Learning · Computer Science 2024-11-11 Utkarsh Saxena , Gobinda Saha , Sakshi Choudhary , Kaushik Roy

Large Language Models (LLMs) have been widely deployed in a variety of applications, and the context length is rapidly increasing to handle tasks such as long-document QA and complex logical reasoning. However, long context poses…

Machine Learning · Computer Science 2025-06-17 Guangda Liu , Chengwei Li , Jieru Zhao , Chenqi Zhang , Minyi Guo

Large language models face significant computational and memory challenges when processing long contexts. During inference, efficient management of the key-value (KV) cache, which stores intermediate activations for autoregressive…

Computation and Language · Computer Science 2025-09-30 Yuxuan Zhu , Ali Falahati , David H. Yang , Mohammad Mohammadi Amiri

In long context scenarios, large language models (LLMs) face three main challenges: higher computational cost, performance reduction, and position bias. Research indicates that LLM performance hinges on the density and position of key…

Computation and Language · Computer Science 2024-08-13 Huiqiang Jiang , Qianhui Wu , Xufang Luo , Dongsheng Li , Chin-Yew Lin , Yuqing Yang , Lili Qiu

Large language models (LLMs) have achieved significant performance gains using advanced prompting techniques over various tasks. However, the increasing length of prompts leads to high computational costs and often obscures crucial…

Computation and Language · Computer Science 2025-01-03 Eunseong Choi , Sunkyung Lee , Minjin Choi , June Park , Jongwuk Lee

Existing key-value (KV) cache compression methods for large language models (LLMs) often rely on token eviction, which risks losing critical local information in both long prefilling and decoding scenarios. When extrapolating beyond the…

Computation and Language · Computer Science 2026-01-30 Jushi Kai , Yixuan Wang , Boyi Zeng , Haoli Bai , Bo Jiang , Ziwei He , Zhouhan Lin

Through reading the documentation in the context, tool-using language models can dynamically extend their capability using external tools. The cost is that we have to input lengthy documentation every time the model needs to use the tool,…

Computation and Language · Computer Science 2024-07-03 Yang Xu , Yunlong Feng , Honglin Mu , Yutai Hou , Yitong Li , Xinghao Wang , Wanjun Zhong , Zhongyang Li , Dandan Tu , Qingfu Zhu , Min Zhang , Wanxiang Che

While Large Language Models (LLMs) can theoretically support extensive context windows, their actual deployment is constrained by the linear growth of Key-Value (KV) cache memory. Prevailing compression strategies mitigate this through…

Artificial Intelligence · Computer Science 2026-02-03 Aryan Sood , Tanvi Sharma , Vansh Agrawal

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…

Computation and Language · Computer Science 2025-05-02 Zheng Zhang , Jinyi Li , Yihuai Lan , Xiang Wang , Hao Wang

Interacting with humans through multi-turn conversations is a fundamental feature of large language models (LLMs). However, existing LLM serving engines executing multi-turn conversations are inefficient due to the need to repeatedly…

Computation and Language · Computer Science 2024-07-02 Bin Gao , Zhuomin He , Puru Sharma , Qingxuan Kang , Djordje Jevdjic , Junbo Deng , Xingkun Yang , Zhou Yu , Pengfei Zuo

Long context compression is a critical research problem due to its significance in reducing the high computational and memory costs associated with LLMs. In this paper, we propose Activation Beacon, a plug-in module for transformer-based…

Computation and Language · Computer Science 2024-10-14 Peitian Zhang , Zheng Liu , Shitao Xiao , Ninglu Shao , Qiwei Ye , Zhicheng Dou

Large Language Models (LLMs) have been widely adopted to process long-context tasks. However, the large memory overhead of the key-value (KV) cache poses significant challenges in long-context scenarios. Existing training-free KV cache…

Machine Learning · Computer Science 2024-10-22 Luning Wang , Shiyao Li , Xuefei Ning , Zhihang Yuan , Shengen Yan , Guohao Dai , Yu Wang

Large language models (LLMs) can now handle longer sequences of tokens, enabling complex tasks like book understanding and generating lengthy novels. However, the key-value (KV) cache required for LLMs consumes substantial memory as context…

Machine Learning · Computer Science 2024-11-13 Haojie Duanmu , Zhihang Yuan , Xiuhong Li , Jiangfei Duan , Xingcheng Zhang , Dahua Lin

In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and…

Computation and Language · Computer Science 2024-10-31 Suyu Ge , Yunan Zhang , Liyuan Liu , Minjia Zhang , Jiawei Han , Jianfeng Gao

Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications. However, their increased computational and memory demands present significant…

Computation and Language · Computer Science 2025-02-28 Yuhui Xu , Zhanming Jie , Hanze Dong , Lei Wang , Xudong Lu , Aojun Zhou , Amrita Saha , Caiming Xiong , Doyen Sahoo

Recently, large language models (LLMs) have been able to handle longer and longer contexts. However, a context that is too long may cause intolerant inference latency and GPU memory usage. Existing methods propose mixed-precision…

Computation and Language · Computer Science 2025-04-01 Wei Tao , Bin Zhang , Xiaoyang Qu , Jiguang Wan , Jianzong Wang

Large Language Models (LLMs) have garnered widespread attention due to their remarkable performance across various tasks. However, to mitigate the issue of hallucinations, LLMs often incorporate retrieval-augmented pipeline to provide them…

Computation and Language · Computer Science 2024-08-29 Haowen Hou , Fei Ma , Binwen Bai , Xinxin Zhu , Fei Yu

Fine-tuning large language models on new data improves task performance but degrades capabilities learned during pretraining, a phenomenon known as catastrophic forgetting. Existing methods mitigate this by modifying the fine-tuning…

Machine Learning · Computer Science 2026-05-20 Parjanya Prajakta Prashant , Jiongli Zhu , Aldan Creo , Babak Salimi