English
Related papers

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

200 papers

Many computational factors limit broader deployment of large language models. In this paper, we focus on a memory bottleneck imposed by the key-value (KV) cache, a computational shortcut that requires storing previous KV pairs during…

Machine Learning · Computer Science 2024-06-13 Harry Dong , Xinyu Yang , Zhenyu Zhang , Zhangyang Wang , Yuejie Chi , Beidi Chen

Transformer-based large language models (LLMs) cache context as key-value (KV) pairs during inference. As context length grows, KV cache sizes expand, leading to substantial memory overhead and increased attention latency. This paper…

Databases · Computer Science 2025-10-01 Jang-Hyun Kim , Jinuk Kim , Sangwoo Kwon , Jae W. Lee , Sangdoo Yun , Hyun Oh Song

Compressing lengthy context is a critical but technically challenging problem. In this paper, we propose a new method called UltraGist, which is distinguished for its high-quality compression of lengthy context due to the innovative design…

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

Despite the recent success of Large Language Models (LLMs), it remains challenging to feed LLMs with long prompts due to the fixed size of LLM inputs. As a remedy, prompt compression becomes a promising solution by removing redundant tokens…

Computation and Language · Computer Science 2025-01-06 Ziyang Yu , Yuyu Liu

Autoregressive Transformers rely on Key-Value (KV) caching to accelerate inference. However, the linear growth of the KV cache with context length leads to excessive memory consumption and bandwidth constraints. This bottleneck is…

Computation and Language · Computer Science 2025-06-10 Ravi Ghadia , Avinash Kumar , Gaurav Jain , Prashant Nair , Poulami Das

While large language models (LLMs) excel in generating coherent and contextually rich outputs, their capacity to efficiently handle long-form contexts is limited by fixed-length position embeddings. Additionally, the computational cost of…

Computation and Language · Computer Science 2025-05-23 Sumin An , Junyoung Sung , Wonpyo Park , Chanjun Park , Paul Hongsuck Seo

Handling long input contexts remains a significant challenge for Large Language Models (LLMs), particularly in resource-constrained environments such as mobile devices. Our work aims to address this limitation by introducing InfiniPot, a…

Computation and Language · Computer Science 2024-10-04 Minsoo Kim , Kyuhong Shim , Jungwook Choi , Simyung Chang

Scaling the input context length of a large language model (LLM) incurs a significant increase in computation cost and memory footprint to maintain the attention key-value (KV) cache. Existing KV cache compression methods suffer from…

Computation and Language · Computer Science 2025-01-31 Yuxiang Huang , Binhang Yuan , Xu Han , Chaojun Xiao , Zhiyuan Liu

With the growing demand for long-context LLMs across a wide range of applications, the key-value (KV) cache has become a critical bottleneck for both latency and memory usage. Recently, KV-cache offloading has emerged as a promising…

Machine Learning · Computer Science 2026-05-18 Andrey Bocharnikov , Ivan Ermakov , Denis Kuznedelev , Vyacheslav Zhdanovskiy , Yegor Yershov

Large language models (LLMs) are typically served from clusters of GPUs/NPUs that consist of large number of devices. Unfortunately, communication between these devices incurs significant overhead, increasing the inference latency and cost…

Artificial Intelligence · Computer Science 2025-05-27 Ahmet Caner Yüzügüler , Jiawei Zhuang , Lukas Cavigelli

Large Language Models (LLMs) face significant challenges in long-context processing, including quadratic computational costs, information forgetting, and the context fragmentation inherent in retrieval-augmented generation (RAG). We propose…

Computation and Language · Computer Science 2026-02-10 Zhuoen Chen , Dongfang Li , Meishan Zhang , Baotian Hu , Min Zhang

The context caching technique is employed to accelerate the Multimodal Large Language Model (MLLM) inference by prevailing serving platforms currently. However, this approach merely reuses the Key-Value (KV) cache of the initial sequence of…

Machine Learning · Computer Science 2025-09-23 Shiju Zhao , Junhao Hu , Rongxiao Huang , Jiaqi Zheng , Guihai Chen

Large Language Models (LLMs) are increasingly used in applications requiring long context lengths, but the key-value (KV) cache often becomes a memory bottleneck on GPUs as context grows. To address this, we propose Commutative Vector…

Large Language Models (LLMs) use key-value (KV) cache to reduce redundant computation in autoregressive generation. However, the KV cache size increases linearly during generation, leading to excessive memory usage, especially for long…

Computation and Language · Computer Science 2025-03-04 Jian Yuan , Ziwei He , Haoli Bai , Jingwen Leng , Bo Jiang

As the ever-increasing token limits of large language models (LLMs) have enabled long context as input, prompting with single data samples might no longer an efficient way. A straightforward strategy improving efficiency is to batch data…

Computation and Language · Computer Science 2024-07-16 Jianzhe Lin , Maurice Diesendruck , Liang Du , Robin Abraham

Although applications involving long-context inputs are crucial for the effective utilization of large language models (LLMs), they also result in increased computational costs and reduced performance. To address this challenge, we propose…

Computation and Language · Computer Science 2025-02-06 Weizhi Fei , Xueyan Niu , Guoqing Xie , Yingqing Liu , Bo Bai , Wei Han

How to efficiently serve Large Language Models (LLMs) has become a pressing issue because of their huge computational cost in their autoregressive generation process. To mitigate computational costs, LLMs often employ the KV Cache technique…

Computation and Language · Computer Science 2024-07-23 Zheng Wang , Boxiao Jin , Zhongzhi Yu , Minjia Zhang

As Large Language Models (LLMs) scale to support context windows exceeding one million tokens, the linear growth of Key-Value (KV) cache imposes severe memory capacity and bandwidth bottlenecks, constraining the efficiency of long-context…

Computation and Language · Computer Science 2026-04-09 Zhirui Chen , Peiyang Liu , Ling Shao

Large Language Models (LLMs) rely heavily on Key-Value (KV) caching to minimize inference latency. However, standard KV caches are context-dependent: reusing a cached document in a new context requires recomputing KV states to account for…

Machine Learning · Computer Science 2026-04-20 Chuangtao Chen , Grace Li Zhang , Xunzhao Yin , Cheng Zhuo , Bing Li , Ulf Schlichtmann

Modern large language models (LLMs) extend context lengths to millions of tokens, enabling coherent, personalized responses grounded in long conversational history. However, the Key-Value (KV) cache grows linearly with the extended dialogue…

Computation and Language · Computer Science 2026-05-21 Minsoo Kim , Arnav Kundu , Han-Byul Kim , Richa Dixit , Minsik Cho
‹ Prev 1 3 4 5 6 7 10 Next ›