English
Related papers

Related papers: FreeKV: Boosting KV Cache Retrieval for Efficient …

200 papers

The memory and computational demands of Key-Value (KV) cache present significant challenges for deploying long-context language models. Previous approaches attempt to mitigate this issue by selectively dropping tokens, which irreversibly…

Machine Learning · Computer Science 2024-07-24 Hanlin Tang , Yang Lin , Jing Lin , Qingsen Han , Shikuan Hong , Yiwu Yao , Gongyi Wang

Large language models (LLMs) rely on key-value cache (KV cache) to accelerate decoding by reducing redundant computations. However, the KV cache memory usage grows substantially with longer text sequences, posing challenges for efficient…

Computation and Language · Computer Science 2025-11-18 Yixuan Wang , Shiyu Ji , Yijun Liu , Yuzhuang Xu , Yang Xu , Qingfu Zhu , Wanxiang Che

Large language models (LLMs) have shown great performance on complex reasoning tasks but often require generating long intermediate thoughts before reaching a final answer. During generation, LLMs rely on a key-value (KV) cache for…

While Key-Value (KV) cache compression is essential for efficient LLM inference, current evaluations disproportionately focus on sparse retrieval tasks, potentially masking the degradation of High-Density Reasoning where Chain-of-Thought…

Computation and Language · Computer Science 2026-05-13 Xiang Liu , Zhenheng Tang , Hong Chen , Peijie Dong , Zeyu Li , Xiuze Zhou , Bo Li , Xuming Hu , Xiaowen Chu

Large Language Models (LLMs) are increasingly deployed in long-context tasks such as reasoning, code generation, and multi-turn dialogue. However, inference over extended contexts is bottlenecked by the Key-Value (KV) cache, whose memory…

Computation and Language · Computer Science 2026-05-21 Seonghwan Choi , Beomseok Kang , Dongwon Jo , Jae-Joon Kim

Long streaming video QA remains challenging due to growing visual tokens and limited reasoning length of large language models (LLMs). KV-caching stores the Key-Value (KV) of the historical tokens via LLM prefill and enables more efficient…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Junbin Xiao , Jiajun Chen , Tianxiang Sun , Xun Yang , Angela Yao

Edge acceleration for large language models is crucial for their widespread application; however, achieving fast attention inference and efficient decoding on resource-constrained edge accelerators remains challenging. This paper presents…

Hardware Architecture · Computer Science 2026-01-19 Junming Zhang , Qinyan Zhang , Huajun Sun , Feiyang Gao , Sheng Hu , Rui Nie , Xiangshui Miao

The key-value (KV) cache is a major bottleneck in long-context inference, where memory and computation grow with sequence length. Existing KV eviction methods reduce this cost but typically degrade performance relative to full-cache…

Machine Learning · Computer Science 2026-05-12 Ngoc Bui , Hieu Trung Nguyen , Arman Cohan , Rex Ying

Large Language Models (LLMs) are increasingly being deployed on edge devices for long-context settings, creating a growing need for fast and efficient long-context inference. In these scenarios, the Key-Value (KV) cache is the primary…

Efficient real-world deployments of large language models (LLMs) rely on Key-Value (KV) caching for processing and generating long outputs, reducing the need for repetitive computation. For large contexts, Key-Value caches can take up tens…

Key-Value (KV) cache plays a crucial role in accelerating inference in large language models (LLMs) by storing intermediate attention states and avoiding redundant computation during autoregressive generation. However, its memory footprint…

Machine Learning · Computer Science 2026-04-14 Yuzhen Mao , Qitong Wang , Martin Ester , Ke Li

Large Language Models (LLMs) exhibit pronounced memory-bound characteristics during inference due to High Bandwidth Memory (HBM) bandwidth constraints. In this paper, we propose an L2 Cache-oriented asynchronous KV Cache prefetching method…

Machine Learning · Computer Science 2025-11-11 Yanhao Dong , Yubo Miao , Weinan Li , Xiao Zheng , Chao Wang , Jiesheng Wu , Feng Lyu

The escalating context length in Large Language Models (LLMs) creates a severe performance bottleneck around the Key-Value (KV) cache, whose memory-bound nature leads to significant GPU under-utilization. This paper introduces Mixture of…

Machine Learning · Computer Science 2025-11-11 Myunghyun Rhee , Sookyung Choi , Euiseok Kim , Joonseop Sim , Youngpyo Joo , Hoshik Kim

The efficacy of Large Language Models (LLMs) in long-context tasks is often hampered by the substantial memory footprint and computational demands of the Key-Value (KV) cache. Current compression strategies, including token eviction and…

Computation and Language · Computer Science 2025-07-29 Runchao Li , Yao Fu , Mu Sheng , Xianxuan Long , Haotian Yu , Pan Li

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks. However, their extensive memory requirements, particularly due to KV cache growth during long-text understanding and…

Computation and Language · Computer Science 2025-10-14 Haoqi Yang , Yao Yao , Zuchao Li , Baoyuan Qi , Guoming Liu , Hai Zhao

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

The quadratic complexity of Multimodal Large Language Models (MLLMs) with respect to context length poses significant computational and memory challenges, hindering their real-world deployment. In the paper, we devise a…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Yuhang Han , Xuyang Liu , Zihan Zhang , Pengxiang Ding , Junjie Chen , Donglin Wang , Honggang Chen , Qingsen Yan , Siteng Huang

Large Reasoning Models (LRMs) are becoming integral to many AI inference systems, enhancing their capabilities with advanced reasoning. However, deploying these models in production environments presents a significant QoS challenge: the…

Machine Learning · Computer Science 2026-05-15 Kaiwen Chen , Xin Tan , Minchen Yu , Jingzong Li , Hong Xu

Disaggregated inference has become an essential framework that separates the prefill (P) and decode (D) stages in large language model inference to improve throughput. However, the KV cache transfer faces significant delays between prefill…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-08 Weiqing Li , Guochao Jiang , Xiangyong Ding , Zhangcheng Tao , Chuzhan Hao , Chenfeng Xu , Yuewei Zhang , Hao Wang

Diffusion large language models (dLLMs) present a promising alternative to dominant autoregressive models (ARMs) by the ability of parallel decoding at the expense of substantial computation and memory costs. Specifically, the cache…

Computation and Language · Computer Science 2025-10-13 Jianuo Huang , Yaojie Zhang , Yicun Yang , Benhao Huang , Biqing Qi , Dongrui Liu , Linfeng Zhang