English
Related papers

Related papers: ThinKV: Thought-Adaptive KV Cache Compression for …

200 papers

With the development of large language models (LLMs), efficient inference through Key-Value (KV) cache compression has attracted considerable attention, especially for long-context generation. To compress the KV cache, recent methods…

Computation and Language · Computer Science 2025-10-28 Qingyue Yang , Jie Wang , Xing Li , Zhihai Wang , Chen Chen , Lei Chen , Xianzhi Yu , Wulong Liu , Jianye Hao , Mingxuan Yuan , Bin Li

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

A critical approach for efficiently deploying computationally demanding large language models (LLMs) is Key-Value (KV) caching. The KV cache stores key-value states of previously generated tokens, significantly reducing the need for…

Computation and Language · Computer Science 2024-09-10 Akide Liu , Jing Liu , Zizheng Pan , Yefei He , Gholamreza Haffari , Bohan Zhuang

Serving large language models (LLMs) at scale necessitates efficient key-value (KV) cache management. KV caches can be reused across conversation turns via shared-prefix prompts that are common in iterative code editing and chat. However,…

Computation and Language · Computer Science 2026-03-12 Konrad Staniszewski , Adrian Łańcucki

The Key-Value (KV) cache is central to the efficiency of transformer-based large language models (LLMs), storing previously computed vectors to accelerate inference. Yet, as sequence length and batch size grow, the cache becomes a major…

Machine Learning · Computer Science 2025-12-08 Damien Lesens , Beheshteh T. Rakhshan , Guillaume Rabusseau

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

Sequence-to-sequence tasks often benefit from long contexts, but the quadratic complexity of self-attention in standard Transformers renders this non-trivial. During generation, temporary representations -stored in the so-called KV…

Computation and Language · Computer Science 2025-03-14 Vivek Chari , Guanghui Qin , Benjamin Van Durme

Scaling language models to long contexts is often bottlenecked by the size of the key-value (KV) cache. In deployed settings, long contexts are typically managed through compaction in token space via summarization. However, summarization…

Machine Learning · Computer Science 2026-05-28 Adam Zweiger , Xinghong Fu , Han Guo , Yoon Kim

The growth of long-context Large Language Models (LLMs) significantly increases memory and bandwidth pressure during autoregressive decoding due to the expanding Key-Value (KV) cache. While accuracy-preserving KV-cache quantization (e.g.,…

Hardware Architecture · Computer Science 2026-01-06 Dayou Du , Shijie Cao , Jianyi Cheng , Luo Mai , Ting Cao , Mao Yang

KV cache memory is the dominant bottleneck for long-context LLM inference. Existing compression methods each act on a single axis of the four-dimensional KV tensor -- token eviction (sequence), quantization (precision), low-rank projection…

Machine Learning · Computer Science 2026-04-21 Libo Sun , Peixiong He , Po-Wei Harn , Xiao Qin

Autoregressive (AR) video diffusion models adopt a streaming generation framework, enabling long-horizon video generation with real-time responsiveness, as exemplified by the Self Forcing training paradigm. However, existing AR video…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Yicheng Ji , Zhizhou Zhong , Jun Zhang , Qin Yang , XiTai Jin , Ying Qin , Wenhan Luo , Shuiyang Mao , Wei Liu , Huan Li

Auto-regressive inference of transformers benefit greatly from Key-Value (KV) caching, but can lead to major memory bottlenecks as model size, batch size, and sequence length grow at scale. We introduce Multi-Layer Key-Value (MLKV) sharing,…

Machine Learning · Computer Science 2024-10-16 Zayd Muhammad Kawakibi Zuhri , Muhammad Farid Adilazuarda , Ayu Purwarianti , Alham Fikri Aji

While generative retrieval (GR) demonstrates competitive performance on standard retrieval benchmarks, existing approaches directly map queries to document identifiers (docids) without intermediate deliberation, limiting their effectiveness…

Information Retrieval · Computer Science 2026-05-22 Wenhao Zhang , Ruihao Yu , Yi Bai , Zhumin Chen , Pengjie Ren

Efficient key-value (KV) cache management is crucial for the practical deployment of large language models (LLMs), yet existing compression techniques often incur a trade-off between performance degradation and computational overhead. We…

Machine Learning · Computer Science 2026-02-10 Jang-Hyun Kim , Dongyoon Han , Sangdoo Yun

Chain-of-Thought (CoT) has been proven effective in enhancing the reasoning capabilities of large language models (LLMs). Recent advancements, such as OpenAI's o1 and DeepSeek-R1, suggest that scaling up the length of CoT sequences during…

Computation and Language · Computer Science 2025-09-17 Heming Xia , Chak Tou Leong , Wenjie Wang , Yongqi Li , Wenjie Li

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…

Attention mechanisms underpin the success of large language models (LLMs), yet their substantial computational and memory overhead poses challenges for optimizing efficiency and performance. A critical bottleneck arises as KV cache and…

Computation and Language · Computer Science 2025-07-24 Luoyang Sun , Cheng Deng , Jiwen Jiang , Xinjian Wu , Haifeng Zhang , Lei Chen , Lionel Ni , Jun Wang

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

Transformer-based large language models (LLMs) demonstrate impressive potential in various practical applications. However, long context inference poses a significant challenge due to the enormous memory requirements of the key-value (KV)…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-03 Bo Jiang , Taolue Yang , Youyuan Liu , Chengming Zhang , Xubin He , Sian Jin

The growing context length of Large Language Models (LLMs) enlarges the Key-Value (KV) cache, limiting deployment in resource-limited environments. Prior training-free approaches for KV cache compression typically rely on low-rank…

Computation and Language · Computer Science 2026-03-18 Yixuan Wang , Qingyu Shi , Jiayu Zhou , Dianbo Liu , Ziwei He , Zhouhan Lin