English
Related papers

Related papers: Dialogue Without Limits: Constant-Sized KV Caches …

200 papers

As context windows in LLMs scale to 100K+ tokens, the key-value (KV) cache becomes the dominant memory bottleneck, with recent methods claiming 80-90% savings and minimal benchmark degradation. We argue these evaluations miss a structural…

Computation and Language · Computer Science 2026-03-03 Samhruth Ananthanarayanan , Ayan Sengupta , Tanmoy Chakraborty

Long-running agentic tasks, such as deep research, require multi-hop reasoning over information distributed across multiple webpages and documents. In such tasks, the LLM context is dominated by tokens from external retrieval, causing…

Artificial Intelligence · Computer Science 2026-03-03 Sanjay Kariyappa , G. Edward Suh

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

The linear growth of the Key-Value (KV) cache is a critical bottleneck in long-form LLM inference. Existing KV compression methods mitigate this by evicting tokens based on importance scores. However, we show that their reliance on global…

Machine Learning · Computer Science 2026-05-25 Junzhe Yang , Xiaoyu Shen

Large reasoning models (LRMs) often incur significant key-value (KV) cache overhead, due to their linear growth with the verbose chain-of-thought (CoT) reasoning. This incurs both memory overhead and throughput bottlenecks, limiting…

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

KV-cache retrieval is essential for long-context LLM inference, yet existing methods struggle with distribution drift and high latency at scale. We introduce ParisKV, a drift-robust, GPU-native KV-cache retrieval framework based on…

Machine Learning · Computer Science 2026-02-11 Yanlin Qi , Xinhang Chen , Huiqiang Jiang , Qitong Wang , Botao Peng , Themis Palpanas

The Key-Value (KV) cache reading latency increases significantly with context lengths, hindering the efficiency of long-context LLM inference. To address this, previous works propose retaining a small fraction of KV cache based on token…

Databases · Computer Science 2025-09-18 Dongwei Wang , Zijie Liu , Song Wang , Yuxin Ren , Jianing Deng , Jingtong Hu , Tianlong Chen , Huanrui Yang

As the demand for long-context large language models (LLMs) increases, models with context windows of up to 128K or 1M tokens are becoming increasingly prevalent. However, long-context LLM inference is challenging since the inference speed…

Computation and Language · Computer Science 2024-08-28 Jiaming Tang , Yilong Zhao , Kan Zhu , Guangxuan Xiao , Baris Kasikci , Song Han

Key-Value (KV) cache facilitates efficient large language models (LLMs) inference by avoiding recomputation of past KVs. As the batch size and context length increase, the oversized KV caches become a significant memory bottleneck,…

Machine Learning · Computer Science 2025-02-04 Zunhai Su , Zhe Chen , Wang Shen , Hanyu Wei , Linge Li , Huangqi Yu , Kehong Yuan

Autoregressive (AR) video generation has emerged as a promising paradigm for long-horizon video synthesis, where each frame is generated conditioned on previously generated tokens. To accelerate inference, the KV cache is used to avoid…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Jiayi Luo , Qiyan Liu , Tengyang Wang , JunHao Liu , Jiayu Chen , Cong Wang , Hanxin Zhu , Chen Gao , Xiaobin Hu , Qingyun Sun , Zhibo Chen

LLM agents today communicate via text, which incurs considerable latency and information loss due to the need to autoregressively decode the sharer model's state and encode at the receiver model. Recent work such as Cache-to-Cache (C2C; Fu…

Machine Learning · Computer Science 2026-05-25 Maximillian Rossi , Prajwal Raghunath , Eugene Wu

Efficient long-context inference is critical as large language models (LLMs) adopt context windows of ranging from 128K to 1M tokens. However, the growing key-value (KV) cache and the high computational complexity of attention create…

Computation and Language · Computer Science 2025-03-13 Guangtao Wang , Shubhangi Upasani , Chen Wu , Darshan Gandhi , Jonathan Li , Changran Hu , Bo Li , Urmish Thakker

Autoregressive language models rely on a Key-Value (KV) Cache, which avoids re-computing past hidden states during generation, making it faster. As model sizes and context lengths grow, the KV Cache becomes a significant memory bottleneck,…

Computation and Language · Computer Science 2025-03-05 Nathan Godey , Alessio Devoto , Yu Zhao , Simone Scardapane , Pasquale Minervini , Éric de la Clergerie , Benoît Sagot

In this study, we investigate whether attention-based information flow inside large language models (LLMs) is aggregated through noticeable patterns for long context processing. Our observations reveal that LLMs aggregate information…

Computation and Language · Computer Science 2025-05-16 Zefan Cai , Yichi Zhang , Bofei Gao , Yuliang Liu , Yucheng Li , Tianyu Liu , Keming Lu , Wayne Xiong , Yue Dong , Junjie Hu , Wen Xiao

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

Large language models (LLMs) are increasingly applied in long-context scenarios such as multi-turn conversations. However, long contexts pose significant challenges for inference efficiency, including high memory overhead from Key-Value…

Computation and Language · Computer Science 2025-12-18 Kuan Lu , Shuhang Lin , Sai Wu , Yichen Yao , Junhan Yang , Huan Li , Wei Chu , Xu Yinghui , Yuan Qi , Gang Chen

Efficiently serving Large Language Models (LLMs) with persistent Prefix Key-Value (KV) Cache is critical for applications like conversational search and multi-turn dialogue. Serving a request requires loading the pre-computed prefix KV…

Operating Systems · Computer Science 2026-01-21 Jing Zou , Shangyu Wu , Hancong Duan , Qiao Li , Chun Jason Xue

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

Recently, significant progress has been made in developing reasoning-capable Large Language Models (LLMs) through long Chain-of-Thought (CoT) techniques. However, this long-CoT reasoning process imposes substantial memory overhead due to…

Computation and Language · Computer Science 2025-05-27 Tengxuan Liu , Shiyao Li , Jiayi Yang , Tianchen Zhao , Feng Zhou , Xiaohui Song , Guohao Dai , Shengen Yan , Huazhong Yang , Yu Wang