English
Related papers

Related papers: StructKV: Preserving the Structural Skeleton for S…

200 papers

Large language models (LLMs) with extended context windows have become increasingly prevalent for tackling complex tasks. However, the substantial Key-Value (KV) cache required for long-context LLMs poses significant deployment challenges.…

Computation and Language · Computer Science 2025-06-16 Jie Hu , Shengnan Wang , Yutong He , Ping Gong , Jiawei Yi , Juncheng Zhang , Youhui Bai , Renhai Chen , Gong Zhang , Cheng Li , Kun Yuan

The Key-Value (KV) cache is crucial for efficient Large Language Models (LLMs) inference, but excessively long contexts drastically increase KV cache memory footprint. Existing KV cache compression methods typically rely on input-side…

Computation and Language · Computer Science 2026-03-13 Zhenxu Tian , Yi Su , Juntao Li , Min Zhang

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

Modern Large Language Models (LLMs) are increasingly trained to support very large context windows. We present Compactor, a training-free, query-agnostic KV compression strategy that uses approximate leverage scores to determine token…

Computation and Language · Computer Science 2025-12-10 Vivek Chari , Benjamin Van Durme

Large Language Models (LLMs) face a significant bottleneck during autoregressive inference due to the massive memory footprint of the Key-Value (KV) cache. Existing compression techniques like token eviction, quantization, or other low-rank…

Machine Learning · Computer Science 2025-11-25 Santhosh G S , Saurav Prakash , Balaraman Ravindran

Large Language Models (LLMs), epitomized by ChatGPT's release in late 2022, have revolutionized various industries with their advanced language comprehension. However, their efficiency is challenged by the Transformer architecture's…

Computation and Language · Computer Science 2024-11-21 Luohe Shi , Hongyi Zhang , Yao Yao , Zuchao Li , Hai Zhao

KV cache quantization reduces the memory cost of long-context LLM inference, but introduces approximation error that is typically validated only empirically. Existing systems rely on average-case robustness, with no mechanism to detect or…

Machine Learning · Computer Science 2026-05-21 Dean Calver

Long-context LLM inference is bottlenecked by the memory and bandwidth cost of reading large KV caches during decoding. KV compression reduces this cost by keeping only part of the cache, but task accuracy alone does not identify why a…

Machine Learning · Computer Science 2026-05-12 Ruijie Zhang , Haozhe Liang , Da Chang , Li Hu , Fanqi Kong , Huaxiao Yin , Yu Li

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 have revolutionized data processing in numerous domains, with their ability to handle extended context reasoning receiving notable recognition. To speed up inference, maintaining a key-value (KV) cache memory is…

Computation and Language · Computer Science 2024-10-22 Zhen Yang , J. N. Han , Kan Wu , Ruobing Xie , An Wang , Xingwu Sun , Zhanhui Kang

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

The deployment of large language models (LLMs) is often hindered by the extensive memory requirements of the Key-Value (KV) cache, especially as context lengths increase. Existing approaches to reduce the KV cache size involve either…

Computation and Language · Computer Science 2024-11-05 Alessio Devoto , Yu Zhao , Simone Scardapane , Pasquale Minervini

Large Language Models (LLMs) exhibit enhanced capabilities by Chain-of-Thought reasoning. However, the extended reasoning sequences introduce significant GPU memory overhead due to increased key-value (KV) cache. Existing KV cache…

Machine Learning · Computer Science 2025-10-16 Haoyue Zhang , Hualei Zhang , Xiaosong Ma , Jie Zhang , Song Guo

We demonstrate that unstructured sparsity significantly improves KV cache compression for LLMs, enabling sparsity levels up to 70% without compromising accuracy or requiring fine-tuning. We conduct a systematic exploration of pruning…

Machine Learning · Computer Science 2025-11-07 Donghyeon Joo , Helya Hosseini , Ramyad Hadidi , Bahar Asgari

Large Language Models (LLMs) have achieved impressive accomplishments in recent years. However, the increasing memory consumption of KV cache has possessed a significant challenge to the inference system. Eviction methods have revealed the…

Computation and Language · Computer Science 2025-07-10 Zicong Tang , Shi Luohe , Zuchao Li , Baoyuan Qi , Guoming Liu , Lefei Zhang , Ping Wang

Diffusion Language Models (DLMs) have been seen as a promising competitor for autoregressive language models. However, diffusion language models have long been constrained by slow inference. A core challenge is that their non-autoregressive…

Computation and Language · Computer Science 2025-05-22 Xinyin Ma , Runpeng Yu , Gongfan Fang , Xinchao Wang

Large language models are increasingly applied to multi-document and long-form inputs, yet long-context inference remains memory- and noise-inefficient. Key-value (KV) caching scales linearly with context length, while external retrieval…

Computation and Language · Computer Science 2026-01-29 Qingsen Ma , Dianyun Wang , Yaoye Wang , Lechen Ning , Sujie Zhu , Xiaohang Zhang , Jiaming Lyu , Linhao Ren , Zhenbo Xu , Zhaofeng He

Deploying long-context large language models (LLMs) is essential but poses significant computational and memory challenges. Caching all Key and Value (KV) states across all attention heads consumes substantial memory. Existing KV cache…

Computation and Language · Computer Science 2024-10-15 Guangxuan Xiao , Jiaming Tang , Jingwei Zuo , Junxian Guo , Shang Yang , Haotian Tang , Yao Fu , Song Han

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

Key-value (KV) cache compression has emerged as a critical technique for reducing the memory and latency overhead of autoregressive language models during inference. Prior approaches predominantly rely on query-key attention scores to rank…

Computation and Language · Computer Science 2025-09-19 Ayan Sengupta , Siddhant Chaudhary , Tanmoy Chakraborty