English
Related papers

Related papers: LAVa: Layer-wise KV Cache Eviction with Dynamic Bu…

200 papers

Recently, large language models (LLMs) have shown remarkable reasoning abilities by producing long reasoning traces. However, as the sequence length grows, the key-value (KV) cache expands linearly, incurring significant memory and…

Computation and Language · Computer Science 2026-02-04 Zican Dong , Peiyu Liu , Junyi Li , Zhipeng Chen , Han Peng , Shuo Wang , Wayne Xin Zhao

Multi-modal Large Language Models (MLLMs) serving systems commonly employ KV-cache compression to reduce memory footprint. However, existing compression methods introduce significant processing overhead and queuing delays, particularly in…

Multimedia · Computer Science 2025-03-12 Jianian Zhu , Hang Wu , Haojie Wang , Yinghui Li , Biao Hou , Ruixuan Li , Jidong Zhai

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 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

Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, quickly becoming the bottleneck for long context inference. A…

Computation and Language · Computer Science 2026-05-26 Xintong Yang , Hao Gu , Binxing Xu , Lujun Li , Bei Liu , Jiacheng Liu , Qiyuan Zhu , Sirui Han , Yike Guo

Supporting long-context LLMs is challenging due to the substantial memory demands of the key-value (KV) cache. Existing offloading systems store the full cache in host memory and selectively fetch critical entries during decoding, but this…

Computation and Language · Computer Science 2026-05-19 Jian Lin , Jiazhi Mi , Zicong Hong , Haodong Wang , Qianli Liu , Haodyue Zhang , Peng Li , Song Guo

We describe KVLink, an approach for efficient key-value (KV) cache reuse in large language models (LLMs). In many LLM applications, different inputs can share overlapping context, such as the same retrieved document appearing in multiple…

Computation and Language · Computer Science 2025-11-11 Jingbo Yang , Bairu Hou , Wei Wei , Yujia Bao , Shiyu Chang

The Key-Value (KV) cache is integral to efficient autoregressive inference in large language models (LLMs), yet its unbounded growth in stateful multi-turn scenarios presents major challenges. This paper examines the interplay between KV…

Machine Learning · Computer Science 2025-11-10 Pratik Poudel

The growing memory footprint of the Key-Value (KV) cache poses a severe scalability bottleneck for long-context Large Language Model (LLM) inference. While KV cache eviction has emerged as an effective solution by discarding less critical…

Computation and Language · Computer Science 2025-10-28 Jinhan Chen , Jianchun Liu , Hongli Xu , Xianjun Gao , Shilong Wang

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

Large language models have revolutionized natural language processing, yet their deployment remains hampered by the substantial memory and runtime overhead of the transformer's Key-Value cache. To mitigate this, recent methods employ a…

Computation and Language · Computer Science 2025-10-16 Yuan Feng , Haoyu Guo , JunLin Lv , S. Kevin Zhou , Xike Xie

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

The deployment of efficient long-context LLMs in applications like autonomous agents, long-chain reasoning, and creative writing is fundamentally bottlenecked by the linear growth of KV cache memory. Existing compression and eviction…

Computation and Language · Computer Science 2026-02-10 Jitai Hao , Qiang Huang , Yaowei Wang , Min Zhang , Jun Yu

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

Serving transformer language models with high throughput requires caching Key-Values (KVs) to avoid redundant computation during autoregressive generation. The memory footprint of KV caching is significant and heavily impacts serving costs.…

Machine Learning · Computer Science 2026-04-28 Anastasiia Filippova , David Grangier , Marco Cuturi , João Monteiro

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

Transformer-based large language models (LLMs) use the key-value (KV) cache to significantly accelerate inference by storing the key and value embeddings of past tokens. However, this cache consumes significant GPU memory. In this work, we…

The growing size of Large Language Models (LLMs) makes efficient inference challenging, primarily due to the memory demands of the autoregressive Key-Value (KV) cache. Existing eviction or compression methods reduce cost but rely on…

Computation and Language · Computer Science 2026-02-12 Luca Moschella , Laura Manduchi , Ozan Sener

This paper introduces MadaKV, a modality-adaptive key-value (KV) cache eviction strategy designed to enhance the efficiency of multimodal large language models (MLLMs) in long-context inference. In multimodal scenarios, attention heads…

Machine Learning · Computer Science 2025-06-23 Kunxi Li , Zhonghua Jiang , Zhouzhou Shen , Zhaode Wang , Chengfei Lv , Shengyu Zhang , Fan Wu , Fei Wu

Reasoning large language models exhibit complex reasoning behaviors via extended chain-of-thought generation that are highly fragile to information loss during decoding, creating critical challenges for KV cache compression. Existing…

Computation and Language · Computer Science 2026-05-28 Wenjie Du , Li Jiang , Keda Tao , Xue Liu , Huan Wang
‹ Prev 1 3 4 5 6 7 10 Next ›