English
Related papers

Related papers: Self-Pruned Key-Value Attention: Learning When to …

200 papers

To improve the robustness of transformer neural networks used for temporal-dynamics prediction of chaotic systems, we propose a novel attention mechanism called easy attention which we demonstrate in time-series reconstruction and…

Machine Learning · Computer Science 2025-06-05 Marcial Sanchis-Agudo , Yuning Wang , Roger Arnau , Luca Guastoni , Jasmin Lim , Karthik Duraisamy , Ricardo Vinuesa

Efficient inference of large language models (LLMs) is hindered by an ever-growing key-value (KV) cache, making KV cache compression a critical research direction. Traditional methods selectively evict less important KV cache entries, which…

Machine Learning · Computer Science 2025-12-01 Yuxuan Tian , Zihan Wang , Yebo Peng , Aomufei Yuan , Zhiming Wang , Bairen Yi , Xin Liu , Yong Cui , Tong Yang

While Key-Value (KV) cache succeeds in reducing redundant computations in auto-regressive models, it introduces significant memory overhead, limiting its practical deployment in long-sequence scenarios. Existing KV retrieval methods…

Machine Learning · Computer Science 2025-10-14 Wenbo Wu , Qingyi Si , Xiurui Pan , Ye Wang , Jie Zhang

Standard Transformer attention uses identical dimensionality for queries, keys, and values, yet these components serve different roles: queries and keys produce scalar attention weights (selection), while values carry rich representations…

Machine Learning · Computer Science 2026-03-31 Hengshuai Yao , Xing Chen , Ahmed Murtadha , Guan Wang

With the increasing volumes of Large Language Models (LLMs) and the expanding context lengths, attention computation has become a key performance bottleneck in LLM serving. For fast attention computation, recent practices often parallelize…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-12 Di Liu , Yifei Liu , Chen Chen , Zhibin Yu , Xiaoyi Fan , Quan Chen , Minyi Guo

KV cache stores key and value states from previous tokens to avoid re-computation, yet it demands substantial storage space, especially for long sequences. Adaptive KV cache compression seeks to discern the saliency of tokens, preserving…

Machine Learning · Computer Science 2024-05-24 Yefei He , Luoming Zhang , Weijia Wu , Jing Liu , Hong Zhou , Bohan Zhuang

Neural language models predict the next token using a latent representation of the immediate token history. Recently, various methods for augmenting neural language models with an attention mechanism over a differentiable memory have been…

Computation and Language · Computer Science 2017-02-16 Michał Daniluk , Tim Rocktäschel , Johannes Welbl , Sebastian Riedel

Multimodal large language models (MLLMs) are plagued by exorbitant inference costs attributable to the profusion of visual tokens within the vision encoder. The redundant visual tokens engenders a substantial computational load and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Jiedong Zhuang , Lu Lu , Ming Dai , Rui Hu , Jian Chen , Qiang Liu , Haoji Hu

Long-context inference in large language models (LLMs) is bottlenecked by the linear growth of the self-attention key-value (KV) cache. Top-k sparse attention alleviates this by loading only a small fraction of the KV cache, but accurately…

Computation and Language · Computer Science 2026-05-28 Keqi Deng , Shaoshi Ling , Ruchao Fan , Jinyu Li

Recent large language models (LLMs) are rapidly extending their context windows, yet inference throughput lags due to increasing GPU memory and bandwidth demands. This is because the key-value (KV) cache, an intermediate structure storing…

This paper proposes SR-KI, a novel approach for integrating real-time and large-scale structured knowledge bases (KBs) into large language models (LLMs). SR-KI begins by encoding KBs into key-value pairs using a pretrained encoder, and…

Computation and Language · Computer Science 2025-11-11 Bohan Yu , Wei Huang , Kang Liu

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

Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks. These capabilities stem primarily from the self-attention mechanism, which enables modeling of long-range…

Computation and Language · Computer Science 2026-01-05 Zeng You , Yaofo Chen , Shuhai Zhang , Zhijie Qiu , Tingyu Wu , Yingjian Li , Yaowei Wang , Mingkui Tan

As large language models (LLMs) and visual language models (VLMs) grow in scale and application, attention mechanisms have become a central computational bottleneck due to their high memory and time complexity. While many efficient…

Machine Learning · Computer Science 2025-07-11 Zhengyu Tian , Anantha Padmanaban Krishna Kumar , Hemant Krishnakumar , Reza Rawassizadeh

Recent advancements in Audio-Video Large Language Models (AV-LLMs) have enhanced their capabilities in tasks like audio-visual question answering and multimodal dialog systems. Video and audio introduce an extended temporal dimension,…

Multimedia · Computer Science 2025-11-17 Zhonghua Jiang , Kui Chen , Kunxi Li , Keting Yin , Yiyun Zhou , Zhaode Wang , Chengfei Lv , Shengyu Zhang

The increasing input sequence length in Large Language Models (LLMs) puts significant pressure on key-value (KV) cache storage, making efficient inference challenging. Explicitly distinguishing attention behavior into our self-defined…

Computation and Language · Computer Science 2025-08-25 Mengjie Li , William J. Song

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

The Key-Value (KV) cache is a crucial component in serving transformer-based autoregressive large language models (LLMs), enabling faster inference by storing previously computed KV vectors. However, its memory consumption scales linearly…

Machine Learning · Computer Science 2024-10-07 Rongzhi Zhang , Kuang Wang , Liyuan Liu , Shuohang Wang , Hao Cheng , Chao Zhang , Yelong Shen

Speculative decoding and dynamic sparse attention are two complementary approaches for accelerating long-context LLM inference: the former amortizes target-model execution across multiple verifier queries, while the latter reduces each…

Operating Systems · Computer Science 2026-05-21 Zhibin Wang , Ziyu Zhong , Nuo Shen , Yuhang Zhou , Rong Gu , Sheng Zhong

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