English
Related papers

Related papers: UNIQUE: Universal Top-k Sparse Attention for Train…

200 papers

In large-scale recommender systems, ultra-long user behavior sequences encode rich signals of evolving interests. Extending sequence length generally improves accuracy, but directly modeling such sequences in production is infeasible due to…

Information Retrieval · Computer Science 2025-08-26 Kaiyuan Li , Yongxiang Tang , Yanhua Cheng , Yong Bai , Yanxiang Zeng , Chao Wang , Xialong Liu , Peng Jiang

Autoregressive decoding in large language models (LLMs) requires caching a growing list of past key-value (KV) pairs, making long-context inference a memory-bound problem. While recent methods have explored quantizing the cache, evicting…

Computation and Language · Computer Science 2025-10-08 Harshil Vejendla

With the rapid development of large language models (LLMs), handling long context has become one of the vital abilities in LLMs. Such long-context ability is accompanied by difficulties in deployment, especially due to the increased…

Computation and Language · Computer Science 2025-08-19 Zhuorui Liu , Chen Zhang , Dawei Song

Large Language Models capable of handling extended contexts are in high demand, yet their inference remains challenging due to substantial Key-Value cache size and high memory bandwidth requirements. Previous research has demonstrated that…

Machine Learning · Computer Science 2025-10-29 Junlin Mu , Hantao Huang , Jihang Zhang , Minghui Yu , Tao Wang , Yidong Li

The key-value (KV) cache is a foundational optimization in Transformer-based large language models (LLMs), eliminating redundant recomputation of past token representations during autoregressive generation. However, its memory footprint…

Machine Learning · Computer Science 2026-03-24 Yichun Xu , Navjot K. Khaira , Tejinder Singh

Large language models (LLMs) with extended context windows enable powerful downstream applications but impose significant memory overhead, as caching all key-value (KV) states scales linearly with sequence length and batch size. Existing…

Computation and Language · Computer Science 2025-10-10 Yuzhe Gu , Xiyu Liang , Jiaojiao Zhao , Enmao Diao

The Segment Anything Model (SAM) achieves strong open-vocabulary segmentation, but its ViT-based image encoders dominate inference latency and memory. Existing activation compression methods, such as token merging, reduce the token length…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Hoai-Chau Tran , Chi H. Nguyen , Duy M. H. Nguyen , Mathias Niepert , Fan Lai , Khoa D. Doan

Deploying Large Language Models (LLMs) on edge devices remains challenging due to their quadratically increasing computations with the sequence length. Existing studies for dynamic attention pruning are designed for hardware with massively…

Artificial Intelligence · Computer Science 2025-07-29 Jiawen Qi , Chang Gao , Zhaochun Ren , Qinyu Chen

The quadratic computational complexity of self-attention remains a fundamental bottleneck for scaling Large Language Models (LLMs) to long contexts, particularly during the pre-filling phase. In this paper, we rethink the causal attention…

Machine Learning · Computer Science 2026-03-09 Lin Niu , Xin Luo , Linchuan Xie , Yifu Sun , Guanghua Yu , Jianchen Zhu , S Kevin Zhou

Scaling inference for large language models (LLMs) is increasingly constrained by limited GPU memory, especially due to growing key-value (KV) caches required for long-context generation. While existing approaches offload KV caches to CPU…

Machine Learning · Computer Science 2025-07-08 Weishu Deng , Yujie Yang , Peiran Du , Lingfeng Xiang , Zhen Lin , Chen Zhong , Song Jiang , Hui Lu , Jia Rao

The Key-Value (KV) cache is the primary memory bottleneck in long-context Large Language Models, yet it is typically treated as an opaque numerical tensor. In this work, we propose \textbf{STA-Attention}, a framework that utilizes Top-K…

Machine Learning · Computer Science 2025-12-12 Qingsen Ma , Dianyun Wang , Jiaming Lyu , Yaoye Wang , Lechen Ning , Sujie Zhu , Zhenbo Xu , Liuyu Xiang , Huining Li , Huijia Wu , Zhaofeng He

Effectively processing long contexts is a critical challenge for language models. While standard Transformers are limited by quadratic complexity and poor length extrapolation, alternative architectures like sliding window attention and…

Computation and Language · Computer Science 2026-05-01 Jiaqi Leng , Xiang Hu , Junxiong Wang , Jianguo Li , Wei Wu , Yucheng Lu

While sparse attention mitigates the computational bottleneck of long-context LLM training, its distributed training process exhibits extreme heterogeneity in both \textit{1)} sequence length and \textit{2)} sparsity sensitivity, leading to…

Machine Learning · Computer Science 2026-04-27 Hongtao Xu , Jianchao Tan , Yuxuan Hu , Pengju Lu , Hongyu Wang , Pingwei Sun , Yerui Sun , Yuchen Xie , Xunliang Cai , Mingzhen Li , Weile Jia

Large language models (LLMs) encounter computational challenges during long-sequence inference, especially in the attention pre-filling phase, where the complexity grows quadratically with the prompt length. Previous efforts to mitigate…

Machine Learning · Computer Science 2025-03-03 Xunhao Lai , Jianqiao Lu , Yao Luo , Yiyuan Ma , Xun Zhou

Large Language Models (LLMs) excel across a variety of language tasks yet are constrained by limited input lengths and high computational costs. Existing approaches\textemdash such as relative positional encodings (e.g., RoPE, ALiBi) and…

Computation and Language · Computer Science 2025-02-18 Kun-Hui Lee , Eunhwan Park , Donghoon Han , Seung-Hoon Na

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

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

Diffusion Transformers (DiTs) set the state of the art in visual generation, yet their quadratic self-attention cost fundamentally limits scaling to long token sequences. Recent Top-K sparse attention approaches reduce the computation of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-19 Yifan Zhou , Zeqi Xiao , Tianyi Wei , Shuai Yang , Xingang Pan

Block-wise diffusion language models (DLMs) generate multiple tokens in any order, offering a promising alternative to the autoregressive decoding pipeline. However, they still remain bottlenecked by memory-bound attention in long-context…

In Large Language Model (LLM) inference, Key-Value (KV) caches (KV-caches) are essential for reducing time complexity. However, they result in a linear increase in GPU memory as the context length grows. While recent work explores KV-cache…

Machine Learning · Computer Science 2025-02-25 Ahmed Burak Gulhan , Krishna Teja Chitty-Venkata , Murali Emani , Mahmut Kandemir , Venkatram Vishwanath