English
Related papers

Related papers: Inference Time Context Sparsity: Illusion or Oppor…

200 papers

Large language models (LLMs) face significant challenges in processing long contexts due to the linear growth of the key-value (KV) cache and quadratic complexity of self-attention. Existing approaches address these bottlenecks separately:…

Computation and Language · Computer Science 2026-04-17 Zeng You , Yaofo Chen , Qiuwu Chen , Ying Sun , Shuhai Zhang , Yingjian Li , Yaowei Wang , Mingkui Tan

In this paper, we demonstrate that an inherent waveform pattern in the attention allocation of large language models (LLMs) significantly affects their performance in tasks demanding a high degree of context awareness, such as utilizing…

Computation and Language · Computer Science 2024-06-05 Yuhan Chen , Ang Lv , Ting-En Lin , Changyu Chen , Yuchuan Wu , Fei Huang , Yongbin Li , Rui Yan

The quadratic complexity of standard attention mechanisms poses a significant scalability bottleneck for large language models (LLMs) in long-context scenarios. While hybrid attention strategies that combine sparse and full attention within…

Computation and Language · Computer Science 2026-01-29 Zecheng Tang , Quantong Qiu , Yi Yang , Zhiyi Hong , Haiya Xiang , Kebin Liu , Qingqing Dang , Juntao Li , Min Zhang

Processing long contexts has become a critical capability for modern large language models (LLMs). However, serving long-context LLMs comes with significant inference costs due to the high memory overhead of the key-value (KV) cache.…

Machine Learning · Computer Science 2025-03-04 Qihui Zhou , Peiqi Yin , Pengfei Zuo , James Cheng

Recent breakthroughs in solving reasoning, math and coding problems with Large Language Models (LLMs) have been enabled by investing substantial computation budgets at inference time. Therefore, inference speed is one of the most critical…

Recent advancements in language models (LMs) have gained substantial attentions on their capability to generate human-like responses. Though exhibiting a promising future for various applications such as conversation AI, these LMs face…

Machine Learning · Computer Science 2023-09-14 Yufei Li , Zexin Li , Wei Yang , Cong Liu

Recent advance in sparse attention mechanisms has demonstrated strong potential for reducing the computational cost of long-context training and inference in large language models (LLMs). Native Sparse Attention (NSA), one state-of-the-art…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-14 Ran Yan , Youhe Jiang , Zhuoming Chen , Haohui Mai , Beidi Chen , Binhang Yuan

Large language models (LLMs) have emerged as a cornerstone in real-world applications with lengthy streaming inputs (e.g., LLM-driven agents). However, existing LLMs, pre-trained on sequences with a restricted maximum length, cannot process…

Computation and Language · Computer Science 2024-05-29 Chaojun Xiao , Pengle Zhang , Xu Han , Guangxuan Xiao , Yankai Lin , Zhengyan Zhang , Zhiyuan Liu , Maosong Sun

Large Language Models (LLMs) have demonstrated remarkable performance across various tasks. However, they are prone to contextual hallucination, generating information that is either unsubstantiated or contradictory to the given context.…

Computation and Language · Computer Science 2025-04-29 Siyi Liu , Kishaloy Halder , Zheng Qi , Wei Xiao , Nikolaos Pappas , Phu Mon Htut , Neha Anna John , Yassine Benajiba , Dan Roth

Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs that…

With the rising popularity of Transformer-based large language models (LLMs), reducing their high inference costs has become a significant research focus. One effective approach is to compress the long input contexts. Existing methods…

Computation and Language · Computer Science 2024-11-06 Xiangfeng Wang , Zaiyi Chen , Zheyong Xie , Tong Xu , Yongyi He , Enhong Chen

As the context limits of Large Language Models (LLMs) increase, the range of possible applications and downstream functions broadens. In many real-world tasks, decisions depend on details scattered across collections of often disparate…

Computation and Language · Computer Science 2025-04-24 Jonathan Roberts , Kai Han , Samuel Albanie

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

Long-context inference in LLMs faces the dual challenges of quadratic attention complexity and prohibitive KV cache memory. While token-level sparse attention offers superior accuracy, its indexing overhead is costly; block-level methods…

Computation and Language · Computer Science 2026-04-10 Yuxuan Hu , Jianchao Tan , Jiaqi Zhang , Wen Zan , Pingwei Sun , Yifan Lu , Yerui Sun , Yuchen Xie , Xunliang Cai , Jing Zhang

With the wide adoption of language models for IR -- and specifically RAG systems -- the latency of the underlying LLM becomes a crucial bottleneck, since the long contexts of retrieved passages lead large prompts and therefore, compute…

Information Retrieval · Computer Science 2026-04-06 Cornelius Kummer , Lena Jurkschat , Michael Färber , Sahar Vahdati

When deploying deep learning models to a device, it is traditionally assumed that available computational resources (compute, memory, and power) remain static. However, real-world computing systems do not always provide stable resource…

Machine Learning · Computer Science 2021-10-11 Elvis Nunez , Maxwell Horton , Anish Prabhu , Anurag Ranjan , Ali Farhadi , Mohammad Rastegari

Data centers capable of running large language models (LLMs) are spread across the globe. Some have high end GPUs for running the most advanced models (100B+ parameters), and others are only suitable for smaller models (1B parameters). The…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-24 Noah Martin , Fahad Dogar

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

Limited by the context window size of Large Language Models(LLMs), handling various tasks with input tokens exceeding the upper limit has been challenging, whether it is a simple direct retrieval task or a complex multi-hop reasoning task.…

Computation and Language · Computer Science 2025-02-19 Xiaoju Ye , Zhichun Wang , Jingyuan Wang

The evolution of Large Language Models from the Transformer architecture to models with trillions of parameters has shifted the primary bottleneck from model training to real time inference. Deploying these massive models is a complex…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-12 Madabattula Rajesh Kumar , Srinivasa Rao Aravilli , Mustafa Saify , Shashank Srivastava