English
Related papers

Related papers: Token Sparse Attention: Efficient Long-Context Inf…

200 papers

Large reasoning models (LRMs) achieve state-of-the-art performance on challenging benchmarks by generating long chains of intermediate steps, but their inference cost is dominated by decoding, where each new token must attend to the entire…

Computation and Language · Computer Science 2026-05-05 Hossein Entezari Zarch , Lei Gao , Chaoyi Jiang , Murali Annavaram

Scaling Transformers to ultra-long contexts is bottlenecked by the $O(n^2 d)$ cost of self-attention. Existing methods reduce this cost along the sequence axis through local windows, kernel approximations, or token-level sparsity, but these…

Machine Learning · Computer Science 2026-03-31 Yan Xie , Tiansheng Wen , Tangda Huang , Bo Chen , Chenyu You , Stefanie Jegelka , Yifei Wang

Long-context LLMs increasingly rely on extended, reusable prefill prompts for agents and domain Q&A, pushing attention and KV-cache to become the dominant decode-time bottlenecks. While sparse attention reduces computation and transfer…

Machine Learning · Computer Science 2026-04-13 Chuxu Song , Zhencan Peng , Jiuqi Wei , Chuanhui Yang

Inference on large language models (LLMs) can be expensive in terms of the compute and memory costs involved, especially when long sequence lengths are used. In particular, the self-attention mechanism used in LLM inference contributes…

Machine Learning · Computer Science 2024-11-11 Prajwal Singhania , Siddharth Singh , Shwai He , Soheil Feizi , Abhinav Bhatele

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

As Large Language Models (LLMs) scale to million-token contexts, traditional Mechanistic Interpretability techniques for analyzing attention scale quadratically with context length, demanding terabytes of memory beyond 100,000 tokens. We…

Computation and Language · Computer Science 2026-02-03 J Rosser , José Luis Redondo García , Gustavo Penha , Konstantina Palla , Hugues Bouchard

The quadratic computational complexity of the standard attention mechanism constitutes a fundamental bottleneck for large language models in long-context inference. While existing KV cache compression methods alleviate memory pressure, they…

Computation and Language · Computer Science 2026-05-06 Jinyu Guo , Zhihan Zhang , Jiehui Xie , Md. Tamim Iqbal , Dongshen Han , Lik-Hang Lee , Sung-Ho Bae , Jie Zou , Yang Yang , Chaoning Zhang

Transformer has achieved great success in NLP. However, the quadratic complexity of the self-attention mechanism in Transformer makes it inefficient in handling long sequences. Many existing works explore to accelerate Transformers by…

Computation and Language · Computer Science 2021-09-03 Chuhan Wu , Fangzhao Wu , Tao Qi , Binxing Jiao , Daxin Jiang , Yongfeng Huang , Xing Xie

Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of…

Computation and Language · Computer Science 2019-12-30 Guangxiang Zhao , Junyang Lin , Zhiyuan Zhang , Xuancheng Ren , Qi Su , Xu Sun

Long-context agentic workflows have emerged as a defining use case for large language models, making attention efficiency critical for both inference speed and serving cost. Sparse attention addresses this challenge effectively, and…

Computation and Language · Computer Science 2026-03-13 Yushi Bai , Qian Dong , Ting Jiang , Xin Lv , Zhengxiao Du , Aohan Zeng , Jie Tang , Juanzi Li

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide array of text-centric tasks. However, their `large' scale introduces significant computational and storage challenges, particularly in…

Computation and Language · Computer Science 2024-07-03 Chaoran Zhang , Lixin Zou , Dan Luo , Min Tang , Xiangyang Luo , Zihao Li , Chenliang Li

Vision Transformers (ViT) have shown their competitive advantages performance-wise compared to convolutional neural networks (CNNs) though they often come with high computational costs. To this end, previous methods explore different…

Computer Vision and Pattern Recognition · Computer Science 2023-03-27 Cong Wei , Brendan Duke , Ruowei Jiang , Parham Aarabi , Graham W. Taylor , Florian Shkurti

We propose Sparse Sinkhorn Attention, a new efficient and sparse method for learning to attend. Our method is based on differentiable sorting of internal representations. Concretely, we introduce a meta sorting network that learns to…

Machine Learning · Computer Science 2020-02-27 Yi Tay , Dara Bahri , Liu Yang , Donald Metzler , Da-Cheng Juan

Large language models (LLMs) have shown remarkable potential in processing long sequences and complex reasoning tasks, yet efficiently serving these models remains challenging due to the quadratic computational complexity of attention in…

Computation and Language · Computer Science 2025-04-22 Shang Yang , Junxian Guo , Haotian Tang , Qinghao Hu , Guangxuan Xiao , Jiaming Tang , Yujun Lin , Zhijian Liu , Yao Lu , Song Han

Structured dilated attention has an appealing inference-time efficiency knob: it reduces the FLOPs of attention and the KV cache size by a factor of the dilation size D, while preserving long-range connectivity. While prior work studies it…

Machine Learning · Computer Science 2026-05-29 Xiuying Wei , Caglar Gulcehre

Sparse Attention is a technique that approximates standard attention computation with sub-quadratic complexity. This is achieved by selectively ignoring smaller entries in the attention matrix during the softmax function computation.…

Machine Learning · Computer Science 2025-02-13 Yichuan Deng , Zhao Song , Jing Xiong , Chiwun Yang

Leveraging attention sparsity to accelerate long-context large language models (LLMs) has been a hot research topic. However, current algorithms such as sparse attention or key-value (KV) cache compression tend to use a fixed budget, which…

Machine Learning · Computer Science 2025-11-05 Chaofan Lin , Jiaming Tang , Shuo Yang , Hanshuo Wang , Tian Tang , Boyu Tian , Ion Stoica , Song Han , Mingyu Gao

The computational challenges of Large Language Model (LLM) inference remain a significant barrier to their widespread deployment, especially as prompt lengths continue to increase. Due to the quadratic complexity of the attention…

Large Language Models (LLMs) incur quadratic attention complexity with input length, creating a major time bottleneck in the prefilling stage. Existing acceleration methods largely exploit attention score sparsity by estimating blocks with…

Computation and Language · Computer Science 2026-04-22 Zhiyuan He , Yike Zhang , Chengruidong Zhang , Huiqiang Jiang , Yuqing Yang , Lili Qiu

We present Top-Theta (Top-$\theta$) Attention, a training-free method for sparsifying transformer attention during inference. Our key insight is that static, per-head thresholds can be calibrated to retain the desired constant number of…

Computation and Language · Computer Science 2025-08-25 Konstantin Berestizshevsky , Renzo Andri , Lukas Cavigelli