English
Related papers

Related papers: Star Attention: Efficient LLM Inference over Long …

200 papers

Due to the auto-regressive nature of current video large language models (Video-LLMs), the inference latency increases as the input sequence length grows, posing challenges for the efficient processing of video sequences that are usually…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Xuan Zhang , Cunxiao Du , Sicheng Yu , Jiawei Wu , Fengzhuo Zhang , Wei Gao , Qian Liu

The quadratic cost of attention limits the scalability of long-context LLMs, especially under limited hardware memory budgets. While attention is often sparse, existing static sparse methods cannot adapt to task- or input-dependent…

Computation and Language · Computer Science 2026-05-29 Siheng Xiong , Joe Zou , Faramarz Fekri , Yae Jee Cho

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

Large Language Models (LLMs) have emerged as a pivotal research area, yet the attention module remains a critical bottleneck in LLM inference, even with techniques like KVCache to mitigate redundant computations. While various top-$k$…

Transformer model with multi-head attention requires caching intermediate results for efficient inference in generation tasks. However, cache brings new memory-related costs and prevents leveraging larger batch size for faster speed. We…

Computation and Language · Computer Science 2021-06-15 Yu Yan , Jiusheng Chen , Weizhen Qi , Nikhil Bhendawade , Yeyun Gong , Nan Duan , Ruofei Zhang

Transformer-based models have become ubiquitous in natural language processing thanks to their large capacity, innate parallelism and high performance. The contextualizing component of a Transformer block is the $\textit{pairwise…

Machine Learning · Computer Science 2020-06-08 Ankit Gupta , Jonathan Berant

As large language models (LLMs) continue to support increasingly longer contexts, the memory demand for key-value (KV) caches during decoding grows rapidly, becoming a critical bottleneck in both GPU memory capacity and PCIe bandwidth.…

Machine Learning · Computer Science 2025-06-23 Feiyu Yao , Qian Wang

Large language models (LLMs) demonstrate strong capabilities across a wide range of complex tasks and are increasingly deployed at scale, placing significant demands on inference efficiency. Prior work typically decomposes inference into…

Computation and Language · Computer Science 2026-04-21 Junhao Hu , Fangze Li , Mingtao Xu , Feifan Meng , Shiju Zhao , Tiancheng Hu , Ting Peng , Anmin Liu , Wenrui Huang , Chenxu Liu , Ziyue Hua , Tao Xie

Long-context inference in large language models is bottlenecked by the quadratic cost of full attention. Existing efficient alternatives often rely either on native sparse training or on heuristic token eviction, creating an undesirable…

Computation and Language · Computer Science 2026-05-19 Yanke Zhou , Yiduo Li , Hanlin Tang , Maohua Li , Kan Liu , Lan Tao , Lin Qu , Yuan Yao , Xiaoxing Ma

As the length of input text increases, the key-value (KV) cache in LLMs imposes prohibitive GPU memory costs and limits long-context inference on resource constrained devices. Existing approaches, such as KV quantization and pruning, reduce…

Machine Learning · Computer Science 2025-12-24 Tenghui Li , Guoxu Zhou , Xuyang Zhao , Yuning Qiu , Qibin Zhao

Pretrained transformer models have demonstrated remarkable performance across various natural language processing tasks. These models leverage the attention mechanism to capture long- and short-range dependencies in the sequence. However,…

Computation and Language · Computer Science 2023-10-20 Qingru Zhang , Dhananjay Ram , Cole Hawkins , Sheng Zha , Tuo Zhao

The per-token cost of transformer inference scales with context length, preventing its application to lifelong in-context learning. Linear attention is an efficient alternative that maintains a constant memory footprint, even on infinite…

Computation and Language · Computer Science 2025-10-01 Luke McDermott , Robert W. Heath , Rahul Parhi

Large Vision-Language Models (VLMs) have achieved remarkable success in multi-modal reasoning, but their inference time efficiency remains a significant challenge due to the memory overhead during decoding, especially when the query and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Fatih Ilhan , Gaowen Liu , Ramana Rao Kompella , Selim Furkan Tekin , Tiansheng Huang , Zachary Yahn , Yichang Xu , Ling Liu

We describe an efficient hierarchical method to compute attention in the Transformer architecture. The proposed attention mechanism exploits a matrix structure similar to the Hierarchical Matrix (H-Matrix) developed by the numerical…

Machine Learning · Computer Science 2021-07-27 Zhenhai Zhu , Radu Soricut

Our formulation reveals that the reduction across the sequence axis can be efficiently computed in parallel through a tree reduction. Our algorithm, called Tree Attention, for parallelizing exact attention computation across multiple GPUs…

Machine Learning · Computer Science 2025-02-11 Vasudev Shyam , Jonathan Pilault , Emily Shepperd , Quentin Anthony , Beren Millidge

Large Language Models (LLMs) are increasingly deployed in long-context tasks such as reasoning, code generation, and multi-turn dialogue. However, inference over extended contexts is bottlenecked by the Key-Value (KV) cache, whose memory…

Computation and Language · Computer Science 2026-05-21 Seonghwan Choi , Beomseok Kang , Dongwon Jo , Jae-Joon Kim

Transformers are widely used across various applications, many of which yield sparse or partially filled attention matrices. Examples include attention masks designed to reduce the quadratic complexity of attention, sequence packing…

Machine Learning · Computer Science 2024-09-25 Agniv Sharma , Jonas Geiping

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

Transformers are mostly relying on softmax attention, which introduces quadratic complexity with respect to sequence length and remains a major bottleneck for efficient inference. Prior work on linear or hybrid attention typically replaces…

Vision-language models (VLMs) have shown remarkable success across various multi-modal tasks, yet large VLMs encounter significant efficiency challenges due to processing numerous visual tokens. A promising approach to accelerating large…

Computer Vision and Pattern Recognition · Computer Science 2024-12-06 Wangbo Zhao , Yizeng Han , Jiasheng Tang , Zhikai Li , Yibing Song , Kai Wang , Zhangyang Wang , Yang You