English
Related papers

Related papers: FastAttention: Extend FlashAttention2 to NPUs and …

200 papers

We present Lightning Attention, the first linear attention implementation that maintains a constant training speed for various sequence lengths under fixed memory consumption. Due to the issue with cumulative summation operations (cumsum),…

Computation and Language · Computer Science 2024-06-21 Zhen Qin , Weigao Sun , Dong Li , Xuyang Shen , Weixuan Sun , Yiran Zhong

Attention is a fundamental building block of large language models (LLMs), so there have been many efforts to implement it efficiently. For example, FlashAttention leverages tiling and kernel fusion to optimize attention. Recently, a number…

The advent of foundation models have revolutionized various fields, enabling unprecedented task accuracy and flexibility in computational linguistics, computer vision and other domains. Attention mechanism has become an essential component…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-19 Mohammadali Shakerdargah , Shan Lu , Chao Gao , Di Niu

Processing long-context inputs with large language models presents a significant challenge due to the enormous memory requirements of the Key-Value (KV) cache during inference. Existing KV cache compression methods exhibit noticeable…

Computation and Language · Computer Science 2025-07-29 Dongquan Yang , Yifan Yang , Xiaotian Yu , Xianbiao Qi , Rong Xiao

Transformers and large language models (LLMs) have revolutionized machine learning, with attention mechanisms at the core of their success. As the landscape of attention variants expands, so too do the challenges of optimizing their…

Computation and Language · Computer Science 2025-02-24 Feiyang Chen , Yu Cheng , Lei Wang , Yuqing Xia , Ziming Miao , Lingxiao Ma , Fan Yang , Jilong Xue , Zhi Yang , Mao Yang , Haibo Chen

Transformer-based Large Language Models (LLMs) have become increasingly important. However, due to the quadratic time complexity of attention computation, scaling LLMs to longer contexts incurs extremely slow inference speed and high GPU…

The evolution of large language models (LLMs) towards applications with ultra-long contexts faces challenges posed by the high computational and memory costs of the Transformer architecture. While existing sparse and linear attention…

Large Language Models (LLMs) face efficiency bottlenecks due to the quadratic complexity of the attention mechanism when processing long contexts. Sparse attention methods offer a promising solution, but existing approaches often suffer…

Computation and Language · Computer Science 2025-03-06 Lida Chen , Dong Xu , Chenxin An , Xintao Wang , Yikai Zhang , Jiangjie Chen , Zujie Liang , Feng Wei , Jiaqing Liang , Yanghua Xiao , Wei Wang

Leveraging long contexts is crucial for advanced AI systems, but attention computation poses a scalability challenge. While scaled dot-product attention (SDPA) exhibits token sparsity, i.e. only a few pivotal tokens significantly contribute…

Machine Learning · Computer Science 2025-06-05 Aditya Desai , Shuo Yang , Alejandro Cuadron , Matei Zaharia , Joseph E. Gonzalez , Ion Stoica

The attention mechanism is the key to the success of transformers in different machine learning tasks. However, the quadratic complexity with respect to the sequence length of the vanilla softmax-based attention mechanism becomes the major…

Image and Video Processing · Electrical Eng. & Systems 2025-08-05 Chong Wu , Maolin Che , Renjie Xu , Zhuoheng Ran , Hong Yan

Distributed attention is a fundamental problem for scaling context window for Large Language Models (LLMs). The state-of-the-art method, Ring-Attention, suffers from scalability limitations due to its excessive communication traffic. This…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-25 Sirui Chen , Jingji Chen , Siqi Zhu , Ziheng Jiang , Yanghua Peng , Xuehai Qian

Mixture of Block Attention (MoBA) (Lu et al., 2025) is a promising building block for efficiently processing long contexts in LLMs by enabling queries to sparsely attend to a small subset of key-value blocks, drastically reducing…

Machine Learning · Computer Science 2025-12-22 Guangxuan Xiao , Junxian Guo , Kasra Mazaheri , Song Han

Transformer-based language models have found many diverse applications requiring them to process sequences of increasing length. For these applications, the causal self-attention -- which is the only component scaling quadratically w.r.t.…

Machine Learning · Computer Science 2023-06-05 Matteo Pagliardini , Daniele Paliotta , Martin Jaggi , François Fleuret

Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…

Machine Learning · Computer Science 2025-07-01 Venmugil Elango

Current high-resolution vision-language models encode images as high-resolution image tokens and exhaustively take all these tokens to compute attention, which significantly increases the computational cost. To address this problem, we…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Junyan Li , Delin Chen , Tianle Cai , Peihao Chen , Yining Hong , Zhenfang Chen , Yikang Shen , Chuang Gan

The quadratic computation complexity of self-attention has been a persistent challenge when applying Transformer models to vision tasks. Linear attention, on the other hand, offers a much more efficient alternative with its linear…

Computer Vision and Pattern Recognition · Computer Science 2023-09-04 Dongchen Han , Xuran Pan , Yizeng Han , Shiji Song , Gao Huang

Softmax Attention has a quadratic time complexity in sequence length, which becomes prohibitive to run at long contexts, even with highly optimized GPU kernels. For example, FlashAttention-2/3 (exact, GPU-optimized implementations of…

Machine Learning · Computer Science 2026-04-21 Sahil Joshi , Agniva Chowdhury , Amar Kanakamedala , Ekam Singh , Evan Tu , Anshumali Shrivastava

Diffusion transformer-based video generation models (DiTs) have recently attracted widespread attention for their excellent generation quality. However, their computational cost remains a major bottleneck-attention alone accounts for over…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Xuan Shen , Chenxia Han , Yufa Zhou , Yanyue Xie , Yifan Gong , Quanyi Wang , Yiwei Wang , Yanzhi Wang , Pu Zhao , Jiuxiang Gu

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

Transformers with linear attention allow for efficient parallel training but can simultaneously be formulated as an RNN with 2D (matrix-valued) hidden states, thus enjoying linear-time inference complexity. However, linear attention…

Machine Learning · Computer Science 2024-08-28 Songlin Yang , Bailin Wang , Yikang Shen , Rameswar Panda , Yoon Kim