English
Related papers

Related papers: IntAttention: A Fully Integer Attention Pipeline f…

200 papers

Attention, as a core layer of the ubiquitous Transformer architecture, is the bottleneck for large language models and long-context applications. While FlashAttention-3 optimized attention for Hopper GPUs through asynchronous execution and…

Computation and Language · Computer Science 2026-03-06 Ted Zadouri , Markus Hoehnerbach , Jay Shah , Timmy Liu , Vijay Thakkar , Tri Dao

Multi-Head Attention (MHA) is a critical computational kernel in transformer-based AI models. Emerging scalable tile-based accelerator architectures integrate increasing numbers of tightly-packed processing elements (PEs) with tensor units.…

Hardware Architecture · Computer Science 2025-05-27 Chi Zhang , Luca Colagrande , Renzo Andri , Thomas Benz , Gamze Islamoglu , Alessandro Nadalini , Francesco Conti , Yawei Li , Luca Benini

Attention, as a core layer of the ubiquitous Transformer architecture, is the bottleneck for large language models and long-context applications. FlashAttention elaborated an approach to speed up attention on GPUs through minimizing memory…

Machine Learning · Computer Science 2024-07-16 Jay Shah , Ganesh Bikshandi , Ying Zhang , Vijay Thakkar , Pradeep Ramani , Tri Dao

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

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

As the performance gains from accelerating quantized matrix multiplication plateau, the softmax operation becomes the critical bottleneck in Transformer inference. This bottleneck stems from two hardware limitations: (1) limited data…

Machine Learning · Computer Science 2026-02-03 Zisheng Ye , Xiaoyu He , Maoyuan Song , Guoliang Qiu , Chao Liao , Chen Wu , Yonggang Sun , Zhichun Li , Xiaoru Xie , Yuanyong Luo , Hu Liu , Pinyan Lu , Heng Liao

Transformers are slow and memory-hungry on long sequences, since the time and memory complexity of self-attention are quadratic in sequence length. Approximate attention methods have attempted to address this problem by trading off model…

Machine Learning · Computer Science 2022-06-24 Tri Dao , Daniel Y. Fu , Stefano Ermon , Atri Rudra , Christopher Ré

Vision transformers (ViTs) have pushed the state-of-the-art for various visual recognition tasks by patch-wise image tokenization followed by self-attention. However, the employment of self-attention modules results in a quadratic…

Computer Vision and Pattern Recognition · Computer Science 2022-05-03 Jiachen Lu , Jinghan Yao , Junge Zhang , Xiatian Zhu , Hang Xu , Weiguo Gao , Chunjing Xu , Tao Xiang , Li Zhang

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

Attention for transformers is a critical workload that has recently received significant "attention" as a target for custom acceleration. Yet, while prior work succeeds in reducing attention's memory-bandwidth requirements, it creates load…

Hardware Architecture · Computer Science 2026-01-28 Nandeeka Nayak , Xinrui Wu , Toluwanimi O. Odemuyiwa , Michael Pellauer , Joel S. Emer , Christopher W. Fletcher

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…

The attention module is the key component in Transformers. While the global attention mechanism offers high expressiveness, its excessive computational cost restricts its applicability in various scenarios. In this paper, we propose a novel…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Dongchen Han , Tianzhu Ye , Yizeng Han , Zhuofan Xia , Siyuan Pan , Pengfei Wan , Shiji Song , Gao Huang

Softmax can become a computational bottleneck in the Transformer model's Multi-Head Attention (MHA) block, particularly in small models under low-precision inference, where exponentiation and normalization incur significant overhead. As…

Machine Learning · Computer Science 2026-04-03 Dimitrios Danopoulos , Enrico Lupi , Michael Kagan , Maurizio Pierini

Edge devices increasingly run multimodal sensing pipelines that must remain accurate despite fluctuating power budgets and unpredictable sensor dropout. Existing pruning methods fail under these conditions: they generally require…

Machine Learning · Computer Science 2026-04-13 Yueyuan Sui , Payal Mohapatra , Doğaç Eldenk , Haodong Yang , Yiting Zhang , Haoyan Zhang , Qi Zhu , Stephen Xia

The attention mechanism is the computational core of modern Transformer architectures, but its quadratic complexity in the input sequence length is the bottleneck for large-scale inference. This has motivated a rapidly growing body of work…

VRAM requirements for transformer models scale quadratically with context length due to the self-attention mechanism. In this paper we modify the decoder-only transformer, replacing self-attention with InAttention, which scales linearly…

Machine Learning · Computer Science 2024-10-10 Joseph Eisner

Backpropagation has been the cornerstone of neural network training for decades, yet its inefficiencies in time and energy consumption limit its suitability for resource-constrained edge devices. While low-precision neural network…

Machine Learning · Computer Science 2025-07-01 Jingxiao Ma , Priyadarshini Panda , Sherief Reda

The original softmax-based attention mechanism (regular attention) in the extremely successful Transformer architecture computes attention between $N$ tokens, each embedded in a $D$-dimensional head, with a time complexity of $O(N^2D)$.…

Machine Learning · Computer Science 2025-10-28 Armin Gerami , Ramani Duraiswami

Diffusion Transformers, particularly for video generation, achieve remarkable quality but suffer from quadratic attention complexity, leading to prohibitive latency. Existing acceleration methods face a fundamental trade-off: dynamically…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Dor Shmilovich , Tony Wu , Aviad Dahan , Yuval Domb

Transformers have achieved widespread and remarkable success, while the computational complexity of their attention modules remains a major bottleneck for vision tasks. Existing methods mainly employ 8-bit or 4-bit quantization to balance…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Chaodong Xiao , Zhengqiang Zhang , Lei Zhang