English
Related papers

Related papers: DISTFLASHATTN: Distributed Memory-efficient Attent…

200 papers

A practical large language model (LLM) service may involve a long system prompt, which specifies the instructions, examples, and knowledge documents of the task and is reused across requests. However, the long system prompt causes…

Computation and Language · Computer Science 2024-05-31 Lei Zhu , Xinjiang Wang , Wayne Zhang , Rynson W. H. Lau

Training causal transformers at extreme sequence lengths is bottlenecked by the quadratic time and memory of scaled dot-product attention (SDPA). In this work, we propose Lighthouse Attention, a training-only symmetrical selection-based…

Computation and Language · Computer Science 2026-05-08 Bowen Peng , Subho Ghosh , Jeffrey Quesnelle

The quadratic computational complexity of standard attention mechanisms presents a severe scalability bottleneck for LLMs in long-context scenarios. While hybrid attention mechanisms combining Full Attention (FA) and Sparse Attention (SA)…

Machine Learning · Computer Science 2026-04-10 Quantong Qiu , Zhiyi Hong , Yi Yang , Haitian Wang , Kebin Liu , Qingqing Dang , Juntao Li , Min Zhang

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

The long-context capability of the Large Language Models (LLM) has made significant breakthroughs, but the maximum supported context length in length extrapolation remains a critical bottleneck limiting their practical applications. The…

Computation and Language · Computer Science 2025-03-20 Xiaoran Liu , Ruixiao Li , Qipeng Guo , Zhigeng Liu , Yuerong Song , Kai Lv , Hang Yan , Linlin Li , Qun Liu , Xipeng Qiu

Transformer-based large language models (LLMs) have achieved remarkable success, yet their standard attention mechanism incurs quadratic computation and memory costs with respect to sequence length, posing a major bottleneck for…

Machine Learning · Computer Science 2025-10-22 Tao Bu , Qiangang Wang , Bowen Zeng , Hanwen Sun , Yunpeng Huang , Chun Cao , Jingwei Xu

Diffusion Language Models (DLMs) enable globally coherent, bidirectional, and controllable text generation, offering advantages over traditional autoregressive LLMs, while scaling to ultra-long sequences remains costly. Many existing…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Wenhu Zhang , Yiming Wu , Huanyu Wang , Yaoyang Liu , Huanzhang Dou , Senqiao Yang , Sitong Wu , Hanbin Zhao , Jiaya Jia

Inference with Transformer-based Large Language Models (LLMs) on long sequences is both costly and slow due to the quadratic complexity of the self-attention mechanism. We introduce Star Attention, a two-phase block-sparse approximation…

Computation and Language · Computer Science 2025-06-02 Shantanu Acharya , Fei Jia , Boris Ginsburg

Optimizing deep learning algorithms currently requires slow, manual derivation, potentially leaving much performance untapped. Methods like FlashAttention have achieved a x6 performance improvement over native PyTorch by avoiding…

Machine Learning · Computer Science 2025-01-22 Vincent Abbott , Gioele Zardini

Large language models (LLMs) are proliferating rapidly at the edge, delivering intelligent capabilities across diverse application scenarios. However, their practical deployment in collaborative scenarios confronts fundamental challenges:…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-05 Xiumei Deng , Zehui Xiong , Binbin Chen , Dong In Kim , Merouane Debbah , H. Vincent Poor

This study introduces bifurcated attention, a method designed to enhance language model inference in shared-context batch decoding scenarios. Our approach addresses the challenge of redundant memory IO costs, a critical factor contributing…

As the foundation of large language models (LLMs), self-attention module faces the challenge of quadratic time and memory complexity with respect to sequence length. FlashAttention accelerates attention computation and reduces its memory…

Machine Learning · Computer Science 2024-09-27 Shimao Chen , Zirui Liu , Zhiying Wu , Ce Zheng , Peizhuang Cong , Zihan Jiang , Yuhan Wu , Lei Su , Tong Yang

We present an approximate attention mechanism named HyperAttention to address the computational challenges posed by the growing complexity of long contexts used in Large Language Models (LLMs). Recent work suggests that in the worst-case…

Machine Learning · Computer Science 2023-12-04 Insu Han , Rajesh Jayaram , Amin Karbasi , Vahab Mirrokni , David P. Woodruff , Amir Zandieh

Attention mechanisms, particularly within Transformer architectures and large language models (LLMs), have revolutionized sequence modeling in machine learning and artificial intelligence applications. To compute attention for increasingly…

Hardware Architecture · Computer Science 2025-06-02 Kosmas Alexandridis , Vasileios Titopoulos , Giorgos Dimitrakopoulos

Deploying Large Language Models (LLMs) on edge devices remains challenging due to their quadratically increasing computations with the sequence length. Existing studies for dynamic attention pruning are designed for hardware with massively…

Artificial Intelligence · Computer Science 2025-07-29 Jiawen Qi , Chang Gao , Zhaochun Ren , Qinyu Chen

Efficient inference on GPUs using large language models remains challenging due to memory bandwidth limitations, particularly during data transfers between High Bandwidth Memory (HBM) and SRAM in attention computations. Approximate…

Machine Learning · Computer Science 2025-06-06 Nirav Koley , Prajwal Singhania , Abhinav Bhatele

Diffusion transformers have achieved remarkable success in high-quality video generation, yet their reliance on spatiotemporal 3D full attention incurs prohibitive computational cost due to the quadratic complexity of attention. Block…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Jie Hu , Zixiang Gao , Yutong He , Kun Yuan

The transformer's attention mechanism has revolutionized AI and machine learning, with its efficient computation being crucial to its performance. However, calculating attention involves matrix operations interspersed with softmax…

Machine Learning · Computer Science 2025-05-21 Kosmas Alexandridis , Vasileios Titopoulos , Giorgos Dimitrakopoulos

Large vision-and-language models (LVLMs) have traditionally integrated visual and textual tokens by concatenating them into a single homogeneous input for large language models (LLMs), thereby maximally preserving the pre-trained language…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Chia-Wen Kuo , Sijie Zhu , Fan Chen , Xiaohui Shen , Longyin Wen

Training and serving long-context large language models (LLMs) incurs substantial overhead. To address this, two critical steps are often required: a pretrained LLM typically undergoes a separate stage for context length extension by…

Computation and Language · Computer Science 2024-12-06 Suyu Ge , Xihui Lin , Yunan Zhang , Jiawei Han , Hao Peng