English
Related papers

Related papers: Block Sparse Flash Attention

200 papers

The computational cost of softmax-based attention in transformers limits their applicability to long-context tasks. Adaptive sparsity, of which $\alpha$-entmax attention is an example, offers a flexible data-dependent alternative, but…

Computation and Language · Computer Science 2025-06-10 Nuno Gonçalves , Marcos Treviso , André F. T. Martins

Despite the success of Transformers, handling long contexts remains challenging due to the limited length generalization and quadratic complexity of self-attention. Thus Transformers often require post-training with a larger attention…

Computation and Language · Computer Science 2025-06-13 Xiang Hu , Zhihao Teng , Jun Zhao , Wei Wu , Kewei Tu

We present core attention disaggregation (CAD), a technique that improves long-context large language model training by decoupling the core attention computation, softmax(QK^T)V, from the rest of the model and executing it on a separate…

Machine Learning · Computer Science 2025-10-22 Yonghao Zhuang , Junda Chen , Bo Pang , Yi Gu , Yibo Zhu , Yimin Jiang , Ion Stoica , Eric Xing , Hao Zhang

The proliferation of long-context large language models (LLMs) exposes a key bottleneck: the rapidly expanding key-value cache during decoding, which imposes heavy memory and latency costs. While recent approaches attempt to alleviate this…

Computation and Language · Computer Science 2026-02-05 Gang Lin , Dongfang Li , Zhuoen Chen , Yukun Shi , Xuhui Chen , Baotian Hu , Min Zhang

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

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 architectures have advanced text summarization, yet their quadratic complexity limits scalability on long documents. This paper introduces BiSparse-AAS (Bilinear Sparse Attention with Adaptive Spans), a novel framework…

Computation and Language · Computer Science 2025-11-03 Desta Haileselassie Hagos , Legand L. Burge , Anietie Andy , Anis Yazidi , Vladimir Vlassov

The computational burden of attention in long-context language models has motivated two largely independent lines of work: sparse attention mechanisms that reduce complexity by attending to selected tokens, and gated attention variants that…

Artificial Intelligence · Computer Science 2026-01-23 Alfred Shen , Aaron Shen

Learning semantic correspondence between image and text is significant as it bridges the semantic gap between vision and language. The key challenge is to accurately find and correlate shared semantics in image and text. Most existing…

Multimedia · Computer Science 2019-09-26 Chunxiao Liu , Zhendong Mao , An-An Liu , Tianzhu Zhang , Bin Wang , Yongdong Zhang

Attention, specifically scaled dot-product attention, has proven effective for natural language, but it does not have a mechanism for handling hierarchical patterns of arbitrary nesting depth, which limits its ability to recognize certain…

Computation and Language · Computer Science 2024-01-25 Brian DuSell , David Chiang

Attention is the cornerstone of modern Large Language Models (LLMs). Yet its quadratic complexity hinders efficiency and scalability, especially for long-context processing. A promising approach is to leverage sparsity in attention.…

Computation and Language · Computer Science 2025-02-18 Yizhao Gao , Zhichen Zeng , Dayou Du , Shijie Cao , Peiyuan Zhou , Jiaxing Qi , Junjie Lai , Hayden Kwok-Hay So , Ting Cao , Fan Yang , Mao Yang

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

Many-shot in-context learning has recently shown promise as an alternative to finetuning, with the major advantage that the same model can be served for multiple tasks. However, this shifts the computational burden from training-time to…

Computation and Language · Computer Science 2025-03-19 Emily Xiao , Chin-Jou Li , Yilin Zhang , Graham Neubig , Amanda Bertsch

Recently Transformers have provided state-of-the-art performance in sparse matching, crucial to realize high-performance 3D vision applications. Yet, these Transformers lack efficiency due to the quadratic computational complexity of their…

Computer Vision and Pattern Recognition · Computer Science 2022-04-25 Suwichaya Suwanwimolkul , Satoshi Komorita

In video and image generation tasks, Diffusion Transformer (DiT) models incur extremely high computational costs due to attention mechanisms, which limits their practical applications. Furthermore, with hardware advancements, a wide range…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Aiyue Chen , Yaofu Liu , Junjian Huang , Guang Lian , Yiwu Yao , Wangli Lan , Jing Lin , Zhixin Ma , Tingting Zhou

Attention mechanisms underpin modern deep learning, while the quadratic time and space complexity limit scalability for long sequences. To address this, Quantum Annealing Multi-Head Attention (QAMA) is proposed, a novel drop-in operator…

Quantum Physics · Physics 2025-10-14 Peng Du , Jinjing Shi , Wenxuan Wang , Yin Ma , Kai Wen , Xuelong Li

DeepSeek Sparse Attention (DSA) sets the state of the art for fine-grained inference-time sparse attention by introducing a learned token-wise indexer that scores every prefix token and selects the most relevant ones for the main attention.…

Machine Learning · Computer Science 2026-05-11 Ruijie Zhou , Fanxu Meng , Yufei Xu , Tongxuan Liu , Guangming Lu , Muhan Zhang , Wenjie Pei

Long-context inference in LLMs faces the dual challenges of quadratic attention complexity and prohibitive KV cache memory. While token-level sparse attention offers superior accuracy, its indexing overhead is costly; block-level methods…

Computation and Language · Computer Science 2026-04-10 Yuxuan Hu , Jianchao Tan , Jiaqi Zhang , Wen Zan , Pingwei Sun , Yifan Lu , Yerui Sun , Yuchen Xie , Xunliang Cai , Jing Zhang

The quadratic computational complexity of the attention mechanism in current Large Language Models (LLMs) renders inference with long contexts prohibitively expensive. To address this challenge, various approaches aim to retain critical…

Computation and Language · Computer Science 2024-12-09 Hongyin Tang , Di Xiu , Lanrui Wang , Xiurui Geng , Jingang Wang , Xunliang Cai

Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces noisy probability distribution, which can impair effective…

Computation and Language · Computer Science 2025-11-11 Dhananjay Ram , Wei Xia , Stefano Soatto