English
Related papers

Related papers: S2-Attention: Hardware-Aware Context Sharding Amon…

200 papers

Transformers have achieved state-of-the-art performance across various tasks, but suffer from a notable quadratic complexity in sequence length due to the attention mechanism. In this work, we propose MonarchAttention -- a novel approach to…

Machine Learning · Computer Science 2025-10-28 Can Yaras , Alec S. Xu , Pierre Abillama , Changwoo Lee , Laura Balzano

Mainstream Transformer-based large language models face major efficiency bottlenecks: training computation scales quadratically with sequence length, and inference memory grows linearly, limiting long-context processing. Building large…

The use of Transformer represents a recent success in speech enhancement. However, as its core component, self-attention suffers from quadratic complexity, which is computationally prohibited for long speech recordings. Moreover, it allows…

Sound · Computer Science 2023-05-16 Qiquan Zhang , Hongxu Zhu , Qi Song , Xinyuan Qian , Zhaoheng Ni , Haizhou Li

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

Soft attention in Transformer-based Large Language Models (LLMs) is susceptible to incorporating irrelevant information from the context into its latent representations, which adversely affects next token generations. To help rectify these…

Computation and Language · Computer Science 2023-11-21 Jason Weston , Sainbayar Sukhbaatar

Transformer models rely heavily on the scaled dot-product attention (SDPA) operation, typically implemented as FlashAttention. Characterized by its frequent interleaving of matrix multiplications and softmax operations, FlashAttention fails…

Hardware Architecture · Computer Science 2025-12-09 Jiawei Lin , Yuanlong Li , Guokai Chen , Thomas Bourgeat

As large language models scale to longer contexts, loading the growing KV cache during attention computation becomes a critical bottleneck. Previous work has shown that attention computation is dominated by a small subset of tokens. This…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-13 Di Liu , Ruitian Wang , Chen Chen , Mingliang Gong , Yongjie Yuan , Han Zhao , Yu Feng , Quan Chen , Minyi Guo

Attention is the dominant source of latency during long-context LLM inference, an increasingly popular workload with reasoning models and RAG. We propose Kascade, a training-free sparse attention method that leverages known observations…

Machine Learning · Computer Science 2025-12-19 Dhruv Deshmukh , Saurabh Goyal , Nipun Kwatra , Ramachandran Ramjee

Attention mechanisms have become ubiquitous in NLP. Recent architectures, notably the Transformer, learn powerful context-aware word representations through layered, multi-headed attention. The multiple heads learn diverse types of word…

Computation and Language · Computer Science 2019-09-09 Gonçalo M. Correia , Vlad Niculae , André F. T. Martins

Transformers allow attention between all pairs of tokens, but there is reason to believe that most of these connections - and their quadratic time and memory - may not be necessary. But which ones? We evaluate the impact of sparsification…

Computation and Language · Computer Science 2022-10-11 Siddhartha Brahma , Polina Zablotskaia , David Mimno

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

Segment Anything Model 2 (SAM2) shows excellent performance in video object segmentation tasks; however, the heavy computational burden hinders its application in real-time video processing. Although there have been efforts to improve the…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Jing Zhang , Zhikai Li , Xuewen Liu , Qingyi Gu

Autoregressive (AR) large language models (LLMs) have achieved remarkable performance across a wide range of natural language tasks, yet their inherent sequential decoding limits inference efficiency. In this work, we propose Fast-dLLM v2,…

Computation and Language · Computer Science 2025-10-01 Chengyue Wu , Hao Zhang , Shuchen Xue , Shizhe Diao , Yonggan Fu , Zhijian Liu , Pavlo Molchanov , Ping Luo , Song Han , Enze Xie

Block-wise sparse attention offers significant efficiency gains for long-context modeling, yet existing methods often suffer from low selection fidelity and cumulative contextual loss by completely discarding unselected blocks. To address…

Computation and Language · Computer Science 2026-02-02 Bailin Wang , Dan Friedman , Tao Lei , Chong Wang

Large language models have shown remarkable performance across a wide range of language tasks, owing to their exceptional capabilities in context modeling. The most commonly used method of context modeling is full self-attention, as seen in…

Computation and Language · Computer Science 2025-06-26 Zhisong Zhang , Yan Wang , Xinting Huang , Tianqing Fang , Hongming Zhang , Chenlong Deng , Shuaiyi Li , Dong Yu

To help address the growing demand for ever-longer sequence lengths in transformer models, Liu et al. recently proposed Ring Attention, an exact attention algorithm capable of overcoming per-device memory bottle- necks by distributing…

Machine Learning · Computer Science 2023-11-17 William Brandon , Aniruddha Nrusimha , Kevin Qian , Zachary Ankner , Tian Jin , Zhiye Song , Jonathan Ragan-Kelley

Diffusion-based video generation has advanced substantially in visual fidelity and temporal coherence, but practical deployment remains limited by the quadratic complexity of full attention. Training-free sparse attention is attractive…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Xuzhe Zheng , Yuexiao Ma , Jing Xu , Xiawu Zheng , Rongrong Ji , Fei Chao

Diffusion Transformers dominate video generation, but the quadratic complexity of attention computation introduces substantial latency. Attention sparsity reduces computational costs by focusing on critical tokens while ignoring…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Xuewen Liu , Zhikai Li , Jing Zhang , Mengjuan Chen , Qingyi Gu

Large Language Models (LLMs) have dramatically advanced AI applications, yet their deployment remains challenging due to their immense inference costs. Recent studies ameliorate the computational costs of LLMs by increasing their activation…

Machine Learning · Computer Science 2024-11-05 Donghyun Lee , Je-Yong Lee , Genghan Zhang , Mo Tiwari , Azalia Mirhoseini

Efficient attention algorithms are critical to mitigate the quadratic cost of attention in long-context workloads. Prior work utilises block-scaled quantisation techniques on Blackwell GPUs to move attention computation to 4-bit precision…

Machine Learning · Computer Science 2026-05-25 Joe Sharratt