English
Related papers

Related papers: Sequence-Aware Split Heuristic to Mitigate SM Unde…

200 papers

Transformers have significantly advanced AI and machine learning through their powerful attention mechanism. However, computing attention on long sequences can become a computational bottleneck. FlashAttention mitigates this by fusing the…

Hardware Architecture · Computer Science 2026-02-10 Kosmas Alexandridis , Giorgos Dimitrakopoulos

Efficiently processing long sequences with Transformer models usually requires splitting the computations across accelerators via context parallelism. The dominant approaches in this family of methods, such as Ring Attention or DeepSpeed…

Machine Learning · Computer Science 2026-02-25 Ravi Ghadia , Maksim Abraham , Sergei Vorobyov , Max Ryabinin

Long-context inference increasingly operates over CPU-resident KV caches, either because decoding-time KV states exceed GPU memory capacity or because disaggregated prefill-decode systems place KV data in host memory. Although block-sparse…

Machine Learning · Computer Science 2026-05-11 Feiyu Yao , Zhixiong Niu , Xiaqing Li , Yongqiang Xiong , Juan Fang , Qian Wang

As large language models (LLMs) and visual language models (VLMs) grow in scale and application, attention mechanisms have become a central computational bottleneck due to their high memory and time complexity. While many efficient…

Machine Learning · Computer Science 2025-07-11 Zhengyu Tian , Anantha Padmanaban Krishna Kumar , Hemant Krishnakumar , Reza Rawassizadeh

The latest trends in high-performance computing systems show an increasing demand on the use of a large scale multicore systems in a efficient way, so that high compute-intensive applications can be executed reasonably well. However, the…

Distributed, Parallel, and Cluster Computing · Computer Science 2013-02-25 Juliana M. N. Silva , Cristina Boeres , Lúcia M. A. Drummond , Artur A. Pessoa

We propose an efficient batching strategy for variable-length decoding on GPU architectures. During decoding, when candidates terminate or are pruned according to heuristics, our streaming approach periodically "refills" the batch before…

Computation and Language · Computer Science 2021-08-17 Kevin Yang , Violet Yao , John DeNero , Dan Klein

Large language models (LLMs) are increasingly employed for complex tasks that process multiple generation calls in a tree structure with shared prefixes of tokens, including few-shot prompting, multi-step reasoning, speculative decoding,…

Computation and Language · Computer Science 2025-03-10 Jinwei Yao , Kaiqi Chen , Kexun Zhang , Jiaxuan You , Binhang Yuan , Zeke Wang , Tao Lin

Linear sequence modeling approaches, such as linear attention, provide advantages like linear-time training and constant-memory inference over sequence lengths. However, existing sequence parallelism (SP) methods are either not optimized…

Machine Learning · Computer Science 2025-02-12 Weigao Sun , Disen Lan , Yiran Zhong , Xiaoye Qu , Yu Cheng

Considering the spectral properties of images, we propose a new self-attention mechanism with highly reduced computational complexity, up to a linear rate. To better preserve edges while promoting similarity within objects, we propose…

Computer Vision and Pattern Recognition · Computer Science 2023-07-27 Fengyu Zhang , Ashkan Panahi , Guangjun Gao

Sequence alignment is a fundamental process in computational biology which identifies regions of similarity in biological sequences. With the exponential growth in the volume of data in bioinformatics databases, the time, processing power,…

Hardware Architecture · Computer Science 2025-07-31 Nasrin Akbari , Mehdi Modarressi , Alireza Khadem

Modern large language models increasingly require long contexts for reasoning and multi-document tasks, but attention's quadratic complexity creates a severe computational bottleneck. We present Block-Sparse FlashAttention (BSFA), a drop-in…

Machine Learning · Computer Science 2025-12-09 Daniel Ohayon , Itay Lamprecht , Itay Hubara , Israel Cohen , Daniel Soudry , Noam Elata

The efficiency of attention is important due to its quadratic time complexity. We enhance the efficiency of attention through two key contributions: First, we leverage the new FP4 Tensor Cores in Blackwell GPUs to accelerate attention…

Machine Learning · Computer Science 2026-01-16 Jintao Zhang , Jia Wei , Pengle Zhang , Xiaoming Xu , Haofeng Huang , Haoxu Wang , Kai Jiang , Jianfei Chen , Jun Zhu

Modern cloud servers routinely co-locate multiple latency-sensitive microservice instances to improve resource efficiency. However, the diversity of microservice behaviors, coupled with mutual performance interference under simultaneous…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-02 Dingyu Yang , Fanyong Kong , Jie Dai , Shiyou Qian , Shuangwei Li , Jian Cao , Guangtao Xue , Gang Chen

Attention based models have achieved many remarkable breakthroughs in numerous applications. However, the quadratic complexity of Attention makes the vanilla Attention based models hard to apply to long sequence tasks. Various improved…

Machine Learning · Computer Science 2024-09-18 Xue Wang , Tian Zhou , Jianqing Zhu , Jialin Liu , Kun Yuan , Tao Yao , Wotao Yin , Rong Jin , HanQin Cai

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

As LLMs scale to multi-million-token KV histories, real-time autoregressive decoding under tight Token-to-Token Latency (TTL) constraints faces growing pressure. Two core bottlenecks dominate: accessing Feed-Forward Network (FFN) weights…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-11 Nidhi Bhatia , Ankit More , Ritika Borkar , Tiyasa Mitra , Ramon Matas , Ritchie Zhao , Maximilian Golub , Dheevatsa Mudigere , Brian Pharris , Bita Darvish Rouhani

Vision Transformers have demonstrated exceptional performance across various computer vision tasks, yet their quadratic computational complexity concerning token length remains a significant challenge. To address this, token reduction…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Dong-Jae Lee , Jiwan Hur , Jaehyun Choi , Jaemyung Yu , Junmo Kim

Speculative decoding has emerged as a powerful method to improve latency and throughput in hosting large language models. However, most existing implementations focus on generating a single sequence. Real-world generative AI applications…

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

To address the high resolution of image pixels, the Swin Transformer introduces window attention. This mechanism divides an image into non-overlapping windows and restricts attention computation to within each window, significantly…

Computer Vision and Pattern Recognition · Computer Science 2025-01-15 Zhendong Zhang