English
Related papers

Related papers: FlashAttention-2: Faster Attention with Better Par…

200 papers

Real-time video generation with Diffusion Transformers is bottlenecked by the quadratic cost of 3D self-attention, especially in real-time regimes that are both few-step and autoregressive, where errors compound across time and each…

Computer Vision and Pattern Recognition · Computer Science 2026-02-13 Krish Agarwal , Zhuoming Chen , Cheng Luo , Yongqi Chen , Haizhong Zheng , Xun Huang , Atri Rudra , Beidi Chen

In sequence to sequence learning, the self-attention mechanism proves to be highly effective, and achieves significant improvements in many tasks. However, the self-attention mechanism is not without its own flaws. Although self-attention…

Computation and Language · Computer Science 2019-11-22 Guangxiang Zhao , Xu Sun , Jingjing Xu , Zhiyuan Zhang , Liangchen Luo

Transformer-based architectures have become the prevailing backbone of large language models. However, the quadratic time and memory complexity of self-attention remains a fundamental obstacle to efficient long-context modeling. To address…

Computation and Language · Computer Science 2026-02-10 Yutao Sun , Zhenyu Li , Yike Zhang , Tengyu Pan , Bowen Dong , Yuyi Guo , Jianyong Wang

Large Language Models struggle with memory demands from the growing Key-Value (KV) cache as context lengths increase. Existing compression methods homogenize head dimensions or rely on attention-guided token pruning, often sacrificing…

Computation and Language · Computer Science 2025-06-16 Xiaoran Liu , Siyang He , Qiqi Wang , Ruixiao Li , Yuerong Song , Zhigeng Liu , Linlin Li , Qun Liu , Zengfeng Huang , Qipeng Guo , Ziwei He , Xipeng Qiu

Deep autoregressive sequence-to-sequence models have demonstrated impressive performance across a wide variety of tasks in recent years. While common architecture classes such as recurrent, convolutional, and self-attention networks make…

Machine Learning · Computer Science 2018-11-09 Mitchell Stern , Noam Shazeer , Jakob Uszkoreit

Together with the improvements in state-of-the-art accuracies of various tasks, deep learning models are getting significantly larger. However, it is extremely difficult to implement these large models because limited GPU memory makes it…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-09-02 Boxiang Wang , Qifan Xu , Zhengda Bian , Yang You

Attention is a fundamental building block of large language models (LLMs), so there have been many efforts to implement it efficiently. For example, FlashAttention leverages tiling and kernel fusion to optimize attention. Recently, a number…

As software projects rapidly evolve, software artifacts become more complex and defects behind get harder to identify. The emerging Transformer-based approaches, though achieving remarkable performance, struggle with long code sequences due…

Software Engineering · Computer Science 2024-09-13 Xueqi Yang , Mariusz Jakubowski , Li Kang , Haojie Yu , Tim Menzies

The computational difficulties of large language model (LLM) inference remain a significant obstacle to their widespread deployment. The need for many applications to support long input sequences and process them in large batches typically…

Machine Learning · Computer Science 2024-09-05 Luka Ribar , Ivan Chelombiev , Luke Hudlass-Galley , Charlie Blake , Carlo Luschi , Douglas Orr

Large deep learning models have demonstrated strong ability to solve many tasks across a wide range of applications. Those large models typically require training and inference to be distributed. Tensor parallelism is a common technique…

The rise of disaggregated AI GPUs has exposed a critical bottleneck in large-scale attention workloads: non-uniform memory access (NUMA). As multi-chiplet designs become the norm for scaling compute capabilities, memory latency and…

Hardware Architecture · Computer Science 2025-11-05 Mansi Choudhary , Karthik Sangaiah , Sonali Singh , Muhammad Osama , Lisa Wu Wills , Ganesh Dasika

Modeling long sequences is crucial for various large-scale models; however, extending existing architectures to handle longer sequences presents significant technical and resource challenges. In this paper, we propose an efficient and…

Computation and Language · Computer Science 2024-10-08 Ning Wang , Zekun Li , Tongxin Bai , Guoqi Li

System-level routers that intercept LLM requests for safety classification, domain routing, and PII detection must be both fast and operationally lightweight: they should add minimal latency to every request, yet not require a dedicated GPU…

Computation and Language · Computer Science 2026-03-16 Xunzhuo Liu , Bowei He , Xue Liu , Andy Luo , Haichen Zhang , Huamin Chen

Efficiently supporting long context length is crucial for Transformer models. The quadratic complexity of the self-attention computation plagues traditional Transformers. Sliding window-based static sparse attention mitigates the problem by…

Hardware Architecture · Computer Science 2024-05-28 Zhenyu Bai , Pranav Dangi , Huize Li , Tulika Mitra

Transformers have been proven a successful model for a variety of tasks in sequence modeling. However, computing the attention matrix, which is their key component, has quadratic complexity with respect to the sequence length, thus making…

Machine Learning · Computer Science 2020-10-01 Apoorv Vyas , Angelos Katharopoulos , François Fleuret

Graphics Processing Units (GPUs) consisting of Streaming Multiprocessors (SMs) achieve high throughput by running a large number of threads and context switching among them to hide execution latencies. The number of thread blocks, and hence…

Hardware Architecture · Computer Science 2015-06-08 Vishwesh Jatala , Jayvant Anantpur , Amey Karkare

Large language models (LLMs) now support extremely long context windows, but the quadratic complexity of vanilla attention results in significantly long Time-to-First-Token (TTFT) latency. Existing approaches to address this complexity…

Computation and Language · Computer Science 2025-09-04 Qianchao Zhu , Jiangfei Duan , Chang Chen , Siran Liu , Guanyu Feng , Xin Lv , Xiao Chuanfu , Dahua Lin , Chao Yang

Scaling sequence length has become a critical demand in the era of large language models. However, existing methods struggle with either computational complexity or model expressivity, rendering the maximum sequence length restricted. To…

Computation and Language · Computer Science 2023-07-20 Jiayu Ding , Shuming Ma , Li Dong , Xingxing Zhang , Shaohan Huang , Wenhui Wang , Nanning Zheng , Furu Wei

Transformer-based models dominate modern AI workloads but exacerbate memory bottlenecks due to their quadratic attention complexity and ever-growing model sizes. Existing accelerators, such as Groq and Cerebras, mitigate off-chip traffic…

Hardware Architecture · Computer Science 2026-02-12 Jinxin Yu , Yudong Pan , Mengdi Wang , Huawei Li , Yinhe Han , Xiaowei Li , Ying Wang

The self-attention mechanism traditionally relies on the softmax operator, necessitating positional embeddings like RoPE, or position biases to account for token order. But current methods using still face length generalisation challenges.…

Machine Learning · Computer Science 2025-05-21 Shawn Tan , Songlin Yang , Aaron Courville , Rameswar Panda , Yikang Shen
‹ Prev 1 8 9 10 Next ›