English
Related papers

Related papers: SageAttention2: Efficient Attention with Thorough …

200 papers

Quantizing the activation, weight, and gradient to 4-bit is promising to accelerate neural network training. However, existing 4-bit training methods require custom numerical formats which are not supported by contemporary hardware. In this…

Machine Learning · Computer Science 2023-06-26 Haocheng Xi , Changhao Li , Jianfei Chen , Jun Zhu

In modern machine learning, inner product attention computation is a fundamental task for training large language models such as Transformer, GPT-1, BERT, GPT-2, GPT-3 and ChatGPT. Formally, in this problem, one is given as input three…

Machine Learning · Computer Science 2023-05-11 Josh Alman , Zhao Song

Transformer-based video diffusion models (VDMs) deliver state-of-the-art video generation quality but are constrained by the quadratic cost of self-attention, making long sequences and high resolutions computationally expensive. While…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Mohsen Ghafoorian , Denis Korzhenkov , Amirhossein Habibian

Mixed-precision quantization methods have been proposed to reduce model size while minimizing accuracy degradation. However, existing studies require retraining and do not consider the computational overhead and intermediate representations…

Artificial Intelligence · Computer Science 2025-01-14 Jeongseok Kim , Jemin Lee , Yongin Kwon , Daeyoung Kim

Our formulation reveals that the reduction across the sequence axis can be efficiently computed in parallel through a tree reduction. Our algorithm, called Tree Attention, for parallelizing exact attention computation across multiple GPUs…

Machine Learning · Computer Science 2025-02-11 Vasudev Shyam , Jonathan Pilault , Emily Shepperd , Quentin Anthony , Beren Millidge

The attention module is the key component in Transformers. While the global attention mechanism offers high expressiveness, its excessive computational cost restricts its applicability in various scenarios. In this paper, we propose a novel…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Dongchen Han , Tianzhu Ye , Yizeng Han , Zhuofan Xia , Siyuan Pan , Pengfei Wan , Shiji Song , Gao Huang

Quantization is an effective method for reducing memory footprint and inference time of Neural Networks, e.g., for efficient inference in the cloud, especially at the edge. However, ultra low precision quantization could lead to significant…

Computer Vision and Pattern Recognition · Computer Science 2021-05-11 Zhen Dong , Zhewei Yao , Yaohui Cai , Daiyaan Arfeen , Amir Gholami , Michael W. Mahoney , Kurt Keutzer

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

VRAM requirements for transformer models scale quadratically with context length due to the self-attention mechanism. In this paper we modify the decoder-only transformer, replacing self-attention with InAttention, which scales linearly…

Machine Learning · Computer Science 2024-10-10 Joseph Eisner

Efficient inference of Multi-Head Latent Attention (MLA) is challenged by deploying the DeepSeek-R1 671B model on a single Multi-GPU server. This paper introduces FlashMLA-ETAP, a novel framework that enhances MLA inference for the…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-05 Pengcuo Dege , Qiuming Luo , Rui Mao , Chang Kong

Quantization has emerged as a standard technique for accelerating inference for generative models by enabling faster low-precision computations and reduced memory transfers. Recently, GPU accelerators have added first-class support for…

Transformers have been successfully used in various fields and are becoming the standard tools in computer vision. However, self-attention, a core component of transformers, has a quadratic complexity problem, which limits the use of…

Computer Vision and Pattern Recognition · Computer Science 2022-06-02 Jiuk Hong , Chaehyeon Lee , Soyoun Bang , Heechul Jung

Neural networks commonly execute on hardware accelerators such as NPUs and GPUs for their size and computation overhead. These accelerators are costly and it is hard to scale their resources to handle real-time workload fluctuations. We…

Machine Learning · Computer Science 2025-10-06 Jaemin Kim , Hongjun Um , Sungkyun Kim , Yongjun Park , Jiwon Seo

As Large Language Models (LLMs) scale to longer context windows, the computational cost of attention mechanisms, which traditionally grows quadratically with input length, presents a critical challenge for real-time and memory-constrained…

Computation and Language · Computer Science 2024-12-10 James Vo

Diffusion transformers have emerged as the mainstream paradigm for video generation models. However, the use of up to billions of parameters incurs significant computational costs. Quantization offers a promising solution by reducing memory…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Weilun Feng , Haotong Qin , Chuanguang Yang , Xiangqi Li , Han Yang , Yuqi Li , Zhulin An , Libo Huang , Michele Magno , Yongjun Xu

Transformers' compute-intensive operations pose enormous challenges for their deployment in resource-constrained EdgeAI / tinyML devices. As an established neural network compression technique, quantization reduces the hardware…

Machine Learning · Computer Science 2023-04-26 Alberto Marchisio , Davide Dura , Maurizio Capra , Maurizio Martina , Guido Masera , Muhammad Shafique

Transformer-based deep learning models are increasingly deployed on energy, and DRAM bandwidth constrained devices such as laptops and gaming consoles, which presents significant challenges in meeting the latency requirements of the models.…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-08-26 Aadesh Deshmukh , Venkata Yaswanth Raparti , Samuel Hsu

Vision Transformer (ViT) architectures are becoming increasingly popular and widely employed to tackle computer vision applications. Their main feature is the capacity to extract global information through the self-attention mechanism,…

Computer Vision and Pattern Recognition · Computer Science 2024-05-06 Lorenzo Papa , Paolo Russo , Irene Amerini , Luping Zhou

We propose Multiplier-less INTeger (MINT) quantization, a uniform quantization scheme that efficiently compresses weights and membrane potentials in spiking neural networks (SNNs). Unlike previous SNN quantization methods, MINT quantizes…

Neural and Evolutionary Computing · Computer Science 2023-11-08 Ruokai Yin , Yuhang Li , Abhishek Moitra , Priyadarshini Panda

The attention module, which is a crucial component in Transformer, cannot scale efficiently to long sequences due to its quadratic complexity. Many works focus on approximating the dot-then-exponentiate softmax function in the original…

Machine Learning · Computer Science 2021-11-04 Shengjie Luo , Shanda Li , Tianle Cai , Di He , Dinglan Peng , Shuxin Zheng , Guolin Ke , Liwei Wang , Tie-Yan Liu