English
Related papers

Related papers: IceFormer: Accelerated Inference with Long-Sequenc…

200 papers

Transformer-based large language models (LLMs) exhibit impressive performance in generative tasks but also introduce significant challenges in real-world serving due to inefficient use of the expensive, computation-optimized accelerators.…

Machine Learning · Computer Science 2025-04-11 Shaoyuan Chen , Wencong Xiao , Yutong Lin , Mingxing Zhang , Yingdi Shan , Jinlei Jiang , Kang Chen , Yongwei Wu

Scaling language models to handle longer contexts introduces substantial memory challenges due to the growing cost of key-value (KV) caches. Motivated by the efficiency gains of hybrid models and the broad availability of pretrained large…

Computation and Language · Computer Science 2026-05-19 Xuan Zhang , Fengzhuo Zhang , Cunxiao Du , Chao Du , Tianyu Pang , Wei Gao , Min Lin

Transformers have been matching deep convolutional networks for vision architectures in recent works. Most work is focused on getting the best results on large-scale benchmarks, and scaling laws seem to be the most successful strategy:…

Computer Vision and Pattern Recognition · Computer Science 2023-03-23 Corentin Dancette , Matthieu Cord

On-device inference for Large Language Models (LLMs), driven by increasing privacy concerns and advancements of mobile-sized models, has gained significant interest. However, even mobile-sized LLMs (e.g., Gemma-2B) encounter unacceptably…

Artificial Intelligence · Computer Science 2024-12-17 Daliang Xu , Hao Zhang , Liming Yang , Ruiqi Liu , Gang Huang , Mengwei Xu , Xuanzhe Liu

The Transformer architecture revolutionized the field of natural language processing (NLP). Transformers-based models (e.g., BERT) power many important Web services, such as search, translation, question-answering, etc. While enormous…

Computation and Language · Computer Science 2021-02-23 Dave Dice , Alex Kogan

Transformers are among the state of the art for many tasks in speech, vision, and natural language processing, among others. Self-attentions, which are crucial contributors to this performance have quadratic computational complexity, which…

Computation and Language · Computer Science 2022-12-21 Roshan Sharma , Bhiksha Raj

We develop a novel approach for confidently accelerating inference in the large and expensive multilayer Transformers that are now ubiquitous in natural language processing (NLP). Amortized or approximate computational methods increase…

Computation and Language · Computer Science 2021-09-10 Tal Schuster , Adam Fisch , Tommi Jaakkola , Regina Barzilay

Large language models have high compute, latency, and memory requirements. While specialized accelerators such as GPUs and TPUs typically run these workloads, CPUs are more widely available and consume less energy. Accelerating LLMs with…

Large Language Model (LLM) inference is hard. The autoregressive Decode phase of the underlying Transformer model makes LLM inference fundamentally different from training. Exacerbated by recent AI trends, the primary challenges are memory…

Hardware Architecture · Computer Science 2026-02-10 Xiaoyu Ma , David Patterson

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

The analysis of long sequence data remains challenging in many real-world applications. We propose a novel architecture, ChunkFormer, that improves the existing Transformer framework to handle the challenges while dealing with long time…

Machine Learning · Computer Science 2022-01-03 Yue Ju , Alka Isac , Yimin Nie

Analyzing long text data such as customer call transcripts is a cost-intensive and tedious task. Machine learning methods, namely Transformers, are leveraged to model agent-customer interactions. Unfortunately, Transformers adhere to…

Computation and Language · Computer Science 2025-02-19 Annamalai Senthilnathan , Kristjan Arumae , Mohammed Khalilia , Zhengzheng Xing , Aaron R. Colak

Transformers have improved the state-of-the-art across numerous tasks in sequence modeling. Besides the quadratic computational and memory complexity w.r.t the sequence length, the self-attention mechanism only processes information at the…

Machine Learning · Computer Science 2021-08-12 Yao Zhang , Yunpu Ma , Thomas Seidl , Volker Tresp

This work introduces an efficient method to scale Transformer-based Large Language Models (LLMs) to infinitely long inputs with bounded memory and computation. A key component in our proposed approach is a new attention technique dubbed…

Computation and Language · Computer Science 2024-08-13 Tsendsuren Munkhdalai , Manaal Faruqui , Siddharth Gopal

Transformers do not scale very well to long sequence lengths largely because of quadratic self-attention complexity. In the recent months, a wide spectrum of efficient, fast Transformers have been proposed to tackle this problem, more often…

Machine Learning · Computer Science 2020-11-10 Yi Tay , Mostafa Dehghani , Samira Abnar , Yikang Shen , Dara Bahri , Philip Pham , Jinfeng Rao , Liu Yang , Sebastian Ruder , Donald Metzler

Transformers are slow and memory-hungry on long sequences, since the time and memory complexity of self-attention are quadratic in sequence length. Approximate attention methods have attempted to address this problem by trading off model…

Machine Learning · Computer Science 2022-06-24 Tri Dao , Daniel Y. Fu , Stefano Ermon , Atri Rudra , Christopher Ré

Transformer-based large models excel in natural language processing and computer vision, but face severe computational inefficiencies due to the self-attention's quadratic complexity with input tokens. Recently, researchers have proposed a…

Computation and Language · Computer Science 2026-05-26 Haojie Ouyang , Jianwei Lv , Lei Ren , Chen Wei , Xiaojie Wang , Fangxiang Feng

Transformer model has gained prominence as a popular deep neural network architecture for neural language processing (NLP) and computer vision (CV) applications. However, the extensive use of nonlinear operations, like softmax, poses a…

Hardware Architecture · Computer Science 2024-11-21 Shuai Dong , Junyi Yang , Xiaoqi Peng , Hongyang Shang , Ye Ke , Xiaofeng Yang , Hongjie Liu , Arindam Basu

Transformers have achieved remarkable success in sequence modeling and beyond but suffer from quadratic computational and memory complexities with respect to the length of the input sequence. Leveraging techniques include sparse and linear…

Machine Learning · Computer Science 2022-08-02 Tan Nguyen , Richard G. Baraniuk , Robert M. Kirby , Stanley J. Osher , Bao Wang

In long-context large language model (LLM) inference, the prefill stage dominates computation due to self-attention over the complete input context. Sparse attention significantly reduces self-attention computation by limiting each token's…

Hardware Architecture · Computer Science 2026-02-25 Rakshith Jayanth , Viktor Prasanna