English
Related papers

Related papers: SpecAttn: Speculating Sparse Attention

200 papers

Speculative Decoding (SD) is a widely used approach to accelerate the inference of large language models (LLMs) without reducing generation quality. It operates by first using a compact model to draft multiple tokens efficiently, followed…

Computation and Language · Computer Science 2025-08-08 Hossein Entezari Zarch , Lei Gao , Chaoyi Jiang , Murali Annavaram

Growing demands from tasks like code generation, deep reasoning, and long-document understanding have made long-context generation a crucial capability for large language models (LLMs). Speculative decoding is one of the most direct and…

Machine Learning · Computer Science 2025-12-03 Zhendong Tan , Xingjun Zhang , Chaoyi Hu , Junjie Peng , Kun Xia

Extending the functionality of the Transformer model to accommodate longer sequence lengths has become a critical challenge. This extension is crucial not only for improving tasks such as language translation and long-context processing but…

Computation and Language · Computer Science 2024-06-11 Hengyu Zhang

As Large Language Models (LLMs) scale to million-token contexts, traditional Mechanistic Interpretability techniques for analyzing attention scale quadratically with context length, demanding terabytes of memory beyond 100,000 tokens. We…

Computation and Language · Computer Science 2026-02-03 J Rosser , José Luis Redondo García , Gustavo Penha , Konstantina Palla , Hugues Bouchard

Large language models incur high inference latency due to sequential autoregressive decoding. Speculative decoding alleviates this bottleneck by using a lightweight draft model to propose multiple tokens for batched verification. However,…

Many advanced Large Language Model (LLM) applications require long-context processing, but the self-attention module becomes a bottleneck during the prefilling stage of inference due to its quadratic time complexity with respect to sequence…

Machine Learning · Computer Science 2025-06-02 Xiaodong Ji , Hailin Zhang , Fangcheng Fu , Bin Cui

The growing gap between the increasing complexity of large language models (LLMs) and the limited computational budgets of edge devices poses a key challenge for efficient on-device inference, despite gradual improvements in hardware…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-06 Xiangchen Li , Dimitrios Spatharakis , Saeid Ghafouri , Jiakun Fan , Hans Vandierendonck , Deepu John , Bo Ji , Dimitrios Nikolopoulos

Transformer-based large language models (e.g., BERT and GPT) achieve great success, and fine-tuning, which tunes a pre-trained model on a task-specific dataset, is the standard practice to utilize these models for downstream tasks. However,…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-12-19 Yuntao Gui , Xiao Yan , Peiqi Yin , Han Yang , James Cheng

Large Vision-Language Models (VLMs) have achieved remarkable progress in multimodal understanding, yet they struggle when reasoning over information-intensive images that densely interleave textual annotations with fine-grained graphical…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Yuhan Liu , Lianhui Qin , Shengjie Wang

Large language model (LLM) inference at the network edge is a promising serving paradigm that leverages distributed edge resources to run inference near users and enhance privacy. Existing edge-based LLM inference systems typically adopt…

Systems and Control · Electrical Eng. & Systems 2025-10-14 Bingjie Zhu , Zhixiong Chen , Liqiang Zhao , Hyundong Shin , Arumugam Nallanathan

Speculative decoding is an effective and lossless method for Large Language Model (LLM) inference acceleration. It employs a smaller model to generate a draft token sequence, which is then verified by the original base model. In multi-GPU…

Machine Learning · Computer Science 2025-12-09 Yize Wu , Ke Gao , Ling Li , Yanjun Wu

Speculative decoding is widely adopted to reduce latency in large language model (LLM) inference by leveraging smaller draft models capable of handling diverse user tasks. However, emerging AI applications, such as LLM-based agents, present…

Computation and Language · Computer Science 2025-10-09 Gabriele Oliaro , Zhihao Jia , Daniel Campos , Aurick Qiao

This paper introduces Multimodal Speculative Decoding (MSD) to accelerate Multimodal Large Language Models (MLLMs) inference. Speculative decoding has been shown to accelerate Large Language Models (LLMs) without sacrificing accuracy.…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Luxi Lin , Zhihang Lin , Zhanpeng Zeng , Rongrong Ji

Large language models (LLMs) suffer from high inference latency due to the auto-regressive decoding process. Speculative decoding accelerates inference by generating multiple draft tokens using a lightweight model and verifying them in…

Machine Learning · Computer Science 2025-05-27 Yixuan Wang , Yijun Liu , Shiyu ji , Yuzhuang Xu , Yang Xu , Qingfu Zhu , Wanxiang Che

The growing demand for on-device large language model (LLM) inference highlights the need for efficient mobile edge computing (MEC) solutions, especially in resource-constrained settings. Speculative decoding offers a promising solution by…

Machine Learning · Computer Science 2025-12-01 Jungyeon Koh , Hyun Jong Yang

Speculative decoding and dynamic sparse attention are two complementary approaches for accelerating long-context LLM inference: the former amortizes target-model execution across multiple verifier queries, while the latter reduces each…

Operating Systems · Computer Science 2026-05-21 Zhibin Wang , Ziyu Zhong , Nuo Shen , Yuhang Zhou , Rong Gu , Sheng Zhong

Inference latency stands as a critical bottleneck in the large-scale deployment of Large Language Models (LLMs). Speculative decoding methods have recently shown promise in accelerating inference without compromising the output…

Machine Learning · Computer Science 2025-10-31 Ruilin Wang , Huixia Li , Yuexiao Ma , Xiawu Zheng , Fei Chao , Xuefeng Xiao , Rongrong Ji

Speculative decoding accelerates inference in large language models (LLMs) by generating multiple draft tokens simultaneously. However, existing methods often struggle with token misalignment between the training and decoding phases,…

Computation and Language · Computer Science 2025-10-21 Shijing Hu , Jingyang Li , Xingyu Xie , Zhihui Lu , Kim-Chuan Toh , Pan Zhou

While transformer-based Large Language Models (LLMs) theoretically support massive context windows, they suffer from severe performance degradation when processing long numerical sequences. We attribute this failure to the attention…

Computation and Language · Computer Science 2026-04-10 Jie Sun , Yu Liu , Lu Han , Qiwen Deng , Xiang Shu , Yang Xiao , Xingyu Lu , Jun Zhou , Pengfei Liu , Lintao Ma , Jiancan Wu , Xiang Wang

Large Language Models (LLMs) have emerged as a pivotal research area, yet the attention module remains a critical bottleneck in LLM inference, even with techniques like KVCache to mitigate redundant computations. While various top-$k$…