English
Related papers

Related papers: FastEagle: Cascaded Drafting for Accelerating Spec…

200 papers

Retrieval augmented generation (RAG) combines the generative abilities of large language models (LLMs) with external knowledge sources to provide more accurate and up-to-date responses. Recent RAG advancements focus on improving retrieval…

LLM serving platforms are increasingly deployed as multi-model cloud systems, where user demand is often long-tailed: a few popular large models receive most requests, while many smaller tail models remain underutilized. We propose…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-13 Jincheng Xie , Yawen Ling , Qi Xiao , Feiyu Zhang , Zhongyi Huang , Wen Hu , Yu Zheng

Speculative Decoding (SD) is a technique to accelerate the inference of Large Language Models (LLMs) by using a lower complexity draft model to propose candidate tokens verified by a larger target model. To further improve efficiency,…

Computation and Language · Computer Science 2024-12-17 Xiaofan Lu , Yixiao Zeng , Feiyang Ma , Zixu Yu , Marco Levorato

LLM deployment on resource-constrained edge devices faces severe latency constraints, particularly in real-time applications where delayed responses can compromise safety or usability. Among many approaches to mitigate the inefficiencies of…

Speculative decoding accelerates large language model inference by using smaller draft models to generate candidate tokens for parallel verification. However, current approaches are limited by sequential stage dependencies that prevent full…

Artificial Intelligence · Computer Science 2025-05-06 Bradley McDanel , Sai Qian Zhang , Yunhai Hu , Zining Liu

Speculative decoding can substantially accelerate LLM inference, but realizing its benefits in practice is challenging due to evolving workloads and system-level constraints. We present TIDE (Temporal Incremental Draft Engine), a…

Machine Learning · Computer Science 2026-02-06 Jiyoung Park , Hankyu Jang , Changseok Song , Wookeun Jung

As large language models (LLMs) become increasingly powerful, the sequential nature of autoregressive generation creates a fundamental throughput bottleneck that limits the practical deployment. While Multi-Token Prediction (MTP) has…

Machine Learning · Computer Science 2025-09-24 Yuxuan Cai , Xiaozhuan Liang , Xinghua Wang , Jin Ma , Haijin Liang , Jinwen Luo , Xinyu Zuo , Lisheng Duan , Yuyang Yin , Xi Chen

Accelerating inference in Large Language Models (LLMs) is critical for real-time interactions, as they have been widely incorporated into real-world services. Speculative decoding, a fully algorithmic solution, has gained attention for…

Computation and Language · Computer Science 2025-02-11 Sukmin Cho , Sangjin Choi , Taeho Hwang , Jeongyeon Seo , Soyeong Jeong , Huije Lee , Hoyun Song , Jong C. Park , Youngjin Kwon

Large Language Models (LLMs) exhibit high inference latency due to their autoregressive decoding nature. While the draft head in speculative decoding mitigates this issue, its full potential remains unexplored. In this paper, we introduce…

Computation and Language · Computer Science 2024-08-16 Kaiqi Zhang , Jing Zhao , Rui Chen

Speculative decoding accelerates LLM inference by letting a small drafter propose multiple tokens which a large target model verifies once per speculation step. As vocabularies scale past 10e5 tokens,verification cost in the target model is…

Computation and Language · Computer Science 2026-02-04 Jinbin Zhang , Nasib Ullah , Erik Schultheis , Rohit Babbar

Inference with modern Large Language Models (LLMs) is expensive and slow, and speculative sampling has emerged as an effective solution to this problem, however, the number of the calls to the draft model for generating candidate tokens in…

Artificial Intelligence · Computer Science 2025-12-17 Junjie Ma , Jinlong Li

Speculative decoding (SD) is a promising method for accelerating the decoding process of Large Language Models (LLMs). The efficiency of SD primarily hinges on the consistency between the draft model and the verify model. However, existing…

Computation and Language · Computer Science 2025-06-02 Longze Chen , Renke Shan , Huiming Wang , Lu Wang , Ziqiang Liu , Run Luo , Jiawei Wang , Hamid Alinejad-Rokny , Min Yang

Speculative sampling is a promising approach to accelerate the decoding stage for Large Language Models (LLMs). Recent advancements that leverage target LLM's contextual information, such as hidden states and KV cache, have shown…

Machine Learning · Computer Science 2025-02-27 Lefan Zhang , Xiaodan Wang , Yanhua Huang , Ruiwen Xu

In this paper, we introduce a simple training-free technique to improve the performance of drafter-based speculative decoding (SpD) methods that incorporates language modeling head (LM head) during drafting process. A drafter-based…

Computation and Language · Computer Science 2025-09-30 Raghavv Goel , Sudhanshu Agrawal , Mukul Gagrani , Junyoung Park , Yifan Zao , He Zhang , Tian Liu , Yiping Yang , Xin Yuan , Jiuyan Lu , Chris Lott , Mingu Lee

The auto-regressive decoding of Large Language Models (LLMs) results in significant overheads in their hardware performance. While recent research has investigated various speculative decoding techniques for multi-token generation, these…

Machine Learning · Computer Science 2025-10-01 Hao Mark Chen , Wayne Luk , Ka Fai Cedric Yiu , Rui Li , Konstantin Mishchenko , Stylianos I. Venieris , Hongxiang Fan

Speculative decoding accelerates autoregressive generation by letting draft tokens bypass full verification, but conventional frameworks suffer from frequent false rejections, particularly when draft models produce semantically correct but…

Computation and Language · Computer Science 2026-04-16 Xuwen Zhou , Fangxin Liu , Chao Wang , Xiao Zheng , Hao Zheng , Min He , Li Jiang , Haibing Guan

Self-speculative decoding (SSD) accelerates LLM inference by skipping layers to create an efficient draft model, yet existing methods often rely on static heuristics that ignore the dynamic computational overhead of attention in…

Machine Learning · Computer Science 2026-02-25 Seongjin Cha , Gyuwan Kim , Dongsu Han , Tao Yang , Insu Han

Transformer-based models have made tremendous impacts in natural language generation. However the inference speed is a bottleneck due to large model size and intensive computing involved in auto-regressive decoding process. We develop…

Computation and Language · Computer Science 2021-07-14 Yu Yan , Fei Hu , Jiusheng Chen , Nikhil Bhendawade , Ting Ye , Yeyun Gong , Nan Duan , Desheng Cui , Bingyu Chi , Ruofei Zhang

Inference from large autoregressive models like Transformers is slow - decoding K tokens takes K serial runs of the model. In this work we introduce speculative decoding - an algorithm to sample from autoregressive models faster without any…

Machine Learning · Computer Science 2023-05-22 Yaniv Leviathan , Matan Kalman , Yossi Matias

Inference efficiency in Large Language Models (LLMs) is fundamentally limited by their serial, autoregressive generation, especially as reasoning becomes a key capability and response sequences grow longer. Speculative decoding (SD) offers…

Machine Learning · Computer Science 2026-02-02 Haoyun Jiang , Junqi He , Feng Hong , Xinlong Yang , Jianwei Zhang , Zheng Li , Zhengyang Zhuge , Zhiyong Chen , Bo Han , Junyang Lin , Jiangchao Yao