English
Related papers

Related papers: HiSpec: Hierarchical Speculative Decoding for LLMs

200 papers

Speculative decoding is a prominent technique to speed up the inference of a large target language model based on predictions of an auxiliary draft model. While effective, in application-specific settings, it often involves fine-tuning both…

Computation and Language · Computer Science 2024-02-20 Nikhil Bhendawade , Irina Belousova , Qichen Fu , Henry Mason , Mohammad Rastegari , Mahyar Najibi

Speculative Decoding (SD) accelerates autoregressive large language model (LLM) inference by decoupling generation and verification. While recent methods improve draft quality by tightly coupling the drafter with the target model, the…

Machine Learning · Computer Science 2026-04-14 Jingwei Song , Xinyu Wang , Hanbin Wang , Xiaoxuan Lei , Bill Shi , Shixin Han , Eric Yang , Xiao-Wen Chang , Lynn Ai

GPU memory bandwidth is the main bottleneck for low-latency Large Language Model (LLM) inference. Speculative decoding leverages idle GPU compute by using a lightweight drafter to propose K tokens, which the LLM verifies in parallel,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-27 Anish Saxena , Po-An Tsai , Hritvik Taneja , Aamer Jaleel , Moinuddin Qureshi

Tool calling has greatly expanded the practical utility of large language models (LLMs) by enabling them to interact with external applications. As LLM capabilities advance, effective tool use increasingly involves multi-step, multi-turn…

Computation and Language · Computer Science 2026-05-29 Heming Xia , Yongqi Li , Cunxiao Du , Mingbo Song , Wenjie Li

This technical report describes the design and training of novel speculative decoding draft models, for accelerating the inference speeds of large language models in a production environment. By conditioning draft predictions on both…

Computation and Language · Computer Science 2024-06-10 Davis Wertheimer , Joshua Rosenkranz , Thomas Parnell , Sahil Suneja , Pavithra Ranganathan , Raghu Ganti , Mudhakar Srivatsa

Large language models typically employ vocabularies of over 100k tokens, which creates a major computational bottleneck at the final linear projection layer when performing speculative decoding. Current methods for vocabulary pruning depend…

Computation and Language · Computer Science 2026-05-27 Zhiyang Chen , Daliang Xu , Yinyuan Zhang , Chenghua Wang , Mengwei Xu , Yun Ma

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

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft…

Machine Learning · Computer Science 2024-12-03 Zhuofan Wen , Shangtong Gui , Yang Feng

Speculative decoding (SD) has been shown to reduce the latency of autoregressive decoding (AD) by 2-3x for small batch sizes. However, increasing throughput and therefore reducing the cost per token requires decoding with large batch sizes.…

Machine Learning · Computer Science 2025-04-10 Sanjit Neelam , Daniel Heinlein , Vaclav Cvicek , Akshay Mishra , Reiner Pope

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

Deployment of autoregressive large language models (LLMs) is costly, and as these models increase in size, the associated costs will become even more considerable. Consequently, different methods have been proposed to accelerate the token…

Computation and Language · Computer Science 2024-07-03 Parsa Kavehzadeh , Mohammadreza Pourreza , Mojtaba Valipour , Tinashu Zhu , Haoli Bai , Ali Ghodsi , Boxing Chen , Mehdi Rezagholizadeh

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

Large language models have shown impressive capabilities across a variety of NLP tasks, yet their generating text autoregressively is time-consuming. One way to speed them up is speculative decoding, which generates candidate segments (a…

Computation and Language · Computer Science 2024-01-15 Sen Yang , Shujian Huang , Xinyu Dai , Jiajun Chen

Speculative decoding has proven effective for accelerating inference in Large Language Models (LLMs), yet its extension to Vision-Language Models (VLMs) remains limited by the computational burden and semantic inconsistency introduced by…

Machine Learning · Computer Science 2025-11-21 Zhinan Xie , Peisong Wang , Shuang Qiu , Jian Cheng

Speculative decoding (SD) accelerates language model inference by drafting tokens from a cheap proposal model and verifying them against an expensive target model via rejection sampling. Because rejection truncates the draft block at the…

Speculative decoding has emerged as a promising approach to accelerate autoregressive inference in large language models (LLMs). Self-draft methods, which leverage the base LLM itself for speculation, avoid the overhead of auxiliary draft…

Computation and Language · Computer Science 2026-04-15 Zhuofan Wen , Yang Feng

Cloud-based Large Language Model (LLM) services often face challenges in achieving low inference latency and meeting Service Level Objectives (SLOs) under dynamic request patterns. Speculative decoding, which exploits lightweight models for…

Computation and Language · Computer Science 2026-01-13 Kaiyu Huang , Hao Wu , Zhubo Shi , Han Zou , Minchen Yu , Qingjiang Shi

This tutorial presents a comprehensive introduction to Speculative Decoding (SD), an advanced technique for LLM inference acceleration that has garnered significant research interest in recent years. SD is introduced as an innovative…

Computation and Language · Computer Science 2025-03-04 Heming Xia , Cunxiao Du , Yongqi Li , Qian Liu , Wenjie Li

Vision-language models (VLMs) have demonstrated strong capabilities in multimodal perception and reasoning. However, deploying large VLMs on mobile devices remains challenging due to their substantial computational and memory demands. A…

Artificial Intelligence · Computer Science 2026-05-05 Yuanyuan Jia , Shunpu Tang , Qianqian Yang

Speculative decoding has become a widely adopted technique for accelerating large language model (LLM) inference by drafting multiple candidate tokens and verifying them with a target model in parallel. Its efficiency, however, critically…

Computation and Language · Computer Science 2026-05-19 Shuoyang Sun , Chang Dai , Hao Fang , Kuofeng Gao , Xinhao Zhong , Yi Sun , Fan Mo , Shu-Tao Xia , Bin Chen