English
Related papers

Related papers: FastEagle: Cascaded Drafting for Accelerating Spec…

200 papers

Autoregressive sampling from large language models has led to state-of-the-art results in several natural language tasks. However, autoregressive sampling generates tokens one at a time making it slow, and even prohibitive in certain tasks.…

Machine Learning · Computer Science 2024-01-19 Ziteng Sun , Ananda Theertha Suresh , Jae Hun Ro , Ahmad Beirami , Himanshu Jain , Felix Yu

Recent advances in reasoning models have demonstrated significant improvements in accuracy by employing detailed and comprehensive reasoning processes. However, generating these lengthy reasoning sequences is computationally expensive and…

Computation and Language · Computer Science 2025-08-27 Yijiong Yu

Modern Large Language Models achieve impressive reasoning capabilities with long Chain of Thoughts, but they incur substantial computational cost during inference, and this motivates techniques to improve the performance-cost ratio. Among…

Although current Video-LLMs achieve impressive performance in video understanding tasks, their autoregressive decoding efficiency remains constrained by the massive number of video tokens. Visual token pruning can partially ease this…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Quan Kong , Yuhao Shen , Yicheng Ji , Huan Li , Cong Wang

Parallel Speculative Decoding (PSD) accelerates traditional Speculative Decoding (SD) by overlapping draft generation with verification. However, it remains hampered by two fundamental challenges: (1) a theoretical speedup ceiling dictated…

Computation and Language · Computer Science 2026-04-15 Yuhao Shen , Tianyu Liu , Junyi Shen , Jinyang Wu , Quan Kong , Li Huan , Cong Wang

Speculative Decoding promises to accelerate the inference of Large Language Models, yet its efficacy often degrades in production-grade serving. Existing evaluations typically overlook the compute-bound nature of high-concurrency regimes,…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-15 Xinyi Hu , Yuhao Shen , Baolin Zhang , Hengxin Zhang , Jun Dai , Shuang Ge , Lei Chen , Yue Li , Mingcheng Wan

Speculative decoding accelerates LLM inference by using a fast draft model to generate tokens and a more accurate target model to verify them. Its performance depends on the $\textit{acceptance length}$, or number of draft tokens accepted…

Computation and Language · Computer Science 2026-05-20 Avinash Kumar , Sujay Sanghavi , Poulami Das

Large language models (LLMs) achieve strong performance across diverse tasks but suffer from high inference latency due to their autoregressive generation. Speculative Decoding (SPD) mitigates this issue by verifying candidate tokens in…

Computation and Language · Computer Science 2026-04-30 Jinze Li , Yixing Xu , Guanchen Li , Shuo Yang , Jinfeng Xu , Xuanwu Yin , Dong Li , Edith C. H. Ngai , Emad Barsoum

Speculative decoding accelerates language model inference by separating generation into fast drafting and parallel verification. Its main limitation is drafter-verifier misalignment, which limits token acceptance and reduces overall…

Machine Learning · Computer Science 2025-11-14 Frédéric Berdoz , Peer Rheinboldt , Roger Wattenhofer

Speculative decoding is commonly used for reducing the inference latency of large language models. Its effectiveness depends highly on the speculation lookahead (SL)-the number of tokens generated by the draft model at each iteration. In…

Computation and Language · Computer Science 2024-11-08 Jonathan Mamou , Oren Pereg , Daniel Korat , Moshe Berchansky , Nadav Timor , Moshe Wasserblat , Roy Schwartz

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

Deploying large language models (LLMs) in mobile and edge computing environments is constrained by limited on-device resources, scarce wireless bandwidth, and frequent model evolution. Although edge-cloud collaborative inference with…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-01-05 Yuchen Li , Rui Kong , Zhonghao Lyu , Qiyang Li , Xinran Chen , Hengyi Cai , Lingyong Yan , Shuaiqiang Wang , Jiashu Zhao , Guangxu Zhu , Linghe Kong , Guihai Chen , Haoyi Xiong , Dawei Yin

Speculative decoding accelerates Large Language Models (LLMs) inference by using a lightweight draft model to propose candidate tokens that are verified in parallel by the target model. However, existing draft model training objectives are…

Computation and Language · Computer Science 2026-05-12 Zihao An , Taichi Liu , Ziqiong Liu , Dong Li , Ruofeng Liu , Emad Barsoum

RL post-training of frontier language models is increasingly bottlenecked by autoregressive rollout generation, making rollout acceleration a central systems challenge. Many existing efficiency methods improve throughput by changing the…

Speculative decoding accelerates large language model inference by drafting multiple candidate tokens and verifying them in a single forward pass. Candidates are organized as a tree: deeper trees accept more tokens per step, but adding…

Computation and Language · Computer Science 2026-04-03 Tao Jin , Phuong Minh Nguyen , Naoya Inoue

Test-time scaling has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs) by allocating additional computational resources during inference. However, this paradigm is inherently…

Computation and Language · Computer Science 2025-09-08 Shengyin Sun , Yiming Li , Xing Li , Yingzhao Lian , Weizhe Lin , Hui-Ling Zhen , Zhiyuan Yang , Chen Chen , Xianzhi Yu , Mingxuan Yuan , Chen Ma

Large language models (LLMs) power many modern applications, but serving them at scale remains costly and resource-intensive. Current server-centric systems overlook consumer-grade GPUs at the edge. We introduce SpecEdge, an edge-assisted…

Computation and Language · Computer Science 2025-11-19 Jinwoo Park , Seunggeun Cho , Dongsu Han

Speculative decoding (SD) accelerates large language model (LLM) reasoning by using a small draft model to generate candidate tokens, which the target LLM either accepts directly or regenerates upon rejection. However, excessive alignment…

Computation and Language · Computer Science 2026-01-01 Tiancheng Su , Meicong Zhang , Guoxiu He

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

Speculative decoding emerges as a pivotal technique for enhancing the inference speed of Large Language Models (LLMs). Despite recent research aiming to improve prediction efficiency, multi-sample speculative decoding has been overlooked…

Computation and Language · Computer Science 2024-10-15 Yunsheng Ni , Chuanjian Liu , Yehui Tang , Kai Han , Yunhe Wang