English
Related papers

Related papers: Jakiro: Boosting Speculative Decoding with Decoupl…

200 papers

Speculative decoding accelerates LLM inference by using a draft model to look ahead, but gains are capped by the cost of autoregressive draft generation: increasing draft size elevates acceptance rates but introduces additional latency…

Computation and Language · Computer Science 2025-12-15 Nikhil Bhendawade , Kumari Nishu , Arnav Kundu , Chris Bartels , Minsik Cho , Irina Belousova

Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generating multiple tokens using a single target forward pass.…

Computation and Language · Computer Science 2025-06-12 Nadav Timor , Jonathan Mamou , Daniel Korat , Moshe Berchansky , Gaurav Jain , Oren Pereg , Moshe Wasserblat , David Harel

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

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…

Recent advancements in Mixture of Experts (MoE) models have significantly increased their parameter scale as well as model performance. Extensive offloading techniques have been proposed to address the GPU memory limitations of MoE…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-03 Zhibin Wang , Zhonghui Zhang , Yuhang Zhou , Zibo Wang , Mo Zhou , Peng Jiang , Weilin Cai , Chengying Huan , Rong Gu , Sheng Zhong , Chen Tian

Speculative decoding (SPD) accelerates large language model (LLM) inference by letting a smaller draft model propose multiple future tokens that are verified in parallel by a larger target model. The dominant SPD paradigm treats the target…

Computation and Language · Computer Science 2026-05-26 Jinze Li , Yixing Xu , Guanchen Li , Jinfeng Xu , Shuo Yang , Yang Zhang , Xuanwu Yin , Dong Li , Edith C. H. Ngai , Emad Barsoum

Reasoning models excel by generating long chain-of-thoughts, but decoding the resulting thousands of tokens is slow. Token-level speculative decoding (SD) helps, but its benefit is capped, because the chance that an entire $\gamma$-token…

Machine Learning · Computer Science 2025-06-25 Yichao Fu , Rui Ge , Zelei Shao , Zhijie Deng , Hao Zhang

Recently, speculative decoding (SD) has emerged as a promising technique to accelerate LLM inference by employing a small draft model to propose draft tokens in advance, and validating them in parallel with the large target model. However,…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-15 Yuhao Shen , Junyi Shen , Quan Kong , Tianyu Liu , Yao Lu , Cong Wang

Speculative decoding has demonstrated its effectiveness in accelerating the inference of large language models while maintaining a consistent sampling distribution. However, the conventional approach of training a separate draft model to…

Computation and Language · Computer Science 2024-04-30 Fangcheng Liu , Yehui Tang , Zhenhua Liu , Yunsheng Ni , Kai Han , Yunhe Wang

Transformer language models generate text autoregressively, making inference latency proportional to the number of tokens generated. Speculative decoding reduces this latency without sacrificing output quality, by leveraging a small draft…

Machine Learning · Computer Science 2025-10-24 Clara Mohri , Haim Kaplan , Tal Schuster , Yishay Mansour , Amir Globerson

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

Group relative policy optimization (GRPO) has demonstrated significant potential in improving the reasoning capabilities of large language models (LLMs) via reinforcement learning. However, its practical deployment is impeded by an…

Machine Learning · Computer Science 2025-09-29 Yizhou Zhang , Ning Lv , Teng Wang , Jisheng Dang

Sparse Mixtures of Experts (SMoE) scales model capacity without significant increases in training and inference costs, but exhibits the following two issues: (1) Low expert activation, where only a small subset of experts are activated for…

Computation and Language · Computer Science 2024-04-24 Xun Wu , Shaohan Huang , Wenhui Wang , Furu Wei

Tree-based speculative decoding accelerates autoregressive generation by verifying multiple draft candidates in parallel, but this advantage weakens for sparse Mixture-of-Experts (MoE) models. As the draft tree grows, different branches…

Computation and Language · Computer Science 2026-05-04 Lehan Pan , Ziyang Tao , Ruoyu Pang , Xiao Wang , Jianjun Zhao , Yanyong Zhang

Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While effective in centralized systems, its behavior in…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-18 Jingwei Song , Wanyi Chen , Xinyuan Song , Max , Chris Tong , Gufeng Chen , Tianyi Zhao , Eric Yang , Bill Shi , Lynn Ai

Diffusion-based Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive models, offering unique advantages through bidirectional attention and parallel generation paradigms. However, the generation results…

Computation and Language · Computer Science 2025-10-07 Yifeng Gao , Ziang Ji , Yuxuan Wang , Biqing Qi , Hanlin Xu , Linfeng Zhang

Speculative decoding accelerates inference in large language models (LLMs) by generating draft tokens for target model verification. Current approaches for obtaining draft tokens rely on lightweight draft models or additional model…

Computation and Language · Computer Science 2025-03-06 Guofeng Quan , Wenfeng Feng , Chuzhan Hao , Guochao Jiang , Yuewei Zhang , Hao 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

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

Speculative decoding accelerates large language model inference using a smaller draft model. In this paper, we establish a surprising connection between speculative decoding and channel simulation, which aims at simulating a noisy channel…

Computation and Language · Computer Science 2025-04-23 Szymon Kobus , Deniz Gündüz