English
Related papers

Related papers: FastDraft: How to Train Your Draft

200 papers

Speculative decoding is an emerging technique that accelerates large language model (LLM) inference by allowing a smaller draft model to predict multiple tokens in advance, which are then verified or corrected by a larger target model. In…

Signal Processing · Electrical Eng. & Systems 2025-11-10 Ce Zheng , Tingting Yang

This paper presents a modular approach to accelerate inference in large language models (LLMs) by adding early exit heads at intermediate transformer layers. Each head is trained in a self-supervised manner to mimic the main model's…

Computation and Language · Computer Science 2026-02-13 Florian Valade

Speculative decoding has been shown as an effective way to accelerate Large Language Model (LLM) inference by using a Small Speculative Model (SSM) to generate candidate tokens in a so-called speculation phase, which are subsequently…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-21 Fahao Chen , Peng Li , Tom H. Luan , Zhou Su , Jing Deng

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 gain widespread adoption, running them efficiently becomes crucial. Recent works on LLM inference use speculative decoding to achieve extreme speedups. However, most of these works implicitly design their algorithms…

Computation and Language · Computer Science 2024-12-03 Ruslan Svirschevski , Avner May , Zhuoming Chen , Beidi Chen , Zhihao Jia , Max Ryabinin

Speculative decoding generally dictates having a small, efficient draft model that is either pretrained or distilled offline to a particular target model series, for instance, Llama or Qwen models. However, within online deployment…

Speculative decoding accelerates LLM inference by using a smaller draft model to speculate tokens that a larger target model verifies. Verification is often the bottleneck (e.g. verification is $4\times$ slower than token generation when a…

Computation and Language · Computer Science 2026-05-27 Avinash Kumar , Sujay Sanghavi , Poulami Das

In this study, we aim to explore Multitask Speech Language Model (SpeechLM) efficient inference via token reduction. Unlike other modalities such as vision or text, speech has unique temporal dependencies, making previous efficient…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-07 Yichen Lu , Jiaqi Song , Chao-Han Huck Yang , Shinji Watanabe

Generative Large Language Models (LLMs) based on the Transformer architecture have recently emerged as a dominant foundation model for a wide range of Natural Language Processing tasks. Nevertheless, their application in real-time scenarios…

Computation and Language · Computer Science 2024-01-04 Coleman Hooper , Sehoon Kim , Hiva Mohammadzadeh , Hasan Genc , Kurt Keutzer , Amir Gholami , Sophia Shao

Autoregressive (AR) image models achieve diffusion-level quality but suffer from sequential inference, requiring approximately 2,000 steps for a 576x576 image. Speculative decoding with draft trees accelerates LLMs yet underperforms on…

Computer Vision and Pattern Recognition · Computer Science 2025-12-29 Haodong Lei , Hongsong Wang , Xin Geng , Liang Wang , Pan Zhou

With the continuous advancement in the performance of large language models (LLMs), their demand for computational resources and memory has significantly increased, which poses major challenges for efficient inference on consumer-grade…

Computation and Language · Computer Science 2025-09-10 Libo Zhang , Zhaoning Zhang , Baizhou Xu , Rui Li , Zhiliang Tian , Songzhu Mei , Dongsheng Li

Speculative decoding (SD) is a powerful technique for accelerating the inference process of large language models (LLMs) without sacrificing accuracy. Typically, SD employs a small draft model to generate a fixed number of draft tokens,…

Computation and Language · Computer Science 2026-02-03 Situo Zhang , Yifan Zhang , Zichen Zhu , Hankun Wang , Da Ma , Danyang Zhang , Lu Chen , Kai Yu

The acceleration of Large Language Models (LLMs) with speculative decoding provides a significant runtime improvement without any loss of accuracy. Currently, EAGLE-2 is the state-of-the-art speculative decoding method, improving on EAGLE…

Computation and Language · Computer Science 2024-09-04 Oscar Brown , Zhengjie Wang , Andrea Do , Nikhil Mathew , Cheng Yu

Scaling the size of language models to tens of billions of parameters has led to impressive performance on a wide range of tasks. At generation, these models are used auto-regressively, requiring a forward pass for each generated token, and…

Computation and Language · Computer Science 2023-11-23 Giovanni Monea , Armand Joulin , Edouard Grave

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

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

Language models have demonstrated remarkable capabilities in reasoning tasks through test-time scaling techniques like best-of-N sampling and tree search. However, these approaches often demand substantial computational resources, creating…

Computation and Language · Computer Science 2026-05-22 Woomin Song , Saket Dingliwal , Sai Muralidhar Jayanthi , Bhavana Ganesh , Jinwoo Shin , Aram Galstyan , Sravan Babu Bodapati

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

We propose a novel speculative decoding method tailored for multi-sample reasoning scenarios, such as self-consistency and Best-of-N sampling. Our method exploits the intrinsic consensus of parallel generation paths to synthesize…

Computation and Language · Computer Science 2025-03-10 Yiwei Li , Jiayi Shi , Shaoxiong Feng , Peiwen Yuan , Xinglin Wang , Yueqi Zhang , Ji Zhang , Chuyi Tan , Boyuan Pan , Yao Hu , Kan Li

Flow-matching models deliver state-of-the-art fidelity in image and video generation, but the inherent sequential denoising process renders them slower. Existing acceleration methods like distillation, trajectory truncation, and consistency…

Computer Vision and Pattern Recognition · Computer Science 2026-02-12 Divya Jyoti Bajpai , Dhruv Bhardwaj , Soumya Roy , Tejas Duseja , Harsh Agarwal , Aashay Sandansing , Manjesh Kumar Hanawal
‹ Prev 1 8 9 10 Next ›