English
Related papers

Related papers: Utility-Driven Speculative Decoding for Mixture-of…

200 papers

Mixture-of-Experts (MoE) language models can reduce computational costs by 2-4$\times$ compared to dense models without sacrificing performance, making them more efficient in computation-bounded scenarios. However, MoE models generally…

Machine Learning · Computer Science 2024-04-09 Bowen Pan , Yikang Shen , Haokun Liu , Mayank Mishra , Gaoyuan Zhang , Aude Oliva , Colin Raffel , Rameswar Panda

Speculative decoding accelerates inference for Large Language Models by using a lightweight draft model to propose candidate tokens that are verified in parallel by a larger target model. Prior work shows that the draft model often…

Computation and Language · Computer Science 2026-03-06 Ofir Ben Shoham

Deployed large language models (LLMs) often rely on speculative decoding, a technique that generates and verifies multiple candidate tokens in parallel, to improve throughput and latency. In this work, we reveal a new side-channel whereby…

Computation and Language · Computer Science 2026-02-12 Jiankun Wei , Abdulrahman Abdulrazzag , Tianchen Zhang , Adel Muursepp , Gururaj Saileshwar

An increasing number of LLMs employ Mixture-of-Experts (MoE) architectures where the feed-forward layer is replaced by a pool of experts and each token only activates a small subset of them. During autoregressive generation, these models…

Machine Learning · Computer Science 2025-11-05 Costin-Andrei Oncescu , Qingyang Wu , Wai Tong Chung , Robert Wu , Bryan Gopal , Junxiong Wang , Tri Dao , Ben Athiwaratkun

Large language models (LLMs) have shown outstanding performance across numerous real-world tasks. However, the autoregressive nature of these models makes the inference process slow and costly. Speculative decoding has emerged as a…

Artificial Intelligence · Computer Science 2025-03-17 Zongyue Qin , Zifan He , Neha Prakriya , Jason Cong , Yizhou Sun

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

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…

Large language models typically generate tokens autoregressively, using each token as input for the next. Recent work on Speculative Decoding has sought to accelerate this process by employing a smaller, faster draft model to more quickly…

Computation and Language · Computer Science 2024-10-24 Bradley McDanel

Mixture-of-Experts (MoE) architectures are increasingly used to efficiently scale large language models. However, in production inference, request batching and speculative decoding significantly amplify expert activation, eroding these…

Machine Learning · Computer Science 2026-02-10 Daniil Vankov , Nikita Ivkin , Kyle Ulrich , Xiang Song , Ashish Khetan , George Karypis

To help the open-source community have a better understanding of Mixture-of-Experts (MoE) based large language models (LLMs), we train and release OpenMoE, a series of fully open-sourced and reproducible decoder-only MoE LLMs, ranging from…

Computation and Language · Computer Science 2024-03-28 Fuzhao Xue , Zian Zheng , Yao Fu , Jinjie Ni , Zangwei Zheng , Wangchunshu Zhou , Yang You

Speculative decoding accelerates memory-bound LLM inference without quality degradation by using a fast drafter to propose multiple candidate tokens and the target model to verify them in parallel. However, conventional sequential…

Computation and Language · Computer Science 2026-05-20 Yaojie Zhang , Jianuo Huang , Junlong Ke , Yuhang Han , Yongji Long , Tianchen Zhao , Biqing Qi , Linfeng Zhang

Transformer-based autoregressive sampling has been the major bottleneck for slowing down large language model inferences. One effective way to accelerate inference is \emph{Speculative Decoding}, which employs a small model to sample a…

Machine Learning · Computer Science 2024-11-05 Ming Yin , Minshuo Chen , Kaixuan Huang , Mengdi Wang

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

Mixture-of-Experts large language models (MoE-LLMs) marks a significant step forward of language models, however, they encounter two critical challenges in practice: 1) expert parameters lead to considerable memory consumption and loading…

Machine Learning · Computer Science 2025-02-25 Wei Huang , Yue Liao , Jianhui Liu , Ruifei He , Haoru Tan , Shiming Zhang , Hongsheng Li , Si Liu , Xiaojuan Qi

Large language models (LLMs) have achieved remarkable success across diverse tasks, yet their inference processes are hindered by substantial time and energy demands due to single-token generation at each decoding step. While previous…

Computation and Language · Computer Science 2025-04-11 Zongyue Qin , Ziniu Hu , Zifan He , Neha Prakriya , Jason Cong , Yizhou Sun

In edge-cloud speculative decoding (SD), edge devices equipped with small language models (SLMs) generate draft tokens that are verified by large language models (LLMs) in the cloud. A key bottleneck in such systems is the limited…

Signal Processing · Electrical Eng. & Systems 2026-01-13 Guangyi Zhang , Yunlong Cai , Guanding Yu , Petar Popovski , Osvaldo Simeone

Mixture of Experts (MoE) LLMs, characterized by their sparse activation patterns, offer a promising approach to scaling language models while avoiding proportionally increasing the inference cost. However, their large parameter sizes…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-15 Yichao Yuan , Lin Ma , Nishil Talati

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 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

Mixture-of-Experts (MoE) models promise efficient scaling of large language models (LLMs) by activating only a small subset of experts per token, but their parallelized inference pipelines make elastic serving challenging. Existing…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-06 Gursimran Singh , Timothy Yu , Haley Li , Cheng Chen , Hanieh Sadri , Qintao Zhang , Yu Zhang , Ying Xiong , Yong Zhang , Zhenan Fan
‹ Prev 1 4 5 6 7 8 10 Next ›