English
Related papers

Related papers: SpecExec: Massively Parallel Speculative Decoding …

200 papers

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 accelerates large language model (LLM) inference by using a small draft model to propose candidate tokens that a larger target model verifies. A critical hyperparameter in this process is the speculation length…

Machine Learning · Computer Science 2026-05-06 Shikhar Shukla

Transformer-based large language models (LLMs) have already achieved remarkable results on long-text tasks, but the limited GPU memory (VRAM) resources struggle to accommodate the linearly growing demand for key-value (KV) cache as the…

Computation and Language · Computer Science 2025-03-21 Shibo Jie , Yehui Tang , Kai Han , Zhi-Hong Deng , Jing Han

Large language models (LLMs) exhibit exceptional performance across a wide range of tasks; however, their token-by-token autoregressive generation process significantly hinders inference speed. Speculative decoding presents a promising…

Computation and Language · Computer Science 2025-03-04 Kai Lv , Honglin Guo , Qipeng Guo , Xipeng Qiu

LLM deployment on resource-constrained edge devices faces severe latency constraints, particularly in real-time applications where delayed responses can compromise safety or usability. Among many approaches to mitigate the inefficiencies of…

The Mixture-of-Experts (MoE) architecture has been widely adopted in large language models (LLMs) to reduce computation cost through model sparsity. Employing speculative decoding (SD) can further accelerate MoE inference by drafting…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-07 Liangkun Chen , Zijian Wen , Tian Wu , Xiaoxi Zhang , Chuan Wu

Large Language Models (LLMs) enable various applications on edge devices such as smartphones, wearables, and embodied robots. However, their deployment often depends on expensive cloud-based APIs, creating high operational costs, which…

Robotics · Computer Science 2025-05-29 Yeshwanth Venkatesha , Souvik Kundu , Priyadarshini Panda

Mixture-of-Experts (MoE) models have gained popularity as a means of scaling the capacity of large language models (LLMs) while maintaining sparse activations and reduced per-token compute. However, in memory-constrained inference settings,…

Machine Learning · Computer Science 2026-03-23 Vivan Madan , Prajwal Singhania , Abhinav Bhatele , Tom Goldstein , Ashwinee Panda

Large language models (LLMs) have revolutionized natural language processing, yet their high computational demands pose significant challenges for real-time inference, especially in multi-user server speculative decoding and…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-16 Phuong Tran , Tzu-Hao Liu , Long Tan Le , Tung-Anh Nguyen , Van Quan La , Eason Yu , Han Shu , Choong Seon Hong , Nguyen H. Tran

This paper introduces SpecInfer, a system that accelerates generative large language model (LLM) serving with tree-based speculative inference and verification. The key idea behind SpecInfer is leveraging small speculative models to predict…

Large language models~(LLMs) are known for their high demand on computing resources and memory due to their substantial model size, which leads to inefficient inference on moderate GPU systems. Techniques like quantization or pruning can…

Computational Engineering, Finance, and Science · Computer Science 2024-11-26 Wenxiang Lin , Xinglin Pan , Shaohuai Shi , Xuan Wang , Xiaowen Chu

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

Self-speculative decoding is an inference technique for large language models designed to speed up generation without sacrificing output quality. It combines fast, approximate decoding using a compact version of the model as a draft model…

Machine Learning · Computer Science 2026-04-17 Walaa Amer , Uday das , Fadi Kurdahi

Autoregressive large language models (LLMs) deliver strong performance but require inherently sequential decoding, leading to high inference latency and poor GPU utilization. Speculative decoding mitigates this bottleneck by using a fast…

Computation and Language · Computer Science 2026-05-29 Jian Chen , Yesheng Liang , Zhijian Liu

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

Speculative decoding has rapidly emerged as a leading approach for accelerating language model (LM) inference, as it offers substantial speedups while yielding identical outputs. This relies upon a small draft model, tasked with predicting…

Computation and Language · Computer Science 2026-02-17 Miles Williams , Young D. Kwon , Rui Li , Alexandros Kouris , Stylianos I. Venieris

Speculative Decoding (SD) is a recently proposed technique for faster inference using Large Language Models (LLMs). SD operates by using a smaller draft LLM for autoregressively generating a sequence of tokens and a larger target LLM for…

Machine Learning · Computer Science 2025-07-09 Meiyu Zhong , Noel Teku , Ravi Tandon

Large Language Models (LLMs) are increasingly being deployed on edge devices for long-context settings, creating a growing need for fast and efficient long-context inference. In these scenarios, the Key-Value (KV) cache is the primary…

We introduce CopySpec, a simple yet effective technique to tackle the inefficiencies LLMs face when generating responses that closely resemble previous outputs or responses that can be verbatim extracted from context. CopySpec identifies…

Computation and Language · Computer Science 2025-05-26 Razvan-Gabriel Dumitru , Minglai Yang , Vikas Yadav , Mihai Surdeanu

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
‹ Prev 1 3 4 5 6 7 10 Next ›