English
Related papers

Related papers: Hydra: Sequentially-Dependent Draft Heads for Medu…

200 papers

Speculative decoding reduces the inference latency of a target large language model via utilizing a smaller and faster draft model. Its performance depends on a hyperparameter K -- the candidate length, i.e., the number of candidate tokens…

Computation and Language · Computer Science 2025-07-14 Kaixuan Huang , Xudong Guo , Mengdi Wang

Large language models (LLMs) have revolutionized natural language processing and broadened their applicability across diverse commercial applications. However, the deployment of these models is constrained by high inference time in…

Computation and Language · Computer Science 2024-11-12 Euiin Yi , Taehyeon Kim , Hongseok Jeung , Du-Seong Chang , Se-Young Yun

Scaling up model depth and size is now a common approach to raise accuracy in many deep learning (DL) applications, as evidenced by the widespread success of multi-billion or even trillion parameter models in natural language processing…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-08-05 Kabir Nagrecha , Arun Kumar

Speculative decoding has emerged as a powerful approach to accelerate large language model (LLM) inference by employing lightweight draft models to propose candidate tokens that are subsequently verified by the target model. The…

Computation and Language · Computer Science 2026-04-22 Zongyue Qin , Raghavv Goel , Mukul Gagrani , Risheek Garrepalli , Mingu Lee , Yizhou Sun

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 LLM inference by drafting multiple tokens and verifying them in parallel with the target model. However, its practical speedup is constrained by the trade-off between draft quality and drafting cost:…

Computation and Language · Computer Science 2026-05-29 Jianuo Huang , Yaojie Zhang , Qituan Zhang , Hao Lin , Hanlin Xu , Linfeng Zhang

The emergence of long-context large language models (LLMs) offers a promising alternative to traditional retrieval-augmented generation (RAG) for processing extensive documents. However, the computational overhead of long-context inference…

Computation and Language · Computer Science 2025-06-24 Guanzheng Chen , Qilong Feng , Jinjie Ni , Xin Li , Michael Qizhe Shieh

Recent works have revealed the great potential of speculative decoding in accelerating the autoregressive generation process of large language models. The success of these methods relies on the alignment between draft candidates and the…

Computation and Language · Computer Science 2025-09-15 Jikai Wang , Zhenxu Tian , Juntao Li , Qingrong Xia , Xinyu Duan , Zhefeng Wang , Baoxing Huai , Min Zhang

Visual document understanding typically requires separate retrieval and generation models, doubling memory and system complexity. We present Hydra, a dual-head approach that provides both ColBERT-style late-interaction retrieval and…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Athos Georgiou

Large language models (LLMs) have achieved remarkable success across diverse natural language processing tasks but face persistent challenges in inference efficiency due to their autoregressive nature. While speculative decoding and beam…

Computation and Language · Computer Science 2026-05-29 Jaydip Sen , Harshitha Puvvala , Subhasis Dasgupta

Large Language Models (LLMs) have revolutionized natural language processing by understanding and generating human-like text. However, the increasing demand for more sophisticated LLMs presents significant computational challenges due to…

Computation and Language · Computer Science 2025-01-14 Ze Yang , Yihong Jin , Xinhe Xu

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 (SD) accelerates large language model inference by using a smaller draft model to propose draft tokens that are subsequently verified by a larger target model. However, the performance of standard SD is often limited by…

Computation and Language · Computer Science 2026-03-20 Zhenwei Tang , Arun Verma , Zijian Zhou , Zhaoxuan Wu , Alok Prakash , Daniela Rus , Bryan Kian Hsiang Low

Speculative decoding accelerates LLM inference by utilizing otherwise idle computational resources during memory-to-chip data transfer. Current speculative decoding methods typically assume a considerable amount of available computing…

Computation and Language · Computer Science 2025-11-26 Luohe Shi , Zuchao Li , Lefei Zhang , Baoyuan Qi , Guoming Liu , Hai Zhao

Speculative decoding is widely used in accelerating large language model (LLM) inference. In this work, we focus on the online draft model selection problem in speculative decoding. We design an algorithm that provably competes with the…

Machine Learning · Computer Science 2026-04-24 Hongyi Liu , Jiaji Huang , Zhen Jia , Youngsuk Park , Yu-Xiang 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

LLMs have low GPU efficiency and high latency due to autoregressive decoding. Speculative decoding (SD) mitigates this using a small draft model to speculatively generate multiple tokens, which are then verified in parallel by a target…

Computation and Language · Computer Science 2026-04-21 Sungkyun Kim , Jaemin Kim , Dogyung Yoon , Jiho Shin , Junyeol Lee , Jiwon Seo

Speculative decoding (SD) has emerged as a method to accelerate LLM inference without sacrificing any accuracy over the 16-bit model inference. In a typical SD setup, the idea is to use a full-precision, small, fast model as "draft" to…

Computation and Language · Computer Science 2025-03-19 Evangelos Georganas , Dhiraj Kalamkar , Alexander Kozlov , Alexander Heinecke

Auto-regressive decoding in Large Language Models (LLMs) is inherently memory-bound: every generation step requires loading the model weights and intermediate results from memory (e.g., High-Bandwidth Memory (HBM) for GPU servers), making…

Machine Learning · Computer Science 2026-05-13 Yuning Han , Yangchenchen Jin , Dylan Zhao , Jingwei Sun

We present Recurrent Drafter (ReDrafter), an advanced speculative decoding approach that achieves state-of-the-art speedup for large language models (LLMs) inference. The performance gains are driven by three key aspects: (1) leveraging a…

Computation and Language · Computer Science 2024-12-17 Yunfei Cheng , Aonan Zhang , Xuanyu Zhang , Chong Wang , Yi Wang