English
Related papers

Related papers: Consultant Decoding: Yet Another Synergistic Mecha…

200 papers

Striking an optimal balance between minimal drafting latency and high speculation accuracy to enhance the inference speed of Large Language Models remains a significant challenge in speculative decoding. In this paper, we introduce Falcon,…

Computation and Language · Computer Science 2025-04-23 Xiangxiang Gao , Weisheng Xie , Yiwei Xiang , Feng Ji

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

Text generation with Large Language Models (LLMs) is known to be memory bound due to the combination of their auto-regressive nature, huge parameter counts, and limited memory bandwidths, often resulting in low token rates. Speculative…

Machine Learning · Computer Science 2024-05-15 Raghavv Goel , Mukul Gagrani , Wonseok Jeon , Junyoung Park , Mingu Lee , Christopher Lott

Autoregressive decoding in Large Language Models (LLMs) generates one token per step, causing high inference latency. Speculative decoding (SD) mitigates this through a guess-and-verify strategy, but existing training-free variants face…

Computation and Language · Computer Science 2026-04-17 Zihong Zhang , Zuchao Li , Lefei Zhang , Ping Wang , Hai Zhao

Large Language Models (LLMs) present a critical trade-off between inference quality and computational cost: larger models offer superior capabilities but incur significant latency, while smaller models are faster but less powerful. Existing…

Machine Learning · Computer Science 2025-05-13 Hang Wu , Jianian Zhu , Yinghui Li , Haojie Wang , Biao Hou , Jidong Zhai

Large language models and large multimodal models (LLMs and LMMs) deliver strong generative performance but suffer from slow decoding, a problem that becomes more severe when handling visual inputs, whose sequences typically contain many…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Zihua Wang , Ruibo Li , Haozhe Du , Joey Tianyi Zhou , Yu Zhang , Xu Yang

Inference efficiency in Large Language Models (LLMs) is fundamentally limited by their serial, autoregressive generation, especially as reasoning becomes a key capability and response sequences grow longer. Speculative decoding (SD) offers…

Machine Learning · Computer Science 2026-02-02 Haoyun Jiang , Junqi He , Feng Hong , Xinlong Yang , Jianwei Zhang , Zheng Li , Zhengyang Zhuge , Zhiyong Chen , Bo Han , Junyang Lin , Jiangchao Yao

Speculative decoding is a powerful way to accelerate autoregressive large language models (LLMs), but directly porting it to vision-language models (VLMs) faces unique systems constraints: the prefill stage is dominated by visual tokens…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Haiduo Huang , Fuwei Yang , Zhenhua Liu , Xuanwu Yin , Dong Li , Pengju Ren , Emad Barsoum

Video Large Language Models (Video-LLMs) excel in video understanding but suffer from high inference latency during autoregressive generation. Speculative Decoding (SD) mitigates this by applying a draft-and-verify paradigm, yet existing…

Computation and Language · Computer Science 2026-04-10 Yicheng Ji , Jun Zhang , Jinpeng Chen , Cong Wang , Lidan Shou , Gang Chen , Huan Li

Edge-cloud speculative decoding (SD) accelerates inference by having a cloud-based large language model (LLM) that verifies draft tokens generated by a resource-constrained small language model (SLM) at the edge. A central bottleneck is the…

Machine Learning · Computer Science 2025-10-14 Payel Bhattacharjee , Fengwei Tian , Meiyu Zhong , Guangyi Zhang , Osvaldo Simeone , Ravi Tandon

Despite their impressive capabilities, large language models (LLMs) have been observed to generate responses that include inaccurate or fabricated information, a phenomenon commonly known as ``hallucination''. In this work, we propose a…

Computation and Language · Computer Science 2024-03-12 Yue Zhang , Leyang Cui , Wei Bi , Shuming Shi

Cloud-based Large Language Model (LLM) services often face challenges in achieving low inference latency and meeting Service Level Objectives (SLOs) under dynamic request patterns. Speculative decoding, which exploits lightweight models for…

Computation and Language · Computer Science 2026-01-13 Kaiyu Huang , Hao Wu , Zhubo Shi , Han Zou , Minchen Yu , Qingjiang Shi

Speculative decoding is a widely used technique for accelerating inference in large language models (LLMs), but its performance degrades as input length grows, with significant drops even at moderate lengths. Yet, this early degradation has…

Computation and Language · Computer Science 2026-01-21 Jungyoub Cha , Hyunjong Kim , Sungzoon Cho

Speculative decoding is a powerful technique for reducing the latency of Large Language Models (LLMs), offering a fault-tolerant framework that enables the use of highly compressed draft models. In this work, we introduce Self-Distilled…

Computation and Language · Computer Science 2025-06-03 Mike Lasby , Nish Sinnadurai , Valavan Manohararajah , Sean Lie , Yani Ioannou , Vithursan Thangarasa

Speculative decoding (SD) is a widely adopted approach for accelerating inference in large language models (LLMs), particularly when the draft and target models are well aligned. However, state-of-the-art SD methods typically rely on…

Computation and Language · Computer Science 2026-02-12 Wei Zhong , Manasa Bharadwaj , Yixiao Wang , Yipeng Ji , Chul Lee

Diffusion Language Models (DLMs) offer a promising parallel generation paradigm but suffer from slow inference due to numerous refinement steps and the inability to use standard KV caching. We introduce CDLM (Consistency Diffusion Language…

Machine Learning · Computer Science 2026-02-23 Minseo Kim , Chenfeng Xu , Coleman Hooper , Harman Singh , Ben Athiwaratkun , Ce Zhang , Kurt Keutzer , Amir Gholami

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 achieve impressive performance across diverse tasks but exhibit high inference latency due to their large parameter sizes. While quantization reduces model size, it often leads to performance degradation compared to…

Hardware Architecture · Computer Science 2025-10-22 Yushu Zhao , Yubin Qin , Yang Wang , Xiaolong Yang , Huiming Han , Shaojun Wei , Yang Hu , Shouyi Yin

Large language models (LLMs) underpin interactive multimedia applications such as captioning, retrieval, recommendation, and creative content generation, yet their autoregressive decoding incurs substantial latency. Speculative decoding…

Artificial Intelligence · Computer Science 2026-02-06 Hanyu Wei , Zunhai Su , Peng Lu , Chao Li , Spandan Tiwari , Ashish Sirasao , Yuhan Dong

The practice of speculative decoding, whereby inference is probabilistically supported by a smaller, cheaper, ``drafter'' model, has become a standard technique for systematically reducing the decoding time of large language models. This…

Computation and Language · Computer Science 2025-10-03 Jameson Sandler , Ahmet Üstün , Marco Romanelli , Sara Hooker , Ferdinando Fioretto