English
Related papers

Related papers: Balancing Coverage and Draft Latency in Vocabulary…

200 papers

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

GPU memory bandwidth is the main bottleneck for low-latency Large Language Model (LLM) inference. Speculative decoding leverages idle GPU compute by using a lightweight drafter to propose K tokens, which the LLM verifies in parallel,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-27 Anish Saxena , Po-An Tsai , Hritvik Taneja , Aamer Jaleel , Moinuddin Qureshi

Speculative decoding (SD) has become a popular technique to accelerate Large Language Model (LLM) inference, yet its real-world effectiveness remains unclear as prior evaluations rely on research prototypes and unrealistically small batch…

Computation and Language · Computer Science 2026-03-19 Xiaoxuan Liu , Jiaxiang Yu , Jongseok Park , Ion Stoica , Alvin Cheung

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

We propose TETRIS, a novel method that optimizes the total throughput of batch speculative decoding in multi-request settings. Unlike existing methods that optimize for a single request or a group of requests as a whole, TETRIS actively…

Computation and Language · Computer Science 2025-06-02 Zhaoxuan Wu , Zijian Zhou , Arun Verma , Alok Prakash , Daniela Rus , Bryan Kian Hsiang Low

Large language model (LLM)-based automatic speech recognition (ASR) has recently attracted a lot of attention due to its high recognition accuracy and enhanced multi-dialect support. However, the high decoding latency of LLMs challenges the…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-29 Linye Wei , Shuzhang Zhong , Songqiang Xu , Runsheng Wang , Ru Huang , Meng Li

Speculative decoding is widely adopted to reduce latency in large language model (LLM) inference by leveraging smaller draft models capable of handling diverse user tasks. However, emerging AI applications, such as LLM-based agents, present…

Computation and Language · Computer Science 2025-10-09 Gabriele Oliaro , Zhihao Jia , Daniel Campos , Aurick Qiao

Speculative decoding is an effective method for accelerating inference of large language models (LLMs) by employing a small draft model to predict the output of a target model. However, when adapting speculative decoding to domain-specific…

Computation and Language · Computer Science 2025-03-27 Fenglu Hong , Ravi Raju , Jonathan Lingjie Li , Bo Li , Urmish Thakker , Avinash Ravichandran , Swayambhoo Jain , Changran Hu

Large language models (LLMs) are increasingly used for long-content generation (e.g., long Chain-of-Thought reasoning) where decoding efficiency becomes a critical bottleneck: Autoregressive decoding is inherently limited by its sequential…

Computation and Language · Computer Science 2025-06-05 Zhepei Wei , Wei-Lin Chen , Xinyu Zhu , Yu Meng

The current study introduces a novel adaptation of speculative decoding, repurposed from generation to classification tasks. We propose a multi-model framework employing up to three lightweight worker models and a single, more robust judge…

Computation and Language · Computer Science 2025-03-25 Somnath Roy , Padharthi Sreekar , Srivatsa Narasimha , Anubhav Anand

Large language models (LLMs) achieve state-of-the-art accuracy on complex reasoning tasks by generating multiple chain-of-thought (CoT) traces, but using a fixed token budget per query leads to over-computation on easy inputs and…

Artificial Intelligence · Computer Science 2026-02-03 Katrina Brown , Aneesh Muppidi , Rana Shahout

Despite the remarkable strides made by autoregressive language models, their potential is often hampered by the slow inference speeds inherent in sequential token generation. Blockwise parallel decoding (BPD) was proposed by Stern et al. as…

Computation and Language · Computer Science 2024-06-06 Taehyeon Kim , Ananda Theertha Suresh , Kishore Papineni , Michael Riley , Sanjiv Kumar , Adrian Benton

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

The quadratic complexity of attention imposes severe memory and computational bottlenecks on Large Language Model (LLM) inference. This challenge is particularly acute for emerging agentic applications that require processing multi-million…

Machine Learning · Computer Science 2026-05-19 Ceyu Xu , Jiangnan Yu , Yongji Wu , Yuan Xie

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

Reasoning models excel by generating long chain-of-thoughts, but decoding the resulting thousands of tokens is slow. Token-level speculative decoding (SD) helps, but its benefit is capped, because the chance that an entire $\gamma$-token…

Machine Learning · Computer Science 2025-06-25 Yichao Fu , Rui Ge , Zelei Shao , Zhijie Deng , Hao Zhang

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

Modern language models rely on static vocabularies, fixed before pretraining, in contrast to the adaptive vocabulary acquisition observed in human language learning. To bridge this gap, we introduce vocabulary curriculum learning, an…

Computation and Language · Computer Science 2025-02-26 Fangyuan Yu

Large language models have achieved remarkable capabilities, but their practical deployment is hindered by significant computational costs. While adaptive computation methods like early-exiting promise to reduce these costs, they introduce…

Computation and Language · Computer Science 2025-12-16 Sangmin Bae

Large language models incur high inference latency due to sequential autoregressive decoding. Speculative decoding alleviates this bottleneck by using a lightweight draft model to propose multiple tokens for batched verification. However,…

‹ Prev 1 8 9 10 Next ›