English
Related papers

Related papers: Goose: Anisotropic Speculation Trees for Training-…

200 papers

Speculative decoding is a pivotal technique to accelerate the inference of large language models (LLMs) by employing a smaller draft model to predict the target model's outputs. However, its efficacy can be limited due to the low predictive…

Artificial Intelligence · Computer Science 2024-06-11 Xiaoxuan Liu , Lanxiang Hu , Peter Bailis , Alvin Cheung , Zhijie Deng , Ion Stoica , Hao Zhang

We present a novel inference scheme, self-speculative decoding, for accelerating Large Language Models (LLMs) without the need for an auxiliary model. This approach is characterized by a two-stage process: drafting and verification. The…

Computation and Language · Computer Science 2025-02-11 Jun Zhang , Jue Wang , Huan Li , Lidan Shou , Ke Chen , Gang Chen , Sharad Mehrotra

Generative Large Language Models (LLMs) based on the Transformer architecture have recently emerged as a dominant foundation model for a wide range of Natural Language Processing tasks. Nevertheless, their application in real-time scenarios…

Computation and Language · Computer Science 2024-01-04 Coleman Hooper , Sehoon Kim , Hiva Mohammadzadeh , Hasan Genc , Kurt Keutzer , Amir Gholami , Sophia Shao

This research aims to accelerate the inference speed of large language models (LLMs) with billions of parameters. We propose \textbf{S}mart \textbf{P}arallel \textbf{A}uto-\textbf{C}orrect d\textbf{E}coding (SPACE), an innovative approach…

Computation and Language · Computer Science 2024-05-21 Hanling Yi , Feng Lin , Hongbin Li , Peiyang Ning , Xiaotian Yu , Rong Xiao

Speculative Decoding (SD) enforces strict distributional equivalence to the target model when accepting candidate tokens. While it maintains the target model's generation quality, this strict equivalence limits the speedup achievable by SD…

Artificial Intelligence · Computer Science 2025-06-04 Maximilian Holsman , Yukun Huang , Bhuwan Dhingra

Decoding strategies play a central role in shaping the reasoning ability of large language models (LLMs). Traditional methods such as greedy decoding and beam search often suffer from error propagation, while sampling-based approaches…

Speculative decoding has emerged as a pivotal technique to accelerate LLM inference by employing a lightweight draft model to generate candidate tokens that are subsequently verified by the target model in parallel. However, while this…

Computation and Language · Computer Science 2026-02-26 Yuetao Chen , Xuliang Wang , Xinzhou Zheng , Ming Li , Peng Wang , Hong Xu

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

Masked language modeling has become a standard pretraining objective for training encoder-based language models. In this approach, certain tokens in the input are masked, and the model learns to predict them using the surrounding context.…

Artificial Intelligence · Computer Science 2026-05-28 Gokul Srinivasagan , Kai Hartung , Munir Georges

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

Large language models (LLMs) and multimodal LLMs (MLL-Ms) excel at chain-of-thought reasoning but face distribution shift at test-time and a lack of verifiable supervision. Recent test-time reinforcement learning (TTRL) methods derive…

Computation and Language · Computer Science 2026-03-09 Jianghao Wu , Yasmeen George , Jin Ye , Yicheng Wu , Daniel F. Schmidt , Jianfei Cai

The escalating demand for efficient decoding in large language models (LLMs) is particularly critical for reasoning-intensive architectures like OpenAI-o3 and DeepSeek-R1, which depend on extended chain-of-thought reasoning. This study…

Computation and Language · Computer Science 2025-05-14 Siyuan Yan , Mo Zhu , Guo-qing Jiang , Jianfei Wang , Jiaxing Chen , Wentai Zhang , Xiang Liao , Xiao Cui , Chen Zhang , Zhuoran Song , Ran Zhu

Sequential dependencies present a fundamental bottleneck in deploying large-scale autoregressive models, particularly for real-time applications. While traditional optimization approaches like pruning and quantization often compromise model…

Computation and Language · Computer Science 2025-10-09 Yunhai Hu , Zining Liu , Zhenyuan Dong , Tianfan Peng , Bradley McDanel , Sai Qian Zhang

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, yet their performance is highly dependent on the prompting strategy and model scale. While reinforcement learning and fine-tuning have been deployed to boost…

Artificial Intelligence · Computer Science 2025-02-10 Tushar Pandey , Ara Ghukasyan , Oktay Goktas , Santosh Kumar Radha

Large Language Models (LLMs) typically generate outputs token by token using a fixed compute budget, leading to inefficient resource utilization. To address this shortcoming, recent advancements in mixture of expert (MoE) models,…

Autoregressive decoding remains a primary bottleneck in large language model (LLM) serving, motivating speculative decoding methods that reduce expensive teacher-model invocations by verifying multiple candidate tokens per step.…

Machine Learning · Computer Science 2026-03-10 Chang Han , Yijie Hu , Jingling Liu

Speculative decoding has become a widely adopted technique for accelerating large language model (LLM) inference by drafting multiple candidate tokens and verifying them with a target model in parallel. Its efficiency, however, critically…

Computation and Language · Computer Science 2026-05-19 Shuoyang Sun , Chang Dai , Hao Fang , Kuofeng Gao , Xinhao Zhong , Yi Sun , Fan Mo , Shu-Tao Xia , Bin Chen

Test-time compute can be scaled both sequentially and in parallel. Sequential scaling involves lengthening the generation process, while parallel scaling involves verifying and selecting among multiple candidate outputs. Combining these two…

Artificial Intelligence · Computer Science 2025-10-08 Weihao Zeng , Keqing He , Chuqiao Kuang , Xiaoguang Li , Junxian He

Speculative decoding accelerates large language model (LLM) inference by using a small draft model to generate candidate tokens for a larger target model to verify. The efficacy of this technique hinges on the trade-off between the time…

Computation and Language · Computer Science 2026-03-03 Jiebin Zhang , Zhenghan Yu , Liang Wang , Nan Yang , Eugene J. Yu , Zheng Li , Yifan Song , Dawei Zhu , Xingxing Zhang , Furu Wei , Sujian Li

We introduce an adaptive tree search algorithm, that can find high-scoring outputs under translation models that make no assumptions about the form or structure of the search objective. This algorithm -- a deterministic variant of Monte…

Computation and Language · Computer Science 2022-02-24 Wang Ling , Wojciech Stokowiec , Domenic Donato , Laurent Sartran , Lei Yu , Austin Matthews , Chris Dyer