English
Related papers

Related papers: Constrained Decoding with Speculative Lookaheads

200 papers

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

Code Large Language Models (Code LLMs) have been increasingly used by developers to boost productivity, but they often generate vulnerable code. Thus, there is an urgent need to ensure that code generated by Code LLMs is correct and secure.…

Cryptography and Security · Computer Science 2024-07-23 Yanjun Fu , Ethan Baker , Yu Ding , Yizheng Chen

We present Cacheback Decoding, a training-free and model-agnostic speculative decoding method that exploits the locality in language to accelerate Large Language Model (LLM) inference. Cacheback leverages only Least Recently Used (LRU)…

Computation and Language · Computer Science 2025-12-01 Zhiyao Ma , In Gim , Lin Zhong

Verification is a key bottleneck in improving inference speed while maintaining distribution fidelity in Speculative Decoding. Recent work has shown that sequence-level verification leads to a higher number of accepted tokens compared to…

Artificial Intelligence · Computer Science 2026-03-03 Yuxuan Zhou , Fei Huang , Heng Li , Fengyi Wu , Tianyu Wang , Jianwei Zhang , Junyang Lin , Zhi-Qi Cheng

Large language models (LLMs) suffer from high inference latency due to the auto-regressive decoding process. Speculative decoding accelerates inference by generating multiple draft tokens using a lightweight model and verifying them in…

Machine Learning · Computer Science 2025-05-27 Yixuan Wang , Yijun Liu , Shiyu ji , Yuzhuang Xu , Yang Xu , Qingfu Zhu , Wanxiang Che

Multiple heads decoding accelerates the inference of Large Language Models (LLMs) by predicting next several tokens simultaneously. It generates and verifies multiple candidate sequences in parallel via tree attention with a fixed…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Zhendong Zhang

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

We explore the possibility of improving probabilistic models in structured prediction. Specifically, we combine the models with constrained decoding approaches in the context of token classification for information extraction. The decoding…

Computation and Language · Computer Science 2023-12-07 Arthur Hemmer , Mickaël Coustaty , Nicola Bartolo , Jérôme Brachat , Jean-Marc Ogier

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

Speculative decoding is a widely used method that accelerates the generation process of large language models (LLMs) with no compromise in model performance. It achieves this goal by using an existing smaller model for drafting and then…

Computation and Language · Computer Science 2024-10-16 Weilin Zhao , Yuxiang Huang , Xu Han , Wang Xu , Chaojun Xiao , Xinrong Zhang , Yewei Fang , Kaihuo Zhang , Zhiyuan Liu , Maosong Sun

The success of deep learning (DL) is often achieved with large models and high complexity during both training and post-training inferences, hindering training in resource-limited settings. To alleviate these issues, this paper introduces a…

Machine Learning · Computer Science 2025-01-20 En-hui Yang , Shayan Mohajer Hamidi

Speculative decoding (SD) accelerates large language model (LLM) inference by using a smaller draft model to propose multiple tokens that are verified by a larger target model in parallel. While prior work demonstrates substantial speedups…

Machine Learning · Computer Science 2026-05-15 Linghao Kong , Megan Flynn , Michael Peng , Nir Shavit , Mark Kurtz , Alexandre Marques

As Large Language Models (LLMs) can now process extremely long contexts, efficient inference over these extended inputs has become increasingly important, especially for emerging applications like LLM agents that highly depend on this…

Computation and Language · Computer Science 2026-04-09 Penghui Yang , Cunxiao Du , Fengzhuo Zhang , Haonan Wang , Tianyu Pang , Chao Du , Bo An

Speculative decoding (SD), where an extra draft model is employed to provide multiple draft tokens first, and then the original target model verifies these tokens in parallel, has shown great power for LLM inference acceleration. However,…

Computation and Language · Computer Science 2025-02-18 Tianyu Liu , Yun Li , Qitan Lv , Kai Liu , Jianchen Zhu , Winston Hu , Xiao Sun

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

With the increasingly giant scales of (causal) large language models (LLMs), the inference efficiency comes as one of the core concerns along the improved performance. In contrast to the memory footprint, the latency bottleneck seems to be…

Computation and Language · Computer Science 2024-04-24 Chen Zhang , Zhuorui Liu , Dawei Song

Large Language Models (LLMs) are increasingly applied to complex tasks that require extended reasoning. In such settings, models often benefit from diverse chains-of-thought to arrive at multiple candidate solutions. This requires two…

Machine Learning · Computer Science 2025-10-08 Xueyan Li , Guinan Su , Mrinmaya Sachan , Jonas Geiping

Aligning large language models (LLMs) with human preferences has become a critical step in their development. Recent research has increasingly focused on test-time alignment, where additional compute is allocated during inference to enhance…

Computation and Language · Computer Science 2025-09-24 Bolian Li , Yanran Wu , Xinyu Luo , Ruqi Zhang

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

Explicit chain-of-thought (CoT) reasoning substantially improves the reasoning ability of large language models (LLMs), but incurs high inference cost due to lengthy autoregressive traces. Existing latent reasoning methods offer a promising…

Computation and Language · Computer Science 2026-05-26 Hui Xie , Jie Liu , Ziyue Qiao , Joaquin Vanschore