English
Related papers

Related papers: SPEED: Speculative Pipelined Execution for Efficie…

200 papers

The recent emergence of Large Language Models based on the Transformer architecture has enabled dramatic advancements in the field of Natural Language Processing. However, these models have long inference latency, which limits their…

Computation and Language · Computer Science 2023-10-13 Sehoon Kim , Karttikeya Mangalam , Suhong Moon , Jitendra Malik , Michael W. Mahoney , Amir Gholami , Kurt Keutzer

Autoregressive language models are constrained by their inherently sequential nature, generating one token at a time. This paradigm limits inference speed and parallelism, especially during later stages of generation when the direction and…

Computation and Language · Computer Science 2025-07-17 Mohammad Samragh , Arnav Kundu , David Harrison , Kumari Nishu , Devang Naik , Minsik Cho , Mehrdad Farajtabar

Speculative Decoding (SD) is a widely used approach to accelerate the inference of large language models (LLMs) without reducing generation quality. It operates by first using a compact model to draft multiple tokens efficiently, followed…

Computation and Language · Computer Science 2025-08-08 Hossein Entezari Zarch , Lei Gao , Chaoyi Jiang , Murali Annavaram

Large language model (LLM) decoding involves generating a sequence of tokens based on a given context, where each token is predicted one at a time using the model's learned probabilities. The typical autoregressive decoding method requires…

Computation and Language · Computer Science 2024-08-20 Xukun Liu , Bowen Lei , Ruqi Zhang , Dongkuan Xu

Cascades and speculative decoding are two common approaches to improving language models' inference efficiency. Both approaches involve interleaving models of different sizes, but via fundamentally distinct mechanisms: cascades employ a…

Computation and Language · Computer Science 2024-10-23 Harikrishna Narasimhan , Wittawat Jitkrittum , Ankit Singh Rawat , Seungyeon Kim , Neha Gupta , Aditya Krishna Menon , Sanjiv Kumar

Speculative decoding (SD) accelerates large language model (LLM) inference by using a smaller model to draft future tokens, which are then verified by the target LLM. This preserves generation quality by accepting only aligned tokens.…

Computation and Language · Computer Science 2026-04-08 Taehyeon Kim , Hojung Jung , Se-Young Yun

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

Speculative decoding accelerates autoregressive language model inference by verifying multiple draft tokens in parallel. However, the verification stage often becomes the dominant computational bottleneck, especially for long-context inputs…

Computation and Language · Computer Science 2025-12-29 Jikai Wang , Jianchao Tan , Yuxuan Hu , Jiayu Qin , Yerui Sun , Yuchen Xie , Xunliang Cai , Juntao Li , Min Zhang

Diffusion large language models (dLLMs) generate text through iterative denoising. In commonly adopted parallel decoding schemes, each step confirms only high-confidence positions while remasking the others. By analyzing dLLM denoising…

Computation and Language · Computer Science 2026-05-27 Kangyu Wang , Zhiyun Jiang , Haibo Feng , Weijia Zhao , Lin Liu , Jianguo Li , Zhenzhong Lan , Weiyao Lin

We propose an acceleration scheme for large language models (LLMs) through Speculative Decoding with Semantic Adaptive Tokens (SDSAT). The primary objective of this design is to enhance the LLM model's ability to generate draft tokens more…

Computation and Language · Computer Science 2024-04-02 Chengbo Liu , Yong Zhu

Rollout dominates the training time in large language model (LLM) post-training, where the trained model is used to generate tokens given a batch of prompts. This work, SpecActor, achieves fast rollout with speculative decoding that deploys…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-24 Rongxin Cheng , Kai Zhou , Xingda Wei , Siyuan Liu , Mingcong Han , Mingjing Ai , Yeju Zhou , Baoquan Zhong , Wencong Xiao , Rong Chen , Haibo Chen

The computational complexity of large language model (LLM) inference significantly constrains their deployment efficiency on edge devices. In contrast, small language models offer faster decoding and lower resource consumption but often…

Computation and Language · Computer Science 2025-04-11 Jianshu She , Wenhao Zheng , Zhengzhong Liu , Hongyi Wang , Eric Xing , Huaxiu Yao , Qirong Ho

The growth in the number of parameters of Large Language Models (LLMs) has led to a significant surge in computational requirements, making them challenging and costly to deploy. Speculative decoding (SD) leverages smaller models to…

Computation and Language · Computer Science 2025-04-04 Matthieu Zimmer , Milan Gritta , Gerasimos Lampouras , Haitham Bou Ammar , Jun Wang

While speculative decoding has recently appeared as a promising direction for accelerating the inference of large language models (LLMs), the speedup and scalability are strongly bounded by the token acceptance rate. Prevalent methods…

Machine Learning · Computer Science 2024-10-16 Yunfan Xiong , Ruoyu Zhang , Yanzeng Li , Tianhao Wu , Lei Zou

Recently, speculative decoding (SD) has emerged as a promising technique to accelerate LLM inference by employing a small draft model to propose draft tokens in advance, and validating them in parallel with the large target model. However,…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-15 Yuhao Shen , Junyi Shen , Quan Kong , Tianyu Liu , Yao Lu , Cong Wang

Speculative decoding accelerates Large Language Model (LLM) inference by verifying multiple drafted tokens in parallel. However, for Mixture-of-Experts (MoE) models, this parallelism introduces a severe bottleneck: large draft trees…

Machine Learning · Computer Science 2026-02-19 Bradley McDanel , Steven Li , Sruthikesh Surineni , Harshit Khaitan

Large language models have demonstrated exceptional capability in natural language understanding and generation. However, their generation speed is limited by the inherently sequential nature of their decoding process, posing challenges for…

Computation and Language · Computer Science 2024-05-27 Chenxi Sun , Hongzhi Zhang , Zijia Lin , Jingyuan Zhang , Fuzheng Zhang , Zhongyuan Wang , Bin Chen , Chengru Song , Di Zhang , Kun Gai , Deyi Xiong

We study the problem of efficient generative inference for Transformer models, in one of its most challenging settings: large deep models, with tight latency targets and long sequence lengths. Better understanding of the engineering…

Large Language Models (LLMs) have achieved state-of-the-art performance on a broad range of Natural Language Processing (NLP) tasks, including document processing and code generation. Autoregressive Language Models (ARMs), which generate…

Large language models~(LLMs) are known for their high demand on computing resources and memory due to their substantial model size, which leads to inefficient inference on moderate GPU systems. Techniques like quantization or pruning can…

Computational Engineering, Finance, and Science · Computer Science 2024-11-26 Wenxiang Lin , Xinglin Pan , Shaohuai Shi , Xuan Wang , Xiaowen Chu