English
Related papers

Related papers: SpecRouter: Adaptive Routing for Multi-Level Specu…

200 papers

Speculative decoding has emerged as a promising approach to accelerate autoregressive inference in large language models (LLMs). Self-draft methods, which leverage the base LLM itself for speculation, avoid the overhead of auxiliary draft…

Computation and Language · Computer Science 2026-04-15 Zhuofan Wen , Yang Feng

Large language models (LLMs) have demonstrated exceptional performance across a wide range of natural language tasks. However, selecting the optimal LLM to respond to a user query often necessitates a delicate balance between performance…

Artificial Intelligence · Computer Science 2025-06-24 Wei Song , Zhenya Huang , Cheng Cheng , Weibo Gao , Bihan Xu , GuanHao Zhao , Fei Wang , Runze Wu

The rapid advancement in large language models (LLMs) has brought forth a diverse range of models with varying capabilities that excel in different tasks and domains. However, selecting the optimal LLM for user queries often involves a…

Machine Learning · Computer Science 2025-02-06 Yang Li

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

Scaling test-time compute has driven the recent advances in the reasoning capabilities of large language models (LLMs), typically by allocating additional computation for more thorough exploration. However, increased compute often comes at…

Artificial Intelligence · Computer Science 2026-02-20 Mert Cemri , Nived Rajaraman , Rishabh Tiwari , Xiaoxuan Liu , Kurt Keutzer , Ion Stoica , Kannan Ramchandran , Ahmad Beirami , Ziteng Sun

The deployment of large language models (LLMs) in real-world applications is increasingly limited by their high inference cost. While recent advances in dynamic token-level computation allocation attempt to improve efficiency by selectively…

Computation and Language · Computer Science 2025-10-17 Chao Han , Yijuan Liang , Zihao Xuan , Daokuan Wu , Wei Zhang , Xiaoyu Shen

Speculative Decoding (SD) accelerates autoregressive large language model (LLM) inference by decoupling generation and verification. While recent methods improve draft quality by tightly coupling the drafter with the target model, the…

Machine Learning · Computer Science 2026-04-14 Jingwei Song , Xinyu Wang , Hanbin Wang , Xiaoxuan Lei , Bill Shi , Shixin Han , Eric Yang , Xiao-Wen Chang , Lynn Ai

Low-latency decoding for large language models (LLMs) is crucial for applications like chatbots and code assistants, yet generating long outputs remains slow in single-query settings. Prior work on speculative decoding (which combines a…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-16 Ziyi Zhang , Ziheng Jiang , Chengquan Jiang , Menghan Yu , Size Zheng , Haibin Lin , Henry Hoffmann , Xin Liu

Large language models (LLM) have recently attracted surging interest due to their outstanding capabilities across various domains. However, enabling efficient LLM inference is challenging due to its autoregressive decoding that generates…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-10-31 Siqi Wang , Hailong Yang , Xuezhu Wang , Tongxuan Liu , Pengbo Wang , Xuning Liang , Kejie Ma , Tianyu Feng , Xin You , Yongjun Bao , Yi Liu , Zhongzhi Luan , Depei Qian

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

Large language models (LLMs) exhibit impressive capabilities across a wide range of tasks, yet the choice of which model to use often involves a trade-off between performance and cost. More powerful models, though effective, come with…

Machine Learning · Computer Science 2025-02-25 Isaac Ong , Amjad Almahairi , Vincent Wu , Wei-Lin Chiang , Tianhao Wu , Joseph E. Gonzalez , M Waleed Kadous , Ion Stoica

Large Language Models (LLMs) have become widely used for Software Engineering (SE) tasks, spanning from function-level code generation to complex repository-level workflows. However, the high latency of autoregressive inference remains a…

Software Engineering · Computer Science 2026-05-05 Yijia Li , Junkai Chen , Xing Hu , Xin Xia

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft…

Machine Learning · Computer Science 2024-12-03 Zhuofan Wen , Shangtong Gui , Yang Feng

Large Language Models (LLMs) face significant inference latency challenges stemming from their autoregressive design and large size. To address this, speculative decoding emerges as a solution, enabling the simultaneous generation and…

Computation and Language · Computer Science 2026-02-27 Yinrong Hong , Zhiquan Tan , Kai Hu

Speculative decoding has emerged as an effective method to reduce latency and inference cost of LLM inferences. However, there has been inadequate attention towards the energy requirements of these models. To address this gap, this paper…

Machine Learning · Computer Science 2026-02-11 Rohit Dutta , Paramita Koley , Soham Poddar , Janardan Misra , Sanjay Podder , Naveen Balani , Saptarshi Ghosh , Niloy Ganguly

Large language models (LLMs) often exhibit complementary strengths. Model routing harnesses these strengths by dynamically directing each query to the most suitable model, given a candidate model pool. However, routing performance relies on…

Machine Learning · Computer Science 2025-11-17 Chenxu Wang , Hao Li , Yiqun Zhang , Linyao Chen , Jianhao Chen , Ping Jian , Peng Ye , Qiaosheng Zhang , Shuyue Hu

Speculative decoding is a prominent technique to speed up the inference of a large target language model based on predictions of an auxiliary draft model. While effective, in application-specific settings, it often involves fine-tuning both…

Computation and Language · Computer Science 2024-02-20 Nikhil Bhendawade , Irina Belousova , Qichen Fu , Henry Mason , Mohammad Rastegari , Mahyar Najibi

Multimodal large language models (MLLMs) have heterogeneous strengths across OCR, chart understanding, spatial reasoning, visual question answering, cost, and latency. Effective MLLM routing therefore requires more than estimating query…

Artificial Intelligence · Computer Science 2026-05-13 Xueqi Cheng , Yushun Dong

Federated inference enhances LLM performance in edge computing through weighted averaging of distributed model predictions. However, autoregressive LLM inference requires frequent full-model forward passes across workers, severely limiting…

Signal Processing · Electrical Eng. & Systems 2026-04-29 Ce Zheng , Xinghan Wang , Jiahong Ning , Yuxuan Shi , Ning Huang , Tingting Yang

Speculative decoding accelerates large language model (LLM) inference by using a small draft model to propose candidate tokens that a larger target model verifies. A critical hyperparameter in this process is the speculation length…

Machine Learning · Computer Science 2026-05-06 Shikhar Shukla