English
Related papers

Related papers: TurboSpec: Closed-loop Speculation Control System …

200 papers

Speculative generation has emerged as a promising technique to accelerate inference in large language models (LLMs) by leveraging parallelism to verify multiple draft tokens simultaneously. However, the fundamental limits on the achievable…

Computation and Language · Computer Science 2025-12-15 Sergey Pankratov , Dan Alistarh

Large Language Models (LLMs) have demonstrated impressive performance on multiple-choice question answering (MCQA) benchmarks, yet they remain highly vulnerable to minor input perturbations. In this paper, we introduce and evaluate Token…

Computation and Language · Computer Science 2025-06-12 Jui-Ming Yao , Hao-Yuan Chen , Zi-Xian Tang , Bing-Jia Tan , Sheng-Wei Peng , Bing-Cheng Xie , Shun-Feng Su

The past few years has witnessed specialized large language model (LLM) inference systems, such as vLLM, SGLang, Mooncake, and DeepFlow, alongside rapid LLM adoption via services like ChatGPT. Driving these system design efforts is the…

Databases · Computer Science 2025-06-30 James Pan , Guoliang Li

Prompt engineering is a new paradigm for enhancing the performance of trained neural network models. For optimizing text-style prompts, existing methods usually individually operate small portions of a text step by step, which either breaks…

Computation and Language · Computer Science 2023-10-03 Yujian Betterest Li , Kai Wu

Large language models (LLMs) are promising tools for supporting security management tasks, such as incident response planning. However, their unreliability and tendency to hallucinate remain significant challenges. In this paper, we address…

Artificial Intelligence · Computer Science 2026-02-06 Kim Hammar , Tansu Alpcan , Emil Lupu

LLM serving is increasingly multi-tenant: the same deployment must handle latency-critical interactive requests and more relaxed background workloads under a fixed GPU budget. This creates a tiered-SLO setting where maximizing overall…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-08 Vikranth Srivatsa , Zijian He , Pu Guo , Dongming Li , Yiying Zhang

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), where a small draft model is employed to propose draft tokens in advance and then the target model validates them in parallel, has emerged as a promising technique for LLM inference acceleration. Many endeavors to…

Computation and Language · Computer Science 2026-04-30 Tianyu Liu , Qitan Lv , Hao Li , Xing Gao , Xiao Sun , Xiaoyan Sun

Retrieval-augmented language models (RaLM) have demonstrated the potential to solve knowledge-intensive natural language processing (NLP) tasks by combining a non-parametric knowledge base with a parametric language model. Instead of…

Machine Learning · Computer Science 2024-01-26 Zhihao Zhang , Alan Zhu , Lijie Yang , Yihua Xu , Lanting Li , Phitchaya Mangpo Phothilimthana , Zhihao Jia

Test-Time Scaling (TTS) has proven effective in improving the performance of Large Language Models (LLMs) during inference. However, existing research has overlooked the efficiency of TTS from a latency-sensitive perspective. Through a…

Computation and Language · Computer Science 2025-09-15 Zili Wang , Tianyu Zhang , Haoli Bai , Lu Hou , Xianzhi Yu , Wulong Liu , Shiming Xiang , Lei Zhu

Recently, there has been an extensive research effort in building efficient large language model (LLM) inference serving systems. These efforts not only include innovations in the algorithm and software domains but also constitute…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-12-02 Jaehong Cho , Minsu Kim , Hyunmin Choi , Guseul Heo , Jongse Park

LLMs have low GPU efficiency and high latency due to autoregressive decoding. Speculative decoding (SD) mitigates this using a small draft model to speculatively generate multiple tokens, which are then verified in parallel by a target…

Computation and Language · Computer Science 2026-04-21 Sungkyun Kim , Jaemin Kim , Dogyung Yoon , Jiho Shin , Junyeol Lee , Jiwon Seo

The transformer is the most critical algorithm innovation of the Nature Language Processing (NLP) field in recent years. Unlike the Recurrent Neural Network (RNN) models, Transformers can process on dimensions of sequence lengths in…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-02-23 Jiarui Fang , Yang Yu , Chengduo Zhao , Jie Zhou

Large language models typically generate tokens autoregressively, using each token as input for the next. Recent work on Speculative Decoding has sought to accelerate this process by employing a smaller, faster draft model to more quickly…

Computation and Language · Computer Science 2024-10-24 Bradley McDanel

Speculative decoding (SD) is a promising method for accelerating the decoding process of Large Language Models (LLMs). The efficiency of SD primarily hinges on the consistency between the draft model and the verify model. However, existing…

Computation and Language · Computer Science 2025-06-02 Longze Chen , Renke Shan , Huiming Wang , Lu Wang , Ziqiang Liu , Run Luo , Jiawei Wang , Hamid Alinejad-Rokny , Min Yang

With the rapid adoption of large language models (LLMs) in recommendation systems, the computational and communication bottlenecks caused by their massive parameter sizes and large data volumes have become increasingly prominent. This paper…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-25 Haowei Yang , Yu Tian , Zhongheng Yang , Zhao Wang , Chengrui Zhou , Dannier Li

Temporal reasoning and planning are essential capabilities for large language models (LLMs), yet most existing benchmarks evaluate them in isolation and under limited forms of complexity. To address this gap, we introduce the Temporal…

Artificial Intelligence · Computer Science 2025-10-14 Zifeng Ding , Sikuan Yan , Zhangdie Yuan , Xianglong Hu , Fangru Lin , Andreas Vlachos

How can small-scale large language models (LLMs) efficiently utilize the supervision of LLMs to improve their generative quality? This question has been well studied in scenarios where there is no restriction on the number of LLM…

Computation and Language · Computer Science 2024-10-04 Hyunjong Ok , Jegwang Ryu , Jaeho Lee

Multimodal Large Language Models (MLLMs) power platforms like ChatGPT, Gemini, and Copilot, enabling richer interactions with text, images, and videos. These heterogeneous workloads introduce additional inference stages, such as vision…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-06 Konstantinos Papaioannou , Thaleia Dimitra Doudali

Large language model-based deep research agents have been increasingly popular for addressing long-horizon information-seeking tasks, but they often incur high end-to-end latency due to extensive reasoning and frequent tool use. Speculation…

Machine Learning · Computer Science 2026-03-10 Shuzhang Zhong , Baotong Lu , Qi Chen , Chuanjie Liu , Fan Yang , Meng Li