English
Related papers

Related papers: Cascadia: An Efficient Cascade Serving System for …

200 papers

High throughput serving of large language models (LLMs) requires batching sufficiently many requests at a time. However, existing systems struggle because the key-value cache (KV cache) memory for each request is huge and grows and shrinks…

Machine Learning · Computer Science 2023-09-13 Woosuk Kwon , Zhuohan Li , Siyuan Zhuang , Ying Sheng , Lianmin Zheng , Cody Hao Yu , Joseph E. Gonzalez , Hao Zhang , Ion Stoica

Large Language Models (LLMs) have revolutionized numerous domains, driving the rise of Language-Model-as-a-Service (LMaaS) platforms that process millions of queries daily. These platforms must minimize latency and meet Service Level…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-21 Zhihan Jiang , Yujie Huang , Guangba Yu , Junjie Huang , Jiazhen Gu , Michael R. Lyu

Large language models (LLMs) process and predict sequences containing text to answer questions, and address tasks including document summarization, providing recommendations, writing software and solving quantitative problems. We provide a…

Numerical Analysis · Mathematics 2026-02-02 Ricardo Baptista , Andrew Stuart , Son Tran

Large language models (LLMs) are powerful tools but are often expensive to deploy at scale. LLM query routing mitigates this by dynamically assigning queries to models of varying cost and quality to obtain a desired trade-off. Prior query…

Modern key-value storage engines built on Log-Structured Merge-trees (LSM-trees), such as RocksDB and LevelDB, rely heavily on the performance of their compaction operations, which are impacted by a complex set of interdependent…

Performance · Computer Science 2026-02-16 Jiabiao Ding , Yina Lv , Qiao Li , Zhirong Shen , Chun Jason Xue

Power system time series analytics is critical in understanding the system operation conditions and predicting the future trends. Despite the wide adoption of Artificial Intelligence (AI) tools, many AI-based time series analytical models…

Signal Processing · Electrical Eng. & Systems 2025-11-12 Zhenghao Zhou , Yiyan Li , Xinjie Yu , Runlong Liu , Zelin Guo , Zheng Yan , Mo-Yuen Chow , Yuqi Yang , Yang Xu

Recent advances in Large Language Models (LLMs) have revolutionized web applications, enabling intelligent search, recommendation, and assistant services with natural language interfaces. Tool-calling extends LLMs with the ability to…

Software Engineering · Computer Science 2026-01-23 Yi Zhai , Dian Shen , Junzhou Luo , Bin Yang

Cascade systems comprise a two-model sequence, with a lightweight model processing all samples and a heavier, higher-accuracy model conditionally refining harder samples to improve accuracy. By placing the light model on the device side and…

Machine Learning · Computer Science 2023-06-23 Sokratis Nikolaidis , Stylianos I. Venieris , Iakovos S. Venieris

Large language model (LLM) serving demands low latency and high throughput, but high load variability makes it challenging to achieve high GPU utilization. In this paper, we identify a synergetic but overlooked opportunity to co-serve…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-05 Yifan Qiao , Shu Anzai , Shan Yu , Haoran Ma , Shuo Yang , Yang Wang , Miryung Kim , Yongji Wu , Yang Zhou , Jiarong Xing , Joseph E. Gonzalez , Ion Stoica , Harry Xu

Serving Large Language Models (LLMs) at scale requires meeting strict Service Level Objectives (SLOs) under severe computational and memory constraints. Nevertheless, traditional caching strategies fall short: exact-matching and prefix…

Databases · Computer Science 2025-08-27 Jungwoo Kim , Minsang Kim , Jaeheon Lee , Chanwoo Moon , Heejin Kim , Taeho Hwang , Woosuk Chung , Yeseong Kim , Sungjin Lee

Modern deployment of large language models (LLMs) frequently involves both inference serving and continuous retraining to stay aligned with evolving data and user feedback. Common practices separate these workloads onto distinct servers in…

Artificial Intelligence · Computer Science 2025-07-30 Yufei Li , Zexin Li , Yinglun Zhu , Cong Liu

To mitigate the trade-offs between performance and costs, LLM providers route user tasks to different models based on task difficulty and latency. We study the effect of LLM routing with respect to user behavior. We propose a game between…

Computer Science and Game Theory · Computer Science 2026-02-11 Rafid Mahmood

Emerging intelligent service scenarios in 6G communication impose stringent requirements for low latency, high reliability, and privacy preservation. Generative large language models (LLMs) are gradually becoming key enablers for the…

Networking and Internet Architecture · Computer Science 2025-05-21 Pengyan Zhu , Tingting Yang

Query understanding is essential in modern relevance systems, where user queries are often short, ambiguous, and highly context-dependent. Traditional approaches often rely on multiple task-specific Named Entity Recognition models to…

Information Retrieval · Computer Science 2025-09-15 Ping Liu , Jianqiang Shen , Qianqi Shen , Chunnan Yao , Kevin Kao , Dan Xu , Rajat Arora , Baofen Zheng , Caleb Johnson , Liangjie Hong , Jingwei Wu , Wenjing Zhang

Large Language Models (LLMs) are becoming key components in various mobile operating systems, driving smart applications like interactive chatbots and personal assistants. While bringing enhanced intelligence to mobile ends, their…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-12 Genglin Wang , Liekang Zeng , Bufang Yang , Kaiwei Liu , Guoliang Xing , Chumin Sun , Li Zhou , Jie Sun , Zhenyu Yan

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,…

Multi-modal Large Language Models (MLLMs) serving systems commonly employ KV-cache compression to reduce memory footprint. However, existing compression methods introduce significant processing overhead and queuing delays, particularly in…

Multimedia · Computer Science 2025-03-12 Jianian Zhu , Hang Wu , Haojie Wang , Yinghui Li , Biao Hou , Ruixuan Li , Jidong Zhai

Table reasoning, which aims to generate the corresponding answer to the question following the user requirement according to the provided table, and optionally a text description of the table, effectively improving the efficiency of…

Computation and Language · Computer Science 2024-02-14 Xuanliang Zhang , Dingzirui Wang , Longxu Dou , Qingfu Zhu , Wanxiang Che

The rapid evolution of Large Language Models (LLMs) has markedly expanded their application across diverse domains, transforming how complex problems are approached and solved. Initially conceived to predict subsequent words in texts, these…

Artificial Intelligence · Computer Science 2024-07-11 Sumedh Rasal , E. J. Hauer

Currently, large language models (LLMs) predominantly focus on the text modality. To enable more natural human-AI interaction, speech LLMs are emerging, but building effective end-to-end speech LLMs remains challenging due to limited data…

Computation and Language · Computer Science 2026-04-14 Yan Zhou , Qingkai Fang , Yun Hong , Yang Feng