English
Related papers

Related papers: Efficient Interactive LLM Serving with Proxy Model…

200 papers

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 models (LLMs) achieve state-of-the-art accuracy on complex reasoning tasks by generating multiple chain-of-thought (CoT) traces, but using a fixed token budget per query leads to over-computation on easy inputs and…

Artificial Intelligence · Computer Science 2026-02-03 Katrina Brown , Aneesh Muppidi , Rana Shahout

The increasing adoption of large language models (LLMs) necessitates inference serving systems that can deliver both high throughput and low latency. Deploying LLMs with hundreds of billions of parameters on memory-constrained GPUs exposes…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-10 Bowen Pang , Kai Li , Feifan Wang

We consider a single-server queue with renewal arrivals and i.i.d. service times, in which the server employs either the preemptive Shortest Remaining Processing Time (SRPT) policy, or its non-preemptive variant, Shortest Job First (SJF).…

Probability · Mathematics 2010-07-16 H. Christian Gromoll , Martin Keutel

Large language models (LLMs) have become increasingly popular in various areas, traditional business gradually shifting from rule-based systems to LLM-based solutions. However, the inference of LLMs is resource-intensive or…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-01-06 Wanyi Zheng , Minxian Xu , Shengye Song , Kejiang Ye

Large Language Model (LLM)-based search agents have shown remarkable capabilities in solving complex tasks by dynamically decomposing problems and addressing them through interleaved reasoning and retrieval. However, this interleaved…

Artificial Intelligence · Computer Science 2025-05-20 Tiannuo Yang , Zebin Yao , Bowen Jin , Lixiao Cui , Yusen Li , Gang Wang , Xiaoguang Liu

While LLMs have demonstrated remarkable potential in time series forecasting, their practical deployment remains constrained by excessive computational demands and memory footprints. Existing LLM-based approaches typically suffer from three…

Computation and Language · Computer Science 2025-03-11 Haoran Fan , Bin Li , Yixuan Weng , Shoujun Zhou

Recent advances with large language models (LLM) illustrate their diverse capabilities. We propose a novel algorithm, staged speculative decoding, to accelerate LLM inference in small-batch, on-device scenarios. We address the low…

Artificial Intelligence · Computer Science 2023-08-10 Benjamin Spector , Chris Re

The need to recognise long-term dependencies in sequential data such as video streams has made Long Short-Term Memory (LSTM) networks a prominent Artificial Intelligence model for many emerging applications. However, the high computational…

Signal Processing · Electrical Eng. & Systems 2019-10-31 Alexandros Kouris , Stylianos I. Venieris , Michail Rizakis , Christos-Savvas Bouganis

Large Language Models (LLMs) are machine learning models that have seen widespread adoption due to their capability of handling previously difficult tasks. LLMs, due to their training, are sensitive to how exactly a question is presented,…

Software Engineering · Computer Science 2025-12-22 Jae Yong Lee , Sungmin Kang , Shin Yoo

This paper presents ServerlessLLM, a distributed system designed to support low-latency serverless inference for Large Language Models (LLMs). By harnessing the substantial near-GPU storage and memory capacities of inference servers,…

Machine Learning · Computer Science 2024-07-26 Yao Fu , Leyang Xue , Yeqi Huang , Andrei-Octavian Brabete , Dmitrii Ustiugov , Yuvraj Patel , Luo Mai

The scaling of transformer-based Large Language Models (LLMs) has significantly expanded their context lengths, enabling applications where inputs exceed 100K tokens. Our analysis of a recent Azure LLM inference trace reveals a highly…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-10 Zeyu Zhang , Haiying Shen

Emergency situations in scheduling systems often trigger local functional failures that undermine system stability and even cause system collapse. Existing methods primarily rely on robust scheduling or reactive scheduling, handling…

Artificial Intelligence · Computer Science 2026-04-14 Shixing Zhao , Zheng Si , Pengpeng Ouyang , Zhengqing Hu , Wanqi Zhu , Dong Chen , Yibo Guo , Mingliang Xu

The World Wide Web needs reliable predictive capabilities to respond to changes in user behavior and usage patterns. Time series forecasting (TSF) is a key means to achieve this goal. In recent years, the large language models (LLMs) for…

Machine Learning · Computer Science 2026-01-23 Jianqi Zhang , Jingyao Wang , Wenwen Qiang , Fanjiang Xu , Changwen Zheng

Agentic workflows are composed of sequences of interdependent Large Language Model (LLM) calls, and they have become a dominant workload in modern AI systems. These workflows exhibit extensive redundancy from overlapping prompts and…

Multiagent Systems · Computer Science 2026-03-18 Noppanat Wadlom , Junyi Shen , Yao Lu

With the growing use of Large Language Model (LLM)-based tools like ChatGPT, Perplexity, and Gemini across industries, there is a rising need for efficient LLM inference systems. These systems handle requests with a unique two-phase…

Machine Learning · Computer Science 2025-12-02 Agrim Bari , Parikshit Hegde , Gustavo de Veciana

Each LLM serving request goes through two phases. The first is prefill which processes the entire input prompt and produces the first output token and the second is decode which generates the rest of output tokens, one-at-a-time. Prefill…

This review report discusses the cold start latency in serverless inference and existing solutions. It particularly reviews the ServerlessLLM method, a system designed to address the cold start problem in serverless inference for large…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-11-26 Himel Ghosh

Efficient LLM inference scheduling is crucial for user experience. However, LLM inferences exhibit remarkable demand uncertainty (with unknown output length beforehand) and hybridity (being both compute and memory intensive). Existing LLM…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-16 Zhenghao Gan , Yichen Bao , Yifei Liu , Chen Chen , Quan Chen , Minyi Guo

As augmented large language models (LLMs) with external tools become increasingly popular in web applications, improving augmented LLM inference serving efficiency and optimizing service-level objectives (SLOs) are critical for enhancing…

Computation and Language · Computer Science 2025-12-17 Ying Wang , Zhen Jin , Jiexiong Xu , Wenhai Lin , Yiquan Chen , Wenzhi Chen