English
Related papers

Related papers: ThunderServe: High-performance and Cost-efficient …

200 papers

Production LLM serving must simultaneously deliver high throughput, low latency, and sufficient context capacity under non-stationary traffic and mixed request requirements. Data parallelism (DP) maximizes throughput by running independent…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-03 Shouwei Gao , Junqi Yin , Feiyi Wang , Wenqian Dong

Big data processing applications are becoming more and more complex. They are no more monolithic in nature but instead they are composed of decoupled analytical processes in the form of a workflow. One type of such workflow applications is…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-12-19 Mutaz Barika , Saurabh Garg , Andrew Chan , Rodrigo N. Calheiros

Large Language Models (LLMs) for Generative AI have achieved remarkable progress, evolving into sophisticated and versatile tools widely adopted across various domains and applications. However, the substantial memory overhead caused by…

Computation and Language · Computer Science 2025-04-29 Ranran Zhen , Juntao Li , Yixin Ji , Zhenlin Yang , Tong Liu , Qingrong Xia , Xinyu Duan , Zhefeng Wang , Baoxing Huai , Min Zhang

Prompts to large language models (LLMs) have evolved beyond simple user questions. For LLMs to solve complex problems, today's practices are to include domain-specific instructions, illustration of tool usages, and/or long context such as…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-10-04 Vikranth Srivatsa , Zijian He , Reyna Abhyankar , Dongming Li , Yiying Zhang

Context retrieval systems for LLM inference face a critical challenge: high retrieval latency creates a fundamental tension between waiting for complete context (poor time-to-first-token) and proceeding without it (reduced quality).…

Databases · Computer Science 2026-05-19 Rajveer Bachkaniwala , Chengqi Luo , Richard So , Divya Mahajan , Kexin Rong

Large language model (LLM) inference is limited by high computational cost and memory bandwidth demands, making deployment on heterogeneous many-core processors challenging. Taking the MT-3000 processor used in the Tianhe supercomputer as…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-26 Yao Lu , Zhongzhi Luan , Gen Li , Jiaxing Qi , Shiqing Ma , Bin Han , Shizhe Shang , Hailong Yang , Depei Qian

Machine learning algorithms must be able to efficiently cope with massive data sets. Therefore, they have to scale well on any modern system and be able to exploit the computing power of accelerators independent of their vendor. In the…

Machine Learning · Computer Science 2022-09-07 Alexander Van Craen , Marcel Breyer , Dirk Pflüger

Training large language models (LLMs) is a computationally intensive task, which is typically conducted in data centers with homogeneous high-performance GPUs. In this paper, we explore an alternative approach by deploying training…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-14 Ran Yan , Youhe Jiang , Xiaonan Nie , Fangcheng Fu , Bin Cui , Binhang Yuan

The rapid advancement of Large Language Models (LLMs) has driven the need for more efficient serving strategies. In this context, efficiency refers to the proportion of requests that meet their Service Level Objectives (SLOs), particularly…

Artificial Intelligence · Computer Science 2025-05-01 Azam Ikram , Xiang Li , Sameh Elnikety , Saurabh Bagchi

We present a number of novel algorithms, based on mathematical optimization formulations, in order to solve a homogeneous multiprocessor scheduling problem, while minimizing the total energy consumption. In particular, for a system with a…

Operating Systems · Computer Science 2015-11-13 Mason Thammawichai , Eric C. Kerrigan

Multi-turn dialogues are essential in many real-world applications of large language models, such as chatbots and virtual assistants. As conversation histories become longer, existing large language models face increasing computational and…

Computation and Language · Computer Science 2025-09-29 Haoyang Li , Zhanchao Xu , Yiming Li , Xuejia Chen , Darian Li , Anxin Tian , Qingfa Xiao , Cheng Deng , Jun Wang , Qing Li , Lei Chen , Mingxuan Yuan

Cloud computing has revolutionized the way organizations manage their IT infrastructure, but it has also introduced new challenges, such as managing cloud costs. The rapid adoption of artificial intelligence (AI) and machine learning (ML)…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-01-28 Saurabh Deochake

Recent innovation in large language models (LLMs), and their myriad use-cases have rapidly driven up the compute capacity demand for datacenter GPUs. Several cloud providers and other enterprises have made substantial plans of growth in…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-08-25 Pratyush Patel , Esha Choukse , Chaojie Zhang , Íñigo Goiri , Brijesh Warrier , Nithish Mahalingam , Ricardo Bianchini

Efficient execution of deep learning workloads on dataflow architectures is crucial for overcoming memory bottlenecks and maximizing performance. While streaming intermediate results between computation kernels can significantly improve…

Hardware Architecture · Computer Science 2025-09-24 Hanchen Ye , Deming Chen

CPUs are critical for LLM serving due to their availability, cost efficiency, and edge applicability. However, efficient CPU serving is hindered by conflicting prefill/decode resource demands under non-disaggregated deployment…

Hardware Architecture · Computer Science 2026-04-16 Juntao Zhao , Jiuru Li , Chuan Wu

Modern cloud platforms increasingly host large-scale deep learning (DL) workloads, demanding high-throughput, low-latency GPU scheduling. However, the growing heterogeneity of GPU clusters and limited visibility into application…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-12 Shruti Dongare , Redwan Ibne Seraj Khan , Hadeel Albahar , Nannan Zhao , Diego Melendez Maita , Ali R. Butt

Deploying modern Speech Language Models (SpeechLMs) in streaming settings requires systems that provide low latency, high throughput, and strong guarantees of streamability. Existing systems fall short of supporting diverse models flexibly…

Machine Learning · Computer Science 2026-02-03 Keisuke Kamahori , Wei-Tzu Lee , Atindra Jha , Rohan Kadekodi , Stephanie Wang , Arvind Krishnamurthy , Baris Kasikci

Large language models (LLMs) have been a disruptive innovation in recent years, and they play a crucial role in our daily lives due to their ability to understand and generate human-like text. Their capabilities include natural language…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-10-17 Akrit Mudvari , Yuang Jiang , Leandros Tassiulas

Serving Large Language Models (LLMs) in production faces significant challenges from highly variable request patterns and severe resource fragmentation in serverless clusters. Current systems rely on static pipeline configurations that…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-12 Yanying Lin , Shijie Peng , Chengzhi Lu , Chengzhong Xu , Kejiang Ye

Generative conversational interfaces powered by large language models (LLMs) typically stream output token-by-token at a rate determined by computational budget, often neglecting actual human reading speeds and the cognitive load associated…

Human-Computer Interaction · Computer Science 2025-07-25 Chang Xiao , Brenda Yang