English
Related papers

Related papers: Coral: Cost-Efficient Multi-LLM Serving over Heter…

200 papers

Low-Rank Adaptation (LoRA) has become the de facto method for parameter-efficient fine-tuning of large language models (LLMs), enabling rapid adaptation to diverse domains. In production, LoRA-based models are served at scale, creating…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-01 Shashwat Jaiswal , Shrikara Arun , Anjaly Parayil , Ankur Mallick , Spyros Mastorakis , Alind Khare , Chloi Alverti , Renee St Amant , Chetan Bansal , Victor Rühle , Josep Torrellas

Both the training and use of Large Language Models (LLMs) require large amounts of energy. Their increasing popularity, therefore, raises critical concerns regarding the energy efficiency and sustainability of data centers that host them.…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-07-02 Grant Wilkins , Srinivasan Keshav , Richard Mortier

GPUs are now used for a wide range of problems within HPC. However, making efficient use of the computational power available with multiple GPUs is challenging. The main challenges in achieving good performance are memory layout, affecting…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-04-20 Robert Clucas , Philip Blakely , Nikolaos Nikiforakis

Large language models (LLMs) require vast amounts of GPU compute to train, but limited availability and high costs of GPUs make homogeneous clusters impractical for many organizations. Instead, assembling heterogeneous clusters by pooling…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-15 Runsheng Benson Guo , Utkarsh Anand , Khuzaima Daudjee , Rathijit Sen

Large language models (LLMs) are transforming society, powering applications from smartphone assistants to autonomous driving. Yet cloud-based LLM services alone cannot serve a growing class of applications, including those operating under…

Signal Processing · Electrical Eng. & Systems 2026-05-12 Liangqi Yuan , Wenzhi Fang , Shiqiang Wang , H. Vincent Poor , Christopher G. Brinton

Serving generative inference of the large language model is a crucial component of contemporary AI applications. This paper focuses on deploying such services in a heterogeneous and cross-datacenter setting to mitigate the substantial…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-05-28 Youhe Jiang , Ran Yan , Xiaozhe Yao , Yang Zhou , Beidi Chen , Binhang Yuan

Large-scale machine learning workloads increasingly rely on multi-GPU systems, yet their performance is often limited by an overlooked component: the CPU. Through a detailed study of modern large language model (LLM) inference and serving…

Hardware Architecture · Computer Science 2026-05-26 Euijun Chung , Yuxiao Jia , Aaron Jezghani , Hyesoon Kim

Existing large language model (LLM) serving systems fall into two categories: 1) a unified system where prefill phase and decode phase are co-located on the same GPU, sharing the unified computational resource and storage, and 2) a…

Computation and Language · Computer Science 2025-04-29 Ke Hong , Lufang Chen , Zhong Wang , Xiuhong Li , Qiuli Mao , Jianping Ma , Chao Xiong , Guanyu Wu , Buhe Han , Guohao Dai , Yun Liang , Yu Wang

In cloud machine learning (ML) inference systems, providing low latency to end-users is of utmost importance. However, maximizing server utilization and system throughput is also crucial for ML service providers as it helps lower the…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-03-01 Yunseong Kim , Yujeong Choi , Minsoo Rhu

The growing demand for large-scale GPU clusters in distributed model training presents a significant barrier to innovation, particularly in model optimization, performance tuning, and system-level enhancements. To address this challenge,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-08-08 Sumit Kumar , Arjun Temura , Naman Sharma , Ramanjeet Singh , Meet Dadhania , Praveen Tammana , Satananda Burla , Abed Mohammad Kamaluddin , Rinku Shah

Training transformer models requires substantial GPU compute and memory resources. In homogeneous clusters, distributed strategies allocate resources evenly, but this approach is inefficient for heterogeneous clusters, where GPUs differ in…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-11-15 Runsheng Benson Guo , Utkarsh Anand , Arthur Chen , Khuzaima Daudjee

Modern computer systems typically conbine multicore CPUs with accelerators like GPUs for inproved performance and energy efficiency. However, these sys- tems suffer from poor performance portability, code tuned for one device must be…

Distributed, Parallel, and Cluster Computing · Computer Science 2016-05-23 Thomas L. Falch , Anne C. Elster

Large language model (LLM) serving is becoming an increasingly critical workload for cloud providers. Existing LLM serving systems focus on interactive requests, such as chatbots and coding assistants, with tight latency SLO requirements.…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-02-26 Archit Patke , Dhemath Reddy , Saurabh Jha , Haoran Qiu , Christian Pinto , Chandra Narayanaswami , Zbigniew Kalbarczyk , Ravishankar Iyer

Large language models (LLMs) are increasingly deployed as the execution core of autonomous agents rather than as standalone text generators. Agentic workloads induce a temporal shift from single-turn inference to multi-turn LLM-tool loops,…

Operating Systems · Computer Science 2026-05-01 Yifei Wang , Hancheng Ye , Yechen Xu , Cong Guo , Chiyue Wei , Qinsi Wang , Dongting Li , Tingjun Chen , Hai "Helen" Li , Danyang Zhuo , Yiran Chen

Serverless Large Language Models (LLMs) have emerged as a cost-effective solution for deploying AI services by enabling a 'pay-as-you-go' pricing model through GPU resource sharing. However, cold-start latency, especially the model loading…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-02 Wenbin Zhu , Zhaoyan Shen , Zili Shao , Hongjun Dai , Feng Chen

This paper investigates the optimal allocation of large language model (LLM) inference workloads across heterogeneous edge data centers over time. Each data center features on-site renewable generation and faces dynamic electricity prices…

Networking and Internet Architecture · Computer Science 2026-04-10 Jiaming Cheng , Duong Tung Nguyen

In this paper, we consider a mixed-prompt scenario for a large language model (LLM) inference serving system that supports diverse applications with both short prompts and long prompts and heterogeneous SLOs for iteration time. To improve…

Computation and Language · Computer Science 2025-03-19 Haiying Shen , Tanmoy Sen

In recent times, the emergence of Large Language Models (LLMs) has resulted in increasingly larger model size, posing challenges for inference on low-resource devices. Prior approaches have explored offloading to facilitate low-memory…

Performance · Computer Science 2024-03-05 Xuanlei Zhao , Bin Jia , Haotian Zhou , Ziming Liu , Shenggan Cheng , Yang You

Nowadays, many companies possess various types of AI accelerators, forming heterogeneous clusters. Efficiently leveraging these clusters for high-throughput large language model (LLM) inference services can significantly reduce costs and…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-23 Yi Xiong , Jinqi Huang , Wenjie Huang , Xuebing Yu , Entong Li , Zhixiong Ning , Jinhua Zhou , Li Zeng , Xin Chen

The deployment of mixture-of-experts (MoE) large language models (LLMs) presents significant challenges due to their high memory demands. These challenges become even more pronounced in multi-tenant environments, where shared resources must…

Machine Learning · Computer Science 2025-05-13 HamidReza Imani , Jiaxin Peng , Peiman Mohseni , Abdolah Amirany , Tarek El-Ghazawi