English
Related papers

Related papers: Improving Multi-Instance GPU Efficiency via Sub-En…

200 papers

Multi-Task Learning (MTL) enables multiple tasks to be learned within a shared network, but differences in objectives across tasks can cause negative transfer, where the learning of one task degrades another task's performance. While…

Machine Learning · Computer Science 2025-07-22 Wooseong Jeong , Kuk-Jin Yoon

Many real-world machine learning applications involve several learning tasks which are inter-related. For example, in healthcare domain, we need to learn a predictive model of a certain disease for many hospitals. The models for each…

Machine Learning · Computer Science 2016-10-03 Inci M. Baytas , Ming Yan , Anil K. Jain , Jiayu Zhou

Large language model (LLM) inference has been a prevalent demand in daily life and industries. The large tensor sizes and computing complexities in LLMs have brought challenges to memory, computing, and databus. This paper proposes a…

Hardware Architecture · Computer Science 2025-09-19 Yimin Wang , Yue Jiet Chong , Xuanyao Fong

Large language models have demonstrated extraordinary performance in many AI tasks but are expensive to use, even after training, due to their requirement of high-end GPUs. Recently, a distributed system called PETALS was developed to lower…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-30 Tingyang Sun , Ting He , Bo Ji , Parimal Parag

Multi-device inference can reduce Transformer latency by parallelizing computation. However, existing methods require high inter-device bandwidth, making them impractical for bandwidth-constrained environments. We present ASTRA, a…

Machine Learning · Computer Science 2026-05-28 Xiao Liu , Lijun Zhang , Deepak Ganesan , Hui Guan

A new flow solver scalable on multiple Graphics Processing Units (GPUs) for direct numerical simulation of wall-bounded incompressible flow is presented. This solver utilizes a previously reported work (J. Comp. Physics, vol. 352 (2018),…

Computational Physics · Physics 2018-12-05 Sanghyun Ha , Junshin Park , Donghyun You

Hardware peripherals such as GPUs and FPGAs are commonly available in server-grade computing to accelerate specific compute tasks, from database queries to machine learning. CSPs have integrated these accelerators into their infrastructure…

Cryptography and Security · Computer Science 2023-03-10 Thore Tiemann , Zane Weissman , Thomas Eisenbarth , Berk Sunar

Modern GPUs increasingly rely on specialized hardware units and asynchronous coordination mechanisms, so performance depends on orchestrating data movement, tensor-core computation, and synchronization rather than exposing more thread-level…

Mixed-integer programming (MIP) extends linear programming by incorporating both continuous and integer decision variables, making it widely used in production planning, logistics scheduling, and resource allocation. However, MIP remains…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-14 Jinyu Zhang , Di Huang , Yue Liu , Shuo Wang , Zhenyu Pu , Zhiyuan Liu

Graph-based ANNS algorithms have gained increasing research interest and market adoption due to their efficiency and accuracy in retrieval. Existing approaches primarily rely on CPUs for graph index construction and retrieval, but this…

Databases · Computer Science 2026-05-12 Lan Lu , Peiqi Yin , Isaac Yang , Tao Luo , Hua Fan , Wenchao Zhou , Feifei Li , Boon Thau Loo

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

As large language models (LLMs) grow in popularity for their diverse capabilities, improving the efficiency of their inference systems has become increasingly critical. Batching LLM requests is a critical step in scheduling the inference…

Computation and Language · Computer Science 2024-12-09 Ozgur Guldogan , Jackson Kunde , Kangwook Lee , Ramtin Pedarsani

Online optimization of resource management for large-scale data centers and infrastructures to meet dynamic capacity reservation demands and various practical constraints (e.g., feasibility and robustness) is a very challenging problem.…

Networking and Internet Architecture · Computer Science 2024-10-18 Chang-Lin Chen , Hanhan Zhou , Jiayu Chen , Mohammad Pedramfar , Tian Lan , Zheqing Zhu , Chi Zhou , Pol Mauri Ruiz , Neeraj Kumar , Hongbo Dong , Vaneet Aggarwal

In this new version of ZMCintegral, we have added the functionality of multi-function integrations, i.e. the ability to integrate more than $10^{3}$ different functions on GPUs. The Python API remains the similar as the previous versions.…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-09-19 Xiao-Yan Cao , Jun-Jie Zhang

Efficient deployment of a pre-trained LLM to a cluster with multiple servers is a critical step for providing fast responses to users' queries. The recent success of Mixture-of-Experts (MoE) LLMs raises the question of how to deploy them…

Networking and Internet Architecture · Computer Science 2025-08-14 Danil Sivtsov , Aleksandr Katrutsa , Ivan Oseledets

Bit-serial Processing-In-Memory (PIM) is an attractive paradigm for accelerator architectures, for parallel workloads such as Deep Learning (DL), because of its capability to achieve massive data parallelism at a low area overhead and…

Hardware Architecture · Computer Science 2023-11-21 Aman Arora , Jian Weng , Siyuan Ma , Tony Nowatzki , Lizy K. John

Modern distributed machine learning (ML) training workloads benefit significantly from leveraging GPUs. However, significant contention ensues when multiple such workloads are run atop a shared cluster of GPUs. A key question is how to…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-10-30 Kshiteej Mahajan , Arjun Balasubramanian , Arjun Singhvi , Shivaram Venkataraman , Aditya Akella , Amar Phanishayee , Shuchi Chawla

Real-world node embedding applications often contain hundreds of billions of edges with high-dimension node features. Scaling node embedding systems to efficiently support these applications remains a challenging problem. In this paper we…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-08-19 Wanjing Wei , Yangzihao Wang , Pin Gao , Shijie Sun , Donghai Yu

A long-standing goal in both industry and academia is to develop an LLM inference platform that is portable across hardware architectures, eliminates the need for low-level hand-tuning, and still delivers best-in-class efficiency. In this…

Machine Learning · Computer Science 2025-11-18 Burkhard Ringlein , Jan van Lunteren , Radu Stoica , Thomas Parnell

We present MT-lib, an efficient message transfer library for messages gather and scatter in benchmarks like Graph500 for Supercomputers. Our library includes MST version as well as new-MST version. The MT-lib is deliberately kept…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-03-30 Xinbiao Gan , Wen Tan