English
Related papers

Related papers: Hyperion: Hierarchical Scheduling for Parallel LLM…

200 papers

The impact of transformer networks is booming, yet, they come with significant computational complexity. It is therefore essential to understand how to optimally map and execute these networks on modern neural processor hardware. So far,…

Hardware Architecture · Computer Science 2024-06-17 Steven Colleman , Arne Symons , Victor J. B. Jung , Marian Verhelst

We present a shared-memory parallelization of flow-based refinement, which is considered the most powerful iterative improvement technique for hypergraph partitioning at the moment. Flow-based refinement works on bipartitions, so current…

Data Structures and Algorithms · Computer Science 2022-01-06 Lars Gottesbüren , Tobias Heuer , Peter Sanders

Large language models now serve millions of users daily, with providers incurring costs exceeding $700,000 per day. Each request requires token-by-token inference, making GPU scheduling central to latency, capacity, and cost. The difficulty…

Machine Learning · Computer Science 2026-05-18 Ruicheng Ao , Gan Luo , David Simchi-Levi , Xinshang Wang

The rapid evolution of Large Language Models (LLMs) towards long-context reasoning and sparse architectures has pushed memory requirements far beyond the capacity of individual device HBM. While emerging supernode architectures offer…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-04 Fangxin Liu , Qinghua Zhang , Hanjing Shen , Zhibo Liang , Li Jiang , Haibing Guan , Chong Bao , Xuefeng Jin

Pipeline parallelism (PP) has become a standard technique for scaling large language model (LLM) training across multiple devices. However, despite recent progress in reducing memory consumption through activation offloading, existing…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-08 Hongpei Li , Han Zhang , Huikang Liu , Dongdong Ge , Yinyu Ye

With the rapidly growing demand of graph processing in the real scene, they have to efficiently handle massive concurrent jobs. Although existing work enable to efficiently handle single graph processing job, there are plenty of memory…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-06-05 Jin Zhao

Large-scale cloud security platforms must continuously query millions of structured cloud resource records distributed across thousands of tenant accounts. Broad, account-spanning queries saturate database infrastructure, producing P95…

Databases · Computer Science 2026-04-22 Prashant Kumar Pathak , Chandra Biksheswaran Mouleeswaran , Rama Teja Repaka

Deploying million-token Large Language Models (LLMs) is challenging because production workloads are highly heterogeneous, mixing short queries and long documents. This heterogeneity, combined with the quadratic complexity of attention,…

Deploying deep learning (DL) models across multiple compute devices to train large and complex models continues to grow in importance because of the demand for faster and more frequent training. Data parallelism (DP) is the most widely used…

Machine Learning · Computer Science 2022-11-08 Saptadeep Pal , Eiman Ebrahimi , Arslan Zulfiqar , Yaosheng Fu , Victor Zhang , Szymon Migacz , David Nellans , Puneet Gupta

The rapid evolution of large language models (LLMs) has made geographically distributed training necessary due to GPU scarcity within a single cloud region. In such cross-region settings, Pipeline Parallelism (PP) is…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-26 Han Zhang , Jianchun Liu , Hongli Xu

Modern computing platforms tend to deploy multiple GPUs (2, 4, or more) on a single node to boost system performance, with each GPU having a large capacity of global memory and streaming multiprocessors (SMs). GPUs are an expensive…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-07-20 Chao Chen , Chris Porter , Santosh Pande

The growing demand for real-time DNN applications on edge devices necessitates faster inference of increasingly complex models. Although many devices include specialized accelerators (e.g., mobile GPUs), dynamic control-flow operators and…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-15 Chong Tang , Hao Dai , Jagmohan Chauhan

Scheduling deep learning (DL) models to train on powerful clusters with accelerators like GPUs and TPUs, presently falls short, either lacking fine-grained heterogeneity awareness or leaving resources substantially under-utilized. To fill…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-17 Abeda Sultana , Nabin Pakka , Fei Xu , Xu Yuan , Li Chen , Nian-Feng Tzeng

Hosting diverse large language model workloads in a unified resource pool through co-location is cost-effective. For example, long-running chat services generally follow diurnal traffic patterns, which inspire co-location of batch jobs to…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-11-19 Ping Zhang , Lei Su , Jinjie Yang , Xin Chen

The multi-level hp-refinement scheme is a powerful extension of the finite element method that allows local mesh adaptation without the trouble of constraining hanging nodes. This is achieved through hierarchical high-order overlay meshes,…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-12-05 John N. Jomo , Nils Zander , Mohamed Elhaddad , Ali Özcan , Stefan Kollmannsberger , Ralf-Peter Mundani , Ernst Rank

Table-text retrieval aims to retrieve relevant tables and text to support open-domain question answering. Existing studies use either early or late fusion, but face limitations. Early fusion pre-aligns a table row with its associated…

Databases · Computer Science 2026-03-04 Sungho Park , Joohyung Yun , Jongwuk Lee , Wook-Shin Han

The rapid adoption of large language models and multimodal foundation models has made multimodal data preparation pipelines critical AI infrastructure. These pipelines interleave CPU-heavy preprocessing with accelerator-backed (GPU/NPU/TPU)…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-03 Ding Pan , Zhuangzhuang Zhou , Long Qian , Binhang Yuan

This paper presents Nova, a real-time scheduling framework for serving agentic vision-language models (VLMs) on a single GPU with balanced per-request latency and overall request process throughput. Our design begins by enabling effective…

Operating Systems · Computer Science 2025-09-26 Yuhang Xu , Shengzhong Liu , Dong Zhang , Bingheng Yan , Fan Wu , Guihai Chen

Developing an efficient server-based real-time scheduling solution that supports dynamic task-level parallelism is now relevant to even the desktop and embedded domains and no longer only to the high performance computing market niche. This…

Distributed, Parallel, and Cluster Computing · Computer Science 2011-06-15 Luís Nogueira , Luís Miguel Pinho

Device-edge collaborative inference with Deep Neural Networks (DNNs) faces fundamental trade-offs among accuracy, latency and energy consumption. Current scheduling exhibits two drawbacks: a granularity mismatch between coarse, task-level…

Networking and Internet Architecture · Computer Science 2026-01-14 Zengzipeng Tang , Yuxuan Sun , Wei Chen , Jianwen Ding , Bo Ai , Yulin Shao