EPIC：用于加速HPC运维数据分析的生成式AI平台
EPIC: Generative AI Platform for Accelerating HPC Operational Data Analytics
AI总结：
本文提出EPIC平台，通过分层多智能体架构结合大语言模型与专用分析智能体，实现对HPC多模态运维数据的动态分析，并在Frontier系统上验证了其高准确率与显著成本节省。
摘要：
我们提出EPIC，一个旨在增强运维数据分析的AI驱动平台。EPIC采用分层多智能体架构，其中顶层大语言模型提供查询处理、推理和综合能力。这些能力协调三个专用底层智能体，分别用于信息检索、描述性分析和预测性分析。该架构使EPIC能够对多模态数据（包括文本、图像和表格格式）动态且迭代地执行HPC运维分析。EPIC解决了现有HPC运维分析方法的局限性，这些方法依赖静态手段，难以适应不断演化的分析任务和利益相关者需求。通过在Frontier HPC系统上的广泛评估，我们证明EPIC能够有效处理复杂查询。以描述性分析为用例，微调后的小型模型优于大型最先进基础模型，准确率最高提升26%。此外，通过采用将大型基础模型与微调后的本地开放权重模型相结合的混合方法，与专有解决方案相比，我们在大语言模型运维成本上实现了19倍的节省。
英文摘要：
We present EPIC, an AI-driven platform designed to augment operational data analytics. EPIC employs a hierarchical multi-agent architecture where a top-level large language model provides query processing, reasoning and synthesis capabilities. These capabilities orchestrate three specialized low-level agents for information retrieval, descriptive analytics, and predictive analytics. This architecture enables EPIC to perform HPC operational analytics on multi-modal data, including text, images, and tabular formats, dynamically and iteratively. EPIC addresses the limitations of existing HPC operational analytics approaches, which rely on static methods that struggle to adapt to evolving analytics tasks and stakeholder demands. Through extensive evaluations on the Frontier HPC system, we demonstrate that EPIC effectively handles complex queries. Using descriptive analytics as a use case, fine-tuned smaller models outperform large state-of-the-art foundation models, achieving up to 26% higher accuracy. Additionally, we achieved 19x savings in LLM operational costs compared to proprietary solutions by employing a hybrid approach that combines large foundational models with fine-tuned local open-weight models.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
