发表机构
North Carolina State University（北卡罗来纳州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出的\textbf{\textsc{Centile}}是首个经重放评估可改善HPC调度与网络配置决策的预训练遥测基础模型，可降低HPC回填平均有界减速约77%、违规率减半。
AI 中文摘要
现代计算与网络基础设施持续产生遥测数据，但运维人员需针对每个任务、实体和时间范围使用单独的预测器将其转化为决策。一种在运维人员自身事件流上预训练一次的生成式模型可替代这组预测器，该方法已在推荐系统中扩展至高基数流。然而，运维遥测的点预测误差接近简单的最后值基线后便趋于饱和，因此仅降低误差未必能改善其支撑的决策。为填补这一差距，我们提出\textbf{\textsc{Centile}}，一种网络与系统遥测的生成式基础模型，通过重放其校准条件分位数所驱动的决策进行评估。\textbf{\textsc{Centile}}将异构遥测视为事件驱动、时间不规则的实体流，单次推理即可提供灵活的预测时间范围，无需未来时间戳。据我们所知，\textbf{\textsc{Centile}}是首个经重放评估可同时改善HPC调度与网络配置决策的预训练遥测模型，其运行时估计器可在数月间零样本迁移，预训练权重可在仅数小时目标数据的跨域间迁移。针对HPC作业日志与网络流量的大量实验证实，\textbf{\textsc{Centile}}相较已部署的用户估计，将回填的平均有界减速降低了约77%，并将已部署规则的违规率减半。我们的代码可在此处获取：this https URL
英文摘要
Modern computing and networking infrastructure emits telemetry continuously, yet operators convert it into decisions with a separate predictor per task, entity, and horizon. One generative model, pretrained once over an operator's own event streams, could replace this fleet, an approach that already scales to high-cardinality streams in recommendation systems. However, point-forecast error on operational telemetry saturates near simple last-value baselines, so lower error alone need not improve the decisions it feeds. To close this gap, we present \sys, a generative foundation model for network and systems telemetry, evaluated by replaying the decisions its calibrated conditional quantiles drive. \sys treats heterogeneous telemetry as event-driven, irregularly timed entity streams and serves flexible forecast horizons in a single pass, requiring no future timestamps. To our knowledge, \sys is the first pretrained telemetry model to improve both HPC scheduling and network provisioning decisions under replay, its runtime estimator transferring zero-shot across months and its pretrained weights across domains from hours of target data. Extensive experiments on HPC job logs and network traffic confirm that \sys lowers the mean bounded slowdown of backfilling by up to approximately $77\%$ over deployed user estimates and roughly halves the deployed rule's violation rate. Our code is available at https://github.com/ZzZTripleZzZ/all-in-one.
