Today's inference-time workloads increasingly depend on timely access to a model's internal states. We present DMI-Lib, a high-speed deep model inspector that treats internal observability as a first-class systems primitive, decoupling it from the inference hot path via an asynchronous observability substrate built from Ring^2, a GPU-CPU memory abstraction for capturing and staging tensors, and a policy-controlled host backend that exports them. DMI-Lib enables the placement of observation points across a rich space of internal signals and diverse inference backends while preserving serving optimizations and adhering to tight GPU memory budgets. Our experiments demonstrate that DMI-Lib incurs only 0.4%--6.8% overhead in offline batch inference and an average of 6% in moderate online serving, reducing latency overhead by 2x-15x compared to existing baselines with similar observability features. DMI-Lib is open-sourced at https://github.com/ProjectDMX/DMI.

翻译：当前推理工作负载日益依赖于对模型内部状态的实时访问。本文提出DMI-Lib,一种高速深度模型检查器,将内部可观测性视为一级系统原语,通过异步可观测性子系统将其与推理热路径解耦。该子系统基于Ring²(一种用于捕获和暂存张量的GPU-CPU内存抽象)以及受策略控制的后端主机导出机制构建。DMI-Lib能够在丰富的内部信号空间和多样化推理后端中部署观测点,同时保持服务优化特性并遵守严格的GPU内存预算约束。实验表明,DMI-Lib在离线批量推理中仅引入0.4%至6.8%的开销,在中等在线服务场景下平均开销为6%,相较于具有相似可观测性功能的现有基线方案,延迟开销降低2至15倍。DMI-Lib已开源发布于https://github.com/ProjectDMX/DMI。