Foundation models (FMs) are increasingly used as backbones for downstream tasks across language, vision, time-series, and multimodal applications. Yet existing model-serving systems deploy each customized task as an independent model instance, thereby replicating heavyweight backbones, wasting accelerator memory, and losing opportunities to amortize batching and loading costs. This paper presents FMplex, a serving system that treats FM backbones as a virtualization substrate for deployment sharing. FMplex presents each task with a virtual foundation model (vFM), a logically private FM instance backed by a shared physical FM. This abstraction lets independently customized tasks share a backbone while preserving task-specific extensions, independent lifecycles, and task-level isolation. In addition, we propose a batch-aware fair-queueing scheduler that combines weighted task-level sharing with inter- and intra-task batching across colocated tasks. We implement a FMplex-based serving stack spanning task construction, sharing-aware deployment, and runtime execution. Across 7 FM backbones (16 variants) and 92 downstream tasks, FMplex reduces latency by up to 80% over spatial partitioning and 33.3% over best-effort co-location, while hosting up to 6x more tasks at cluster scale.

翻译：基础模型（FM）正越来越多地作为下游任务的主干网络，广泛应用于语言、视觉、时间序列及多模态场景。然而，现有模型服务系统将每个定制任务部署为独立模型实例，导致重型主干网络的重复部署，浪费加速器内存，并错失聚合批处理与加载成本的机遇。本文提出FMplex——一种将FM主干网络视为部署共享的虚拟化基础的服务系统。FMplex为每个任务提供虚拟基础模型（vFM），即由共享物理FM支持的逻辑私有FM实例。这一抽象让独立定制的任务在共享主干网络的同时，保留任务专属扩展、独立生命周期与任务级隔离。此外，我们提出一种批感知公平排队调度器，融合加权任务级共享与跨共置任务的内部及任务间批处理。我们实现了一套基于FMplex的服务栈，覆盖任务构建、共享感知部署与运行时执行。在7个FM主干网络（16个变体）及92个下游任务上，FMplex相较空间划分降低高达80%延迟，相较尽力而为共置降低33.3%延迟，同时集群规模下可承载多达6倍的任务数。