FaaSMoE让多租户专家模型按需调用，资源消耗不到传统方式的三分之一。
FaaSMoE: A Serverless Framework for Multi-Tenant Mixture-of-Experts Serving
- 将专家模型拆成无状态函数，按需启动、用完即停
- 在多租户场景下资源占用不足基线的1/3，支持弹性伸缩
- 适合需要低成本部署MoE模型的云服务或边缘计算场景
Mixture-of-Experts（MoE）模型通过仅激活少量专家实现高容量与低推理开销。但部署时需将所有专家常驻内存，导致实际使用资源远低于分配资源，多租户环境下问题更突出。本文提出FaaSMoE，一种基于函数即服务（FaaS）平台的多租户MoE服务架构。FaaSMoE通过将专家部署为无状态函数，解耦控制与执行平面，实现跨租户的按需、零扩展专家调用。同时支持函数内可配置专家粒度，在单个专家弹性与调用开销间权衡。我们基于开源边缘导向的FaaS平台实现了原型，并在Qwen1.5-moe-2.7B上评估了多租户负载下的表现。相比完整模型基线，FaaSMoE资源消耗不足其1/3，证明了其在多租户环境中可扩展、高效的可行性。
原文摘要 · Abstract (English)
Mixture-of-Experts (MoE) models offer high capacity with efficient inference cost by activating a small subset of expert models per input. However, deploying MoE models requires all experts to reside in memory, creating a gap between the resource used by activated experts and the provisioned resources. This underutilization is further pronounced in multi-tenant scenarios. In this paper, we propose FaaSMoE, a multi-tenant MoE serving architecture built on Function-as-a-Service (FaaS) platforms. FaaSMoE decouples the control and execution planes of MoE by deploying experts as stateless FaaS functions, enabling on-demand and scale-to-zero expert invocation across tenants. FaaSMoE further supports configurable expert granularity within functions, trading off per-expert elasticity for reduced invocation overhead. We implement a prototype with an open-source edge-oriented FaaS platform and evaluate it using Qwen1.5-moe-2.7B under multi-tenant workloads. Compared to a full-model baseline, FaaSMoE uses less than one third of the resources, demonstrating a practical and resource-efficient path towards scalable MoE serving in a multi-tenant environment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。