为了让员工更便捷地访问GPU资源以执行推理任务，苹果公司整合了它的“小黄人”——这里指的不是动画片中的黄色小生物，而是一个分布式系统，它利用Mac设备上闲置的GPU来处理AI工作负载。苹果研究人员将其描述为：“一种动态且分布式的虚拟GPU云，能够聚合macOS设备上闲置的Apple Silicon GPU，以执行大规模机器学习推理工作负载。”
In an effort to give its employees better access to GPU resources for inference tasks, Apple has rounded up its Minions, not the animated yellow creatures, but a distributed system that puts idle GPUs across its Macs to work on AI workloads. Apple researchers describe it as "a dynamic and distributed virtual GPU cloud that aggregates idle Apple Silicon GPUs across macOS devices to execute large-scale machine learning inference workloads."
苹果研究人员表示，公司已通过“小黄人”让GPU计算资源更易于团队使用。该论文中解释道：“在采用之前，由于中心化GPU资源有限，某些推理任务的排队时间曾超过十小时。”而“有了‘小黄人’，任务通常可以在几分钟内开始执行，通过利用闲置的macOS设备。”苹果最近发布的Mac mini和Mac Studio支持通过Thunderbolt 5使用RDMA（远程直接内存访问）进行集群，使得计算和内存可以结合，以支持单个AI工作负载。
Apple's researchers said the company has used Minions to make GPU compute more readily available to its teams. "Prior to its adoption, some inference jobs experienced queue times exceeding ten hours due to limited centralized GPU availability," the paper on Minions explains. "With Minions, tasks can often begin execution within minutes by leveraging idle macOS devices." Apple's recently released Mac mini and Mac Studio support clustering using RDMA (Remote Direct Memory Access) over Thunderbolt 5, allowing compute and memory to be combined to support a single AI workload.
例如，这使得可以加载单台机器无法容纳的过大模型。“小黄人”旨在通过连接的Mac硬件创建一个虚拟GPU云，在共享的分布式推理平台中构建一个容错的推理工作节点池。因此，GPU资源不再闲置，网络上的团队可以更便捷地使用它们。它并不一定旨在像运行大模型那样使用，而是为了重新分配网络上的闲置资源。“小黄人”包含四个主要组件：小黄人服务器、PostgreSQL元数据存储、小黄人执行器和小黄人看门狗。
This allows, for example, loading a model too large for a single machine to accommodate. Minions is designed to create a virtual GPU cloud from connected Mac hardware to create a fault-tolerant pool of inference workers in a shared distributed inference platform. So instead of sitting idle, GPU resources can be used more readily by teams on the network. It's not necessarily intended as a way to run large models as much as it is to redistribute idle resources on the network. Minions has four primary components: Minion Server, PostgreSQL Metadata Store, Minion Executor, and Minion Watchdog.
小黄人服务器提供协调层，接收用户请求并将其作为子任务提供。小黄人执行器在Mac的GPU上运行推理任务，将结果上传至S3，并通过小黄人服务器报告执行状态，而小黄人服务器则在PostgreSQL中维护任务元数据。
The Minion Server provides the coordination layer, receiving user requests and making them available as subtasks. The Minion Executor runs inference tasks on a Mac's GPU, uploads the results to S3, and reports execution status through the Minion Server, which maintains task metadata in PostgreSQL.
而 Minion Watchdog 会监控此过程中的故障 — — 比如网络中的某台 Mac 没有响应 — — 并在必要时重新分配任务。数据库统计信息会被送入基于 Grafana 的仪表盘，以实现实时可见性。苹果的方法侧重于硬件的可用性和利用率，这与 Nvidia 集群不同，后者侧重于吞吐量、延迟以及大型模型的高效 GPU 利用率。®
And the Minion Watchdog monitors this process for failures – like one of the Macs in the network not responding – and re-assigns tasks if needed. Database stats get fed to Grafana-based dashboards for real-time visibility. Apple's approach, which focuses on hardware availability and utilization, is not the same as an Nvidia cluster, which focuses on throughput, latency, and efficient GPU utilization for large models. ®