about
Minions: Dynamic, Distributed VGPU Cloud Built on Idle Apple Silicon Devices (arxiv.org)
2 points by gmays 34 days ago | hide | past | pdf | 1 comment on HN

In plain words: Minions pools the idle graphics chips in a team's Mac computers into one shared cloud that runs AI jobs, splitting work across machines and keeping going if one drops out. It handled real workloads without buying new GPUs, unlike renting scarce centralized ones.

Abstract · Minions: A Dynamic and Distributed Virtual GPU Cloud Built on Idle Apple Silicon Devices

The increasing demand for GPU-accelerated machine learning inference has exposed limitations in centralized GPU infrastructures, including high cost, limited elasticity, and long wait times under resource constraints. At the same time, modern Apple Silicon-based macOS devices are equipped with powerful GPUs that remain largely idle during normal usage. This paper presents Minions, a dynamic and distributed virtual GPU cloud that aggregates idle Apple Silicon GPUs across macOS devices to execute large-scale machine learning inference workloads. Minions enables teams to leverage existing hardware without requiring additional GPU procurement. The system provides flexible GPU inference task execution, fault tolerance, and efficient resource utilization. Our experience shows that idle macOS devices can be transformed into a practical distributed GPU inference platform in environments where centralized GPU resources are constrained.

Jianhua Li, Yun Xing, Girisha De Silva, Ryan Flint, Kai Yuan, Sean Suchter
arXiv:2610.12970 · cs.DC, cs.LG · submitted Oct 9, 2026
abstract · pdf · html · 3 pages, 1 figure, 1 table

add comment on HN
Also discussed: Oct 2026 (1 point, 1 comment)