Saturn Cloud Integrates NVIDIA Run:ai to Enhance GPU Utilization for Inference Services
Saturn Cloud has integrated NVIDIA Run:ai's AI workload and GPU orchestration platform into its multi-tenant inference solution. This integration allows cloud operators to monetize their existing NVIDIA GPU fleets more effectively by converting raw computing capacity into per-token services, which can be sold under the operator’s brand without requiring in-house development. The partnership leverages NVIDIA Run:ai's KAI Scheduler and Grove orchestration tools to maximize GPU utilization across distributed workloads. Saturn Cloud provides a commercial layer that enables operators to offer various AI-related products—such as per-token inference endpoints, managed fine-tuning jobs, or dedicated GPU capacity—all from the same infrastructure. The integration supports NVIDIA Dynamo for distributed inference and includes enterprise-grade features like model onboarding, identity controls, and fleet health monitoring. The platform is now available, with Saturn Cloud positioning itself as a key enabler of AI-as-a-service in both public and private cloud environments.
Tickers: $NVDA
Topics: DSX AI Factory Platform GPU orchestration multi-tenant inference platform NVIDIA Saturn Cloud