Hardware
Run Your Own Inference Stack on Vultr with Modelplane
Modelplane v0.3 adds Vultr Kubernetes Engine (VKE) as a fully‑managed inference cluster provider, allowing users to describe GPU clusters in YAML with region, node pool, instance class, and min/max sc
Modelplane v0.3 adds Vultr Kubernetes Engine (VKE) as a fully‑managed inference cluster provider, allowing users to describe GPU clusters in YAML with region, node pool, instance class, and min/max scaling limits; Modelplane automatically provisions the VPC, control plane, system and GPU node pools, and the inference stack for you. Because Modelplane uses a uniform resource model, deployment manifests are identical across providers (GKE, EKS, AKS, Vultr), giving true hardware‑agnostic portability of AI workloads. The release also ships an end‑to‑end Anthropic Messages API via a vLLM server that serves both OpenAI‑compatible routes and Claude Code from the same service address.
Related
- Vultr Clusters Now Supports CPUs in Addition to GPUs – Plus Other Enhancements
- How to Run Isolated Tenant Kubernetes Clusters on Shared GPU Infrastructure
- SUSE, NVIDIA, and Vultr Simplify the Path from AI Pilots to Production
Source: Vultr | 2026-09-03