Cluster-level inference tooling is fine. It just doesn't help you orchestrate the GPUs you own. Nobody at scale runs one cluster. The fix: treat the ones you own as one pool. That's the fleet-level API we designed. How we built it → modelplane.ai/blog/how-we-...

Modelplane v0.2 is out. Two new providers (Nebius, @microsoft.com Azure AKS), weighted routing for canarying model versions, and cluster taints to reserve or drain capacity. The clusters you own, one pool. Building in the open. → modelplane.ai/blog/modelplane-v0-2

Modelplane is here: an open source control plane for AI inference. Any model, any engine, any infra, from one GPU to multi-node. It's v0.1 and built in the open. Spin it up on a kind cluster, then tell us where it breaks. ⭐ → modelplane.ai