https://docs.modelplane.ai/architecture/Recent content in Architecture on Modelplane DocsHugo -- gohugo.ioen-usMon, 01 Jan 0001 00:00:00 +0000https://docs.modelplane.ai/architecture/scheduling/https://docs.modelplane.ai/architecture/scheduling/<p><strong>API:</strong> <a href="https://docs.modelplane.ai/reference/modeldeployments/"><code>modelplane.ai/v1alpha1</code> · ModelDeployment</a></p> <!-- vale write-good.Passive = NO --> <p>When an ML team creates a <a href="https://docs.modelplane.ai/models/model-deployment/">ModelDeployment</a>, the fleet scheduler decides which cluster each replica runs on and which node pool each engine uses. Platform teams don&rsquo;t drive it directly, but what they publish, the clusters, their labels, and each pool&rsquo;s <a href="https://docs.modelplane.ai/platform/inference-class/">InferenceClass</a>, is exactly what the scheduler matches against. This page explains how it places work and where it deliberately stops short, so you can reason about why a deployment landed where it did.</p>