Runtime registry v5

Connect model runtimes to the edge network.

Register OpenAI-compatible runtimes hosted on GPU nodes, then route traffic using the gateway and routing engine. Source: demo.

Registered runtimes

Inference endpoints by node.

NameStatusTypeNodeBase URLCreated
umami-swahili-inference-smallonlineopenai-compatibletz-dar-edge-01http://127.0.0.1:8080/v14/28/2026, 11:45:54 AM
umami-document-ai-smalldegradedopenai-compatibletz-aru-edge-01http://127.0.0.1:8081/v14/28/2026, 11:45:54 AM
Register runtime API

Use this route after node provisioning.

POST /api/model-runtimes/register
{
  "organizationId": "demo-org",
  "nodeId": "<node-id>",
  "name": "umami-swahili-inference-small",
  "baseUrl": "http://10.0.0.15:8080/v1",
  "runtimeType": "openai-compatible",
  "status": "online"
}