{
  "host": "0.0.0.0",
  "port": 8080,
  "api_keys": ["your-secret-key"],
  "poll_interval": 5,
  "slot_wait_timeout": 30,
  "session_idle_ttl": 300,
  "default_slot_capacity": 1,
  "default_max_models": 1,
  "model_affinity_sched_bonus": 10,
  "queue_aging_equalization": 30.0,
  "model_unload_delay": 3.0,
  "model_limits": {
    "my-very-large-model": 1
  },
  "backends": [
    {
      "url": "http://localhost:8081",
      "api_key": null,
      "model_ids": [],
      "max_models": 1
    },
    {
      "url": "http://localhost:8082",
      "api_key": "backend-secret",
      "model_ids": ["llama3"],
      "max_models": null
    }
  ]
}