TorchServe: check model and server status/health using the Management API and inference health endpoint

Steps

1. Check overall server health with `curl http://localhost:8080/ping` (TorchServe's Inference API, port 8080 by default); a healthy server returns HTTP 200 with {"status": "Healthy"}.
2. The ping endpoint is model-aware: it returns 200/"healthy" only if every registered model has active workers >= its configured minWorkers, and 500/"unhealthy" otherwise.
3. Get per-model runtime detail from the Management API's Describe Model endpoint: `curl http://localhost:8081/models/{model_name}` (port 8081 by default) — returns workers[] with each worker's status (e.g. READY), minWorkers/maxWorkers, and jobQueueStatus (remainingCapacity, pendingRequests).
4. List all registered models with `curl http://localhost:8081/models` (supports limit and next_page_token query params for pagination).
5. Get a specific model version's status with `GET /models/{model_name}/{version}`, or every version at once with `GET /models/{model_name}/all`.