❯ ray start --head --metrics-export-port=8080
2026-01-28 01:11:24,923 - INFO - Note: NumExpr detected 16 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 8.
2026-01-28 01:11:24,923 - INFO - NumExpr defaulting to 8 threads.
Usage stats collection is enabled. To disable this, add `--disable-usage-stats` to the command that starts the cluster, or run the following command: `ray disable-usage-stats` before starting the cluster. See https://docs.ray.io/en/master/cluster/usage-stats.html for more details.

Local node IP: 172.31.7.228

--------------------
Ray runtime started.
--------------------

Next steps
  To add another node to this Ray cluster, run
    ray start --address='172.31.7.228:6379'

  To connect to this Ray cluster:
    import ray
    ray.init()

  To submit a Ray job using the Ray Jobs CLI:
    RAY_API_SERVER_ADDRESS='http://127.0.0.1:8265' ray job submit --working-dir . -- python my_script.py

  See https://docs.ray.io/en/latest/cluster/running-applications/job-submission/index.html
  for more information on submitting Ray jobs to the Ray cluster.

  To terminate the Ray runtime, run
    ray stop

  To view the status of the cluster, use
    ray status

  To monitor and debug Ray, view the dashboard at
    127.0.0.1:8265

  If connection to the dashboard fails, check your firewall settings and network configuration.
❯ serve start
2026-01-28 01:11:31,295	INFO worker.py:1818 -- Connecting to existing Ray cluster at address: 172.31.7.228:6379...
2026-01-28 01:11:31,315	INFO worker.py:1998 -- Connected to Ray cluster. View the dashboard at 127.0.0.1:8265
/home/ubuntu/ray/python/ray/_private/worker.py:2046: FutureWarning: Tip: In future versions of Ray, Ray will no longer override accelerator visible devices env var if num_gpus=0 or num_gpus=None (default). To enable this behavior and turn off this error message, set RAY_ACCEL_ENV_VAR_OVERRIDE_ON_ZERO=0
  warnings.warn(
(ProxyActor pid=1976778) INFO 2026-01-28 01:11:32,716 proxy 172.31.7.228 -- Proxy starting on node c4e8e7cbced234146fc4e47ad45a94f2b04dbb7b4ba03aee4542ca98 (HTTP port: 8000).
INFO 2026-01-28 01:11:32,774 serve 1976714 -- Started Serve in namespace "serve".
(ProxyActor pid=1976778) INFO 2026-01-28 01:11:32,771 proxy 172.31.7.228 -- Got updated endpoints: {}.
❯ serve controller-health --json | jq .
2026-01-28 01:11:38,690	INFO worker.py:1818 -- Connecting to existing Ray cluster at address: 172.31.7.228:6379...
2026-01-28 01:11:38,710	INFO worker.py:1998 -- Connected to Ray cluster. View the dashboard at 127.0.0.1:8265
/home/ubuntu/ray/python/ray/_private/worker.py:2046: FutureWarning: Tip: In future versions of Ray, Ray will no longer override accelerator visible devices env var if num_gpus=0 or num_gpus=None (default). To enable this behavior and turn off this error message, set RAY_ACCEL_ENV_VAR_OVERRIDE_ON_ZERO=0
  warnings.warn(
{
  "timestamp": 1769562698.7340927,
  "controller_start_time": 1769562692.1990602,
  "uptime_s": 6.535032510757446,
  "num_control_loops": 65,
  "loop_duration_s": {
    "mean": 0.0011578083038330078,
    "std": 0.0012476540718215343,
    "min": 0.0007350444793701172,
    "max": 0.011061429977416992
  },
  "loops_per_second": 9.946392752140438,
  "last_sleep_duration_s": 0.10063314437866211,
  "expected_sleep_duration_s": 0.1,
  "event_loop_delay_s": 0.0006331443786621038,
  "num_asyncio_tasks": 5,
  "deployment_state_update_duration_s": {
    "mean": 1.5174425565279447e-05,
    "std": 1.9936262596089162e-06,
    "min": 8.344650268554688e-06,
    "max": 2.5510787963867188e-05
  },
  "application_state_update_duration_s": {
    "mean": 2.6226043701171875e-06,
    "std": 3.18502181802785e-07,
    "min": 1.9073486328125e-06,
    "max": 3.5762786865234375e-06
  },
  "proxy_state_update_duration_s": {
    "mean": 0.00020424769474909857,
    "std": 0.0013016703229816826,
    "min": 2.2172927856445312e-05,
    "max": 0.010605335235595703
  },
  "node_update_duration_s": {
    "mean": 6.070503821739783e-06,
    "std": 7.122869784728825e-07,
    "min": 2.6226043701171875e-06,
    "max": 7.3909759521484375e-06
  },
  "handle_metrics_delay_ms": {
    "mean": 0,
    "std": 0,
    "min": 0,
    "max": 0
  },
  "replica_metrics_delay_ms": {
    "mean": 0,
    "std": 0,
    "min": 0,
    "max": 0
  },
  "process_memory_mb": 178.44921875
}