/opt/chainguard/azureml-inference-server-http/bin/azmlinfsrv

usage: azmlinfsrv [-h] [--entry_script ENTRY_SCRIPT] [--model_dir MODEL_DIR]
                  [--appinsights_instrumentation_key APPINSIGHTS_INSTRUMENTATION_KEY]
                  [--port PORT] [--health_port HEALTH_PORT] [--worker_count WORKER_COUNT]
                  [--access_control_allow_origins ACCESS_CONTROL_ALLOW_ORIGINS]
                  [--config_file CONFIG_FILE]

Azure ML Inferencing HTTP server v1.5.1

options:
  -h, --help            show this help message and exit
  --entry_script ENTRY_SCRIPT
                        The relative or absolute path to the scoring script.
  --model_dir MODEL_DIR
                        The relative or absolute path to the model directory. The model directory
                        will be accessiblethrough the 'AZUREML_MODEL_DIR' environment variable.
  --appinsights_instrumentation_key APPINSIGHTS_INSTRUMENTATION_KEY
                        The instrumentation key to the application insights where the logs will be
                        published.
  --port PORT           The serving port of the server. Default is 5001.
  --health_port HEALTH_PORT
                        The health port of the server. Default is 5000.
  --worker_count WORKER_COUNT
                        The number of worker threads which will process concurrent requests.
                        Default is 1.
  --access_control_allow_origins ACCESS_CONTROL_ALLOW_ORIGINS
                        Enable CORS for the specified origins. Separate multiple origins with
                        ",".Example: "microsoft.com, bing.com"
  --config_file CONFIG_FILE
                        The relative or absolute path to the configuration file