Skip to main content

Configuration

vLLora can be configured via a config.yaml file or through command-line arguments. CLI arguments take precedence over config file settings.

Config File​

Create a config.yaml file in your working directory to configure vLLora.

HTTP Configuration​

Configure the backend API server settings:

http:
  host: "0.0.0.0"          # Host address to bind to
  port: 9090               # Backend API port (default: 9090)
  cors_allowed_origins:    # List of allowed CORS origins
    - "*"                  # Default: ["*"] (all origins)

UI Configuration​

Configure the web UI server settings:

ui:
  port: 9091               # UI port (default: 9091)
  open_on_startup: true    # Auto-open browser on startup (default: true)

OTEL Configuration​

Configure the OpenTelemetry gRPC collector settings:

otel:
  host: "[::]"             # Host for OTEL gRPC collector (default: "[::]")
  port: 4317               # OTEL port (default: 4317)

Example Config File​

Here's a complete example config.yaml:

http:
  host: "0.0.0.0"
  port: 9090
  cors_allowed_origins:
    - "http://localhost:3000"
    - "https://example.com"

ui:
  port: 9091
  open_on_startup: true

otel:
  host: "[::]"
  port: 4317

Environment Variable Substitution​

You can use environment variables in your config file:

http:
  host: "{{ HTTP_HOST }}"
  port: 9090

Set the environment variable before starting vLLora:

export HTTP_HOST="127.0.0.1"
vllora serve

Command-Line Arguments​

All configuration options can also be set via CLI arguments. Run vllora serve --help to see all available options:

vllora serve --help

Available CLI options:

  • --host <ADDRESS> - Host address to bind to
  • --port <PORT> - Backend API port
  • --ui-port <UI_PORT> - UI server port
  • --cors-origins <ORIGINS> - Comma-separated list of allowed CORS origins
  • --open-ui-on-startup <true|false> - Control browser auto-open on startup

CLI arguments override corresponding config file settings when both are specified.

Port Conflicts​

If a configured port is already in use, vLLora will automatically find the next available port and prompt you to accept the change. You can accept or reject the new port assignment.