MLServer Settings

MLServer can be configured through a settings.json file on the root folder from where MLServer is started. Note that these are server-wide settings (e.g. gRPC or HTTP port) which are separate from the invidual model settings. Alternatively, this configuration can also be passed through environment variables prefixed with MLSERVER_ (e.g. MLSERVER_GRPC_PORT).

Settings

pydantic settings mlserver.settings.Settings

Config:

• env_file: str = .env

• env_prefix: str = MLSERVER_

Fields:

• cache_enabled (bool)

• cache_size (int)

• cors_settings (mlserver.settings.CORSSettings | None)

• debug (bool)

• environments_dir (str)

• extensions (List[str])

• grpc_max_message_length (int | None)

• grpc_port (int)

• host (str)

• http_port (int)

• kafka_enabled (bool)

• kafka_servers (str)

• kafka_topic_input (str)

• kafka_topic_output (str)

• load_models_at_startup (bool)

• logging_settings (str | Dict | None)

• metrics_dir (str)

• metrics_endpoint (str | None)

• metrics_port (int)

• metrics_rest_server_prefix (str)

• model_repository_implementation (pydantic.types.PyObject | None)

• model_repository_implementation_args (dict)

• model_repository_root (str)

• parallel_workers (int)

• parallel_workers_timeout (int)

• root_path (str)

• server_name (str)

• server_version (str)

• tracing_server (str | None)

• use_structured_logging (bool)

field cache_enabled: bool = False

Enable caching for the model predictions.

field cache_size: int = 100

Cache size to be used if caching is enabled.

field cors_settings: CORSSettings | None = None

field debug: bool = True

field environments_dir: str = '/home/docs/checkouts/readthedocs.org/user_builds/mlserver/checkouts/latest/docs/.envs'

Directory used to store custom environments. By default, the .envs folder of the current working directory will be used.

field extensions: List[str] = []

Server extensions loaded.

field grpc_max_message_length: int | None = None

Maximum length (i.e. size) of gRPC payloads.

field grpc_port: int = 8081

Port where to listen for gRPC connections.

field host: str = '0.0.0.0'

Host where to listen for connections.

field http_port: int = 8080

Port where to listen for HTTP / REST connections.

field kafka_enabled: bool = False

field kafka_servers: str = 'localhost:9092'

field kafka_topic_input: str = 'mlserver-input'

field kafka_topic_output: str = 'mlserver-output'

field load_models_at_startup: bool = True

Flag to load all available models automatically at startup.

field logging_settings: str | Dict | None = None

Path to logging config file or dictionary configuration.

field metrics_dir: str = '/home/docs/checkouts/readthedocs.org/user_builds/mlserver/checkouts/latest/docs/.metrics'

Directory used to share metrics across parallel workers. Equivalent to the PROMETHEUS_MULTIPROC_DIR env var in prometheus-client. Note that this won’t be used if the parallel_workers flag is disabled. By default, the .metrics folder of the current working directory will be used.

field metrics_endpoint: str | None = '/metrics'

Endpoint used to expose Prometheus metrics. Alternatively, can be set to None to disable it.

field metrics_port: int = 8082

Port used to expose metrics endpoint.

field metrics_rest_server_prefix: str = 'rest_server'

Metrics rest server string prefix to be exported.

field model_repository_implementation: PyObject | None = None

Python path to the inference runtime to model repository (e.g. mlserver.repository.repository.SchemalessModelRepository).

field model_repository_implementation_args: dict = {}

Extra parameters for model repository.

field model_repository_root: str = '.'

Root of the model repository, where we will search for models.

field parallel_workers: int = 1

When parallel inference is enabled, number of workers to run inference across.

field parallel_workers_timeout: int = 5

Grace timeout to wait until the workers shut down when stopping MLServer.

field root_path: str = ''

Set the ASGI root_path for applications submounted below a given URL path.

field server_name: str = 'mlserver'

Name of the server.

field server_version: str = '1.4.0.dev3'

Version of the server.

field tracing_server: str | None = None

Server name used to export OpenTelemetry tracing to collector service.

field use_structured_logging: bool = False

Use JSON-formatted structured logging instead of default format.