ray.serve.schema.DeploymentSchema

class ray.serve.schema.DeploymentSchema(*, name: str, num_replicas: PositiveInt | str | None = DEFAULT.VALUE, route_prefix: str | None = DEFAULT.VALUE, max_concurrent_queries: ConstrainedIntValue = DEFAULT.VALUE, max_ongoing_requests: ConstrainedIntValue = DEFAULT.VALUE, max_queued_requests: StrictInt = DEFAULT.VALUE, user_config: Dict | None = DEFAULT.VALUE, autoscaling_config: Dict | None = DEFAULT.VALUE, graceful_shutdown_wait_loop_s: ConstrainedFloatValue = DEFAULT.VALUE, graceful_shutdown_timeout_s: ConstrainedFloatValue = DEFAULT.VALUE, health_check_period_s: ConstrainedFloatValue = DEFAULT.VALUE, health_check_timeout_s: ConstrainedFloatValue = DEFAULT.VALUE, ray_actor_options: RayActorOptionsSchema = DEFAULT.VALUE, placement_group_bundles: List[Dict[str, float]] = DEFAULT.VALUE, placement_group_strategy: str = DEFAULT.VALUE, max_replicas_per_node: int = DEFAULT.VALUE, logging_config: LoggingConfig = DEFAULT.VALUE)

Bases: BaseModel

Specifies options for one deployment within a Serve application. For each deployment this can optionally be included in ServeApplicationSchema to override deployment options specified in code.

Methods

__init__	Create a new model by parsing and validating input data from keyword arguments.
construct	Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data.
copy	Duplicate a model, optionally choose which fields to include, exclude and change.
deployment_schema_route_prefix_format	The route_prefix 1.
dict	Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.
json	Generate a JSON representation of the model, include and exclude arguments as per dict().
update_forward_refs	Try to update ForwardRefs on fields based on this Model, globalns and localns.

Attributes

name
num_replicas
route_prefix
max_concurrent_queries
max_ongoing_requests
max_queued_requests
user_config
autoscaling_config
graceful_shutdown_wait_loop_s
graceful_shutdown_timeout_s
health_check_period_s
health_check_timeout_s
ray_actor_options
placement_group_bundles
placement_group_strategy
max_replicas_per_node
logging_config