ray.serve.schema.ServeDeploySchema#
- pydantic model ray.serve.schema.ServeDeploySchema[source]#
Multi-application config for deploying a list of Serve applications to the Ray cluster.
This is the request JSON schema for the v2 REST API
PUT "/api/serve/applications/".- NOTE: This config allows extra parameters to make it forward-compatible (ie
older versions of Serve are able to accept configs from a newer versions, simply ignoring new parameters)
Show JSON schema
{ "title": "ServeDeploySchema", "description": "Multi-application config for deploying a list of Serve applications to the Ray\ncluster.\n\nThis is the request JSON schema for the v2 REST API\n`PUT \"/api/serve/applications/\"`.\n\nNOTE: This config allows extra parameters to make it forward-compatible (ie\n older versions of Serve are able to accept configs from a newer versions,\n simply ignoring new parameters)", "type": "object", "properties": { "proxy_location": { "description": "Config for where to run proxies for ingress traffic to the cluster.", "default": "EveryNode", "allOf": [ { "$ref": "#/definitions/ProxyLocation" } ] }, "http_options": { "title": "Http Options", "description": "Options to start the HTTP Proxy with.", "default": { "host": "0.0.0.0", "port": 8000, "root_path": "", "request_timeout_s": null, "keep_alive_timeout_s": 5 }, "allOf": [ { "$ref": "#/definitions/HTTPOptionsSchema" } ] }, "grpc_options": { "title": "Grpc Options", "description": "Options to start the gRPC Proxy with.", "default": { "port": 9000, "grpc_servicer_functions": [] }, "allOf": [ { "$ref": "#/definitions/gRPCOptionsSchema" } ] }, "logging_config": { "title": "Logging Config", "description": "Logging config for configuring serve components logs.", "allOf": [ { "$ref": "#/definitions/LoggingConfig" } ] }, "applications": { "title": "Applications", "description": "The set of applications to run on the Ray cluster.", "type": "array", "items": { "$ref": "#/definitions/ServeApplicationSchema" } }, "target_capacity": { "title": "Target Capacity", "description": "[EXPERIMENTAL]: the target capacity percentage for all replicas across the cluster. The `num_replicas`, `min_replicas`, `max_replicas`, and `initial_replicas` for each deployment will be scaled by this percentage.", "minimum": 0, "maximum": 100, "type": "number" } }, "required": [ "applications" ], "definitions": { "ProxyLocation": { "title": "ProxyLocation", "description": "Config for where to run proxies to receive ingress traffic to the cluster.\n\nOptions:\n\n - Disabled: don't run proxies at all. This should be used if you are only\n making calls to your applications via deployment handles.\n - HeadOnly: only run a single proxy on the head node.\n - EveryNode: run a proxy on every node in the cluster that has at least one\n replica actor. This is the default.", "enum": [ "Disabled", "HeadOnly", "EveryNode" ], "type": "string" }, "HTTPOptionsSchema": { "title": "HTTPOptionsSchema", "description": "Options to start the HTTP Proxy with.\n\nNOTE: This config allows extra parameters to make it forward-compatible (ie\n older versions of Serve are able to accept configs from a newer versions,\n simply ignoring new parameters).", "type": "object", "properties": { "host": { "title": "Host", "description": "Host for HTTP servers to listen on. Defaults to \"0.0.0.0\", which exposes Serve publicly. Cannot be updated once Serve has started running. Serve must be shut down and restarted with the new host instead.", "default": "0.0.0.0", "type": "string" }, "port": { "title": "Port", "description": "Port for HTTP server. Defaults to 8000. Cannot be updated once Serve has started running. Serve must be shut down and restarted with the new port instead.", "default": 8000, "type": "integer" }, "root_path": { "title": "Root Path", "description": "Root path to mount the serve application (for example, \"/serve\"). All deployment routes will be prefixed with this path. Defaults to \"\".", "default": "", "type": "string" }, "request_timeout_s": { "title": "Request Timeout S", "description": "The timeout for HTTP requests. Defaults to no timeout.", "type": "number" }, "keep_alive_timeout_s": { "title": "Keep Alive Timeout S", "description": "The HTTP proxy will keep idle connections alive for this duration before closing them when no requests are ongoing. Defaults to 5 seconds.", "default": 5, "type": "integer" } } }, "gRPCOptionsSchema": { "title": "gRPCOptionsSchema", "description": "Options to start the gRPC Proxy with.\n\n**PublicAPI (alpha):** This API is in alpha and may change before becoming stable.", "type": "object", "properties": { "port": { "title": "Port", "description": "Port for gRPC server. Defaults to 9000. Cannot be updated once Serve has started running. Serve must be shut down and restarted with the new port instead.", "default": 9000, "type": "integer" }, "grpc_servicer_functions": { "title": "Grpc Servicer Functions", "description": "List of import paths for gRPC `add_servicer_to_server` functions to add to Serve's gRPC proxy. Default to empty list, which means no gRPC methods will be added and no gRPC server will be started. The servicer functions need to be importable from the context of where Serve is running.", "default": [], "type": "array", "items": { "type": "string" } } } }, "EncodingType": { "title": "EncodingType", "description": "Encoding type for the serve logs.\n\n**PublicAPI (alpha):** This API is in alpha and may change before becoming stable.", "enum": [ "TEXT", "JSON" ], "type": "string" }, "LoggingConfig": { "title": "LoggingConfig", "description": "Logging config schema for configuring serve components logs.\n\nExample:\n\n .. code-block:: python\n\n from ray import serve\n from ray.serve.schema import LoggingConfig\n # Set log level for the deployment.\n @serve.deployment(LoggingConfig(log_level=\"DEBUG\")\n class MyDeployment:\n def __call__(self) -> str:\n return \"Hello world!\"\n # Set log directory for the deployment.\n @serve.deployment(LoggingConfig(logs_dir=\"/my_dir\")\n class MyDeployment:\n def __call__(self) -> str:\n return \"Hello world!\"\n\n**PublicAPI (alpha):** This API is in alpha and may change before becoming stable.", "type": "object", "properties": { "encoding": { "title": "Encoding", "description": "Encoding type for the serve logs. Defaults to 'TEXT'. The default can be overwritten using the `RAY_SERVE_LOG_ENCODING` environment variable. 'JSON' is also supported for structured logging.", "anyOf": [ { "type": "string" }, { "$ref": "#/definitions/EncodingType" } ] }, "log_level": { "title": "Log Level", "description": "Log level for the serve logs. Defaults to INFO. You can set it to 'DEBUG' to get more detailed debug logs.", "default": "INFO", "anyOf": [ { "type": "integer" }, { "type": "string" } ] }, "logs_dir": { "title": "Logs Dir", "description": "Directory to store the logs. Default to None, which means logs will be stored in the default directory ('/tmp/ray/session_latest/logs/serve/...').", "type": "string" }, "enable_access_log": { "title": "Enable Access Log", "description": "Whether to enable access logs for each request. Default to True.", "default": true, "type": "boolean" } }, "additionalProperties": false }, "RayActorOptionsSchema": { "title": "RayActorOptionsSchema", "description": "Options with which to start a replica actor.", "type": "object", "properties": { "runtime_env": { "title": "Runtime Env", "description": "This deployment's runtime_env. working_dir and py_modules may contain only remote URIs.", "default": {}, "type": "object" }, "num_cpus": { "title": "Num Cpus", "description": "The number of CPUs required by the deployment's application per replica. This is the same as a ray actor's num_cpus. Uses a default if null.", "minimum": 0, "type": "number" }, "num_gpus": { "title": "Num Gpus", "description": "The number of GPUs required by the deployment's application per replica. This is the same as a ray actor's num_gpus. Uses a default if null.", "minimum": 0, "type": "number" }, "memory": { "title": "Memory", "description": "Restrict the heap memory usage of each replica. Uses a default if null.", "minimum": 0, "type": "number" }, "object_store_memory": { "title": "Object Store Memory", "description": "Restrict the object store memory used per replica when creating objects. Uses a default if null.", "minimum": 0, "type": "number" }, "resources": { "title": "Resources", "description": "The custom resources required by each replica.", "default": {}, "type": "object" }, "accelerator_type": { "title": "Accelerator Type", "description": "Forces replicas to run on nodes with the specified accelerator type.See :ref:`accelerator types <accelerator_types>`.", "type": "string" } } }, "DeploymentSchema": { "title": "DeploymentSchema", "description": "Specifies options for one deployment within a Serve application. For each deployment\nthis can optionally be included in `ServeApplicationSchema` to override deployment\noptions specified in code.", "type": "object", "properties": { "name": { "title": "Name", "description": "Globally-unique name identifying this deployment.", "type": "string" }, "num_replicas": { "title": "Num Replicas", "description": "The number of processes that handle requests to this deployment. Uses a default if null. Can also be set to `auto` for a default autoscaling configuration (experimental).", "default": 1, "anyOf": [ { "type": "integer", "exclusiveMinimum": 0 }, { "type": "string" } ] }, "route_prefix": { "title": "Route Prefix", "description": "[DEPRECATED] Please use route_prefix under ServeApplicationSchema instead.", "default": 1, "type": "string" }, "max_concurrent_queries": { "title": "Max Concurrent Queries", "description": "[DEPRECATED] The max number of requests that will be executed at once in each replica. Defaults to 100.", "default": 1, "exclusiveMinimum": 0, "type": "integer" }, "max_ongoing_requests": { "title": "Max Ongoing Requests", "description": "Maximum number of requests that are sent in parallel to each replica of this deployment. The limit is enforced across all callers (HTTP requests or DeploymentHandles). Defaults to 100.", "default": 1, "exclusiveMinimum": 0, "type": "integer" }, "max_queued_requests": { "title": "Max Queued Requests", "description": "[DEPRECATED] The max number of requests that will be executed at once in each replica. Defaults to 100.", "default": 1, "type": "integer" }, "user_config": { "title": "User Config", "description": "Config to pass into this deployment's reconfigure method. This can be updated dynamically without restarting replicas", "default": 1, "type": "object" }, "autoscaling_config": { "title": "Autoscaling Config", "description": "Config specifying autoscaling parameters for the deployment's number of replicas. If null, the deployment won't autoscale its number of replicas; the number of replicas will be fixed at num_replicas.", "default": 1, "type": "object" }, "graceful_shutdown_wait_loop_s": { "title": "Graceful Shutdown Wait Loop S", "description": "Duration that deployment replicas will wait until there is no more work to be done before shutting down. Uses a default if null.", "default": 1, "minimum": 0, "type": "number" }, "graceful_shutdown_timeout_s": { "title": "Graceful Shutdown Timeout S", "description": "Serve controller waits for this duration before forcefully killing the replica for shutdown. Uses a default if null.", "default": 1, "minimum": 0, "type": "number" }, "health_check_period_s": { "title": "Health Check Period S", "description": "Frequency at which the controller will health check replicas. Uses a default if null.", "default": 1, "exclusiveMinimum": 0, "type": "number" }, "health_check_timeout_s": { "title": "Health Check Timeout S", "description": "Timeout that the controller will wait for a response from the replica's health check before marking it unhealthy. Uses a default if null.", "default": 1, "exclusiveMinimum": 0, "type": "number" }, "ray_actor_options": { "title": "Ray Actor Options", "description": "Options set for each replica actor.", "default": 1, "allOf": [ { "$ref": "#/definitions/RayActorOptionsSchema" } ] }, "placement_group_bundles": { "title": "Placement Group Bundles", "description": "Define a set of placement group bundles to be scheduled *for each replica* of this deployment. The replica actor will be scheduled in the first bundle provided, so the resources specified in `ray_actor_options` must be a subset of the first bundle's resources. All actors and tasks created by the replica actor will be scheduled in the placement group by default (`placement_group_capture_child_tasks` is set to True).", "default": 1, "type": "array", "items": { "type": "object", "additionalProperties": { "type": "number" } } }, "placement_group_strategy": { "title": "Placement Group Strategy", "description": "Strategy to use for the replica placement group specified via `placement_group_bundles`. Defaults to `PACK`.", "default": 1, "type": "string" }, "max_replicas_per_node": { "title": "Max Replicas Per Node", "description": "The max number of replicas of this deployment that can run on a single Valid values are None (default, no limit) or an integer in the range of [1, 100]. ", "default": 1, "type": "integer" }, "logging_config": { "title": "Logging Config", "description": "Logging config for configuring serve deployment logs.", "default": 1, "allOf": [ { "$ref": "#/definitions/LoggingConfig" } ] } }, "required": [ "name" ] }, "ServeApplicationSchema": { "title": "ServeApplicationSchema", "description": "Describes one Serve application, and currently can also be used as a standalone\nconfig to deploy a single application to a Ray cluster.", "type": "object", "properties": { "name": { "title": "Name", "description": "Application name, the name should be unique within the serve instance", "default": "default", "type": "string" }, "route_prefix": { "title": "Route Prefix", "description": "Route prefix for HTTP requests. If not provided, it will useroute_prefix of the ingress deployment. By default, the ingress route prefix is '/'.", "default": "/", "type": "string" }, "import_path": { "title": "Import Path", "description": "An import path to a bound deployment node. Should be of the form \"module.submodule_1...submodule_n.dag_node\". This is equivalent to \"from module.submodule_1...submodule_n import dag_node\". Only works with Python applications. This field is REQUIRED when deploying Serve config to a Ray cluster.", "type": "string" }, "runtime_env": { "title": "Runtime Env", "description": "The runtime_env that the deployment graph will be run in. Per-deployment runtime_envs will inherit from this. working_dir and py_modules may contain only remote URIs.", "default": {}, "type": "object" }, "host": { "title": "Host", "description": "Host for HTTP servers to listen on. Defaults to \"0.0.0.0\", which exposes Serve publicly. Cannot be updated once your Serve application has started running. The Serve application must be shut down and restarted with the new host instead.", "default": "0.0.0.0", "type": "string" }, "port": { "title": "Port", "description": "Port for HTTP server. Defaults to 8000. Cannot be updated once your Serve application has started running. The Serve application must be shut down and restarted with the new port instead.", "default": 8000, "type": "integer" }, "deployments": { "title": "Deployments", "description": "Deployment options that override options specified in the code.", "default": [], "type": "array", "items": { "$ref": "#/definitions/DeploymentSchema" } }, "args": { "title": "Args", "description": "Arguments that will be passed to the application builder.", "default": {}, "type": "object" }, "logging_config": { "title": "Logging Config", "description": "Logging config for configuring serve application logs.", "allOf": [ { "$ref": "#/definitions/LoggingConfig" } ] } }, "required": [ "import_path" ] } } }
- Fields:
- Validators:
- field applications: List[ServeApplicationSchema] [Required]#
The set of applications to run on the Ray cluster.
- field grpc_options: gRPCOptionsSchema = gRPCOptionsSchema(port=9000, grpc_servicer_functions=[])#
Options to start the gRPC Proxy with.
- Validated by:
- field http_options: HTTPOptionsSchema = HTTPOptionsSchema(host='0.0.0.0', port=8000, root_path='', request_timeout_s=None, keep_alive_timeout_s=5)#
Options to start the HTTP Proxy with.
- Validated by:
- field logging_config: LoggingConfig = None#
Logging config for configuring serve components logs.
- Validated by:
- field proxy_location: ProxyLocation = ProxyLocation.EveryNode#
Config for where to run proxies for ingress traffic to the cluster.
- Validated by:
- field target_capacity: float | None = None#
[EXPERIMENTAL]: the target capacity percentage for all replicas across the cluster. The
num_replicas,min_replicas,max_replicas, andinitial_replicasfor each deployment will be scaled by this percentage.- Constraints:
minimum = 0
maximum = 100
- Validated by:
- validator application_names_nonempty » applications[source]#
- validator application_names_unique » applications[source]#
- validator application_routes_unique » applications[source]#