CreateCServeV3DeploymentRequest.md

CreateCServeV3DeploymentRequest

Properties

Name	Type	Description	Notes
max_surge	int		[optional]
max_unavailable	int		[optional]
name	str
cluster_id	int
hardware_instance_id	int
user_annotations	Dict[str, str]		[optional]
recipe	CServeV2Recipe
cserve_version	str		[optional]
hf_token	str		[optional]
endpoint_bearer_token	str		[optional]
endpoint_certificate_authority	str		[optional]
min_replicas	int
max_replicas	int
initial_replicas	int		[optional]
concurrency	int		[optional]
cooldown_period	int		[optional]
env_vars	Dict[str, str]		[optional]
enable_logging	bool		[optional] [default to True]
enable_node_model_cache	bool		[optional] [default to False]
session_affinity	bool	Enable best-effort sticky routing via the `X-Session-Id` request header. Requests carrying the same header value land on the same pod, improving KV cache reuse for agentic workloads. Requests without the header are routed at random. Affinity is NOT durable: scaling, rollouts, restarts, or readiness-probe transitions will remap sessions to different pods. Do not use for irreplaceable in-pod state.	[optional] [default to False]

Example

from platform_api_python_client.models.create_c_serve_v3_deployment_request import CreateCServeV3DeploymentRequest

# TODO update the JSON string below
json = "{}"
# create an instance of CreateCServeV3DeploymentRequest from a JSON string
create_c_serve_v3_deployment_request_instance = CreateCServeV3DeploymentRequest.from_json(json)
# print the JSON string representation of the object
print(CreateCServeV3DeploymentRequest.to_json())

# convert the object into a dict
create_c_serve_v3_deployment_request_dict = create_c_serve_v3_deployment_request_instance.to_dict()
# create an instance of CreateCServeV3DeploymentRequest from a dict
create_c_serve_v3_deployment_request_from_dict = CreateCServeV3DeploymentRequest.from_dict(create_c_serve_v3_deployment_request_dict)

[Back to Model list] [Back to API list] [Back to README]