Skip to content

Latest commit

 

History

History
58 lines (49 loc) · 2.95 KB

File metadata and controls

58 lines (49 loc) · 2.95 KB

GetInferenceV3DeploymentResponse

Properties

Name Type Description Notes
creator_email str
cluster_id int
id int
name str
endpoint_url str
image_url str [optional]
type DeploymentType
status DeploymentStatus
created_at datetime
hardware_instance_id int
revision_number int
user_annotations Dict[str, str] [optional]
container_port int
min_replicas int
max_replicas int
initial_replicas int [optional]
concurrency int [optional]
cooldown_period int [optional] [default to 1800]
healthcheck str [optional]
endpoint_certificate_authority str [optional]
endpoint_bearer_token str [optional]
env_vars Dict[str, str] [optional]
command List[str] [optional]
command_args List[str] [optional]
original_command str [optional]
image_pull_secret_credentials ImagePullSecretCredentials [optional]
backend_protocol BackendProtocol [optional]
enable_logging bool [optional] [default to True]
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]
config_file ConfigFileMount [optional]

Example

from platform_api_python_client.models.get_inference_v3_deployment_response import GetInferenceV3DeploymentResponse

# TODO update the JSON string below
json = "{}"
# create an instance of GetInferenceV3DeploymentResponse from a JSON string
get_inference_v3_deployment_response_instance = GetInferenceV3DeploymentResponse.from_json(json)
# print the JSON string representation of the object
print(GetInferenceV3DeploymentResponse.to_json())

# convert the object into a dict
get_inference_v3_deployment_response_dict = get_inference_v3_deployment_response_instance.to_dict()
# create an instance of GetInferenceV3DeploymentResponse from a dict
get_inference_v3_deployment_response_from_dict = GetInferenceV3DeploymentResponse.from_dict(get_inference_v3_deployment_response_dict)

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