Skip to content

Latest commit

 

History

History
66 lines (57 loc) · 3.25 KB

UnifiedGetDeploymentResponse.md

File metadata and controls

66 lines (57 loc) · 3.25 KB

UnifiedGetDeploymentResponse

Properties

Name Type Description Notes
id int
status DeploymentStatus
creator_email str
created_at datetime
updated_at datetime
revision_number int
endpoint_url str
type str
name str
cluster_id int
user_annotations Dict[str, str] [optional]
chart_revision str [optional]
volume_mounts List[VolumeMount] [optional]
priority str [optional]
pools CclDynamoPools
env Env [optional]
image DynamoImage
ssh_public_key str
enable_logging bool [optional] [default to True]
exposed_port int
ingress Ingress
port int
healthcheck str [optional]
command str [optional]
config_file ConfigFileMount [optional]
hf_token_ref int [optional]
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]
metrics MetricsConfig [optional]
enable_node_model_cache bool [optional] [default to False]
completions int [optional] [default to 1]
parallelism int [optional] [default to 1]
backoff_limit int [optional] [default to 3]
active_deadline_seconds int [optional]
serving_mode DynamoServingMode [optional]
communications DynamoCommunicationsOutput [optional]
model str
served_model_name str [optional]
extra_args str [optional]

Example

from platform_api_python_client.models.unified_get_deployment_response import UnifiedGetDeploymentResponse

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

# convert the object into a dict
unified_get_deployment_response_dict = unified_get_deployment_response_instance.to_dict()
# create an instance of UnifiedGetDeploymentResponse from a dict
unified_get_deployment_response_from_dict = UnifiedGetDeploymentResponse.from_dict(unified_get_deployment_response_dict)

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