UnifiedWriteInferenceV3DeploymentRequest.md

UnifiedWriteInferenceV3DeploymentRequest

Properties

Name	Type	Description	Notes
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	CclMainPools
env	Env		[optional]
image	Image
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_logging	bool		[optional] [default to False]
enable_node_model_cache	bool		[optional] [default to False]

Example

from platform_api_python_client.models.unified_write_inference_v3_deployment_request import UnifiedWriteInferenceV3DeploymentRequest

# TODO update the JSON string below
json = "{}"
# create an instance of UnifiedWriteInferenceV3DeploymentRequest from a JSON string
unified_write_inference_v3_deployment_request_instance = UnifiedWriteInferenceV3DeploymentRequest.from_json(json)
# print the JSON string representation of the object
print(UnifiedWriteInferenceV3DeploymentRequest.to_json())

# convert the object into a dict
unified_write_inference_v3_deployment_request_dict = unified_write_inference_v3_deployment_request_instance.to_dict()
# create an instance of UnifiedWriteInferenceV3DeploymentRequest from a dict
unified_write_inference_v3_deployment_request_from_dict = UnifiedWriteInferenceV3DeploymentRequest.from_dict(unified_write_inference_v3_deployment_request_dict)

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