nemo_microservices.types.v2.inference.k8s_nim_operator_config_param#
Module Contents#
Classes#
API#
- class nemo_microservices.types.v2.inference.k8s_nim_operator_config_param.K8sNIMOperatorConfigParam#
Bases:
typing_extensions.TypedDict- node_selector: Dict[str, str]#
None
Kubernetes node selector for pod placement.
Example: {‘node-type’: ‘gpu-node’, ‘zone’: ‘us-west1-a’}
- resources: Dict[str, object]#
None
Kubernetes resource requirements including requests and limits.
Example: {‘requests’: {‘cpu’: ‘2’, ‘memory’: ‘8Gi’}, ‘limits’: {‘memory’: ‘16Gi’}}
- startup_probe_grace_seconds: int#
None
Grace period in seconds for NIM startup.
Determines how long Kubernetes will wait for the NIM to become ready before restarting it. Example: 600 (10 minutes). Must be a positive integer.
- tolerations: Iterable[Dict[str, object]]#
None
Kubernetes tolerations for pod scheduling.
Example: [{‘key’: ‘nvidia.com/gpu’, ‘operator’: ‘Exists’, ‘effect’: ‘NoSchedule’}]