Viewing docs for CAST AI v8.60.0
published on Wednesday, Aug 19, 2026 by CAST AI
published on Wednesday, Aug 19, 2026 by CAST AI
Viewing docs for CAST AI v8.60.0
published on Wednesday, Aug 19, 2026 by CAST AI
published on Wednesday, Aug 19, 2026 by CAST AI
Create AiOptimizerHostedModel Resource
Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.
Constructor syntax
new AiOptimizerHostedModel(name: string, args: AiOptimizerHostedModelArgs, opts?: CustomResourceOptions);@overload
def AiOptimizerHostedModel(resource_name: str,
args: AiOptimizerHostedModelArgs,
opts: Optional[ResourceOptions] = None)
@overload
def AiOptimizerHostedModel(resource_name: str,
opts: Optional[ResourceOptions] = None,
cluster_id: Optional[str] = None,
model_specs_id: Optional[str] = None,
port: Optional[int] = None,
service: Optional[str] = None,
edge_location_ids: Optional[Sequence[str]] = None,
fallback: Optional[AiOptimizerHostedModelFallbackArgs] = None,
hibernation: Optional[AiOptimizerHostedModelHibernationArgs] = None,
horizontal_autoscaling: Optional[AiOptimizerHostedModelHorizontalAutoscalingArgs] = None,
node_template_name: Optional[str] = None,
vllm_config: Optional[AiOptimizerHostedModelVllmConfigArgs] = None)func NewAiOptimizerHostedModel(ctx *Context, name string, args AiOptimizerHostedModelArgs, opts ...ResourceOption) (*AiOptimizerHostedModel, error)public AiOptimizerHostedModel(string name, AiOptimizerHostedModelArgs args, CustomResourceOptions? opts = null)
public AiOptimizerHostedModel(String name, AiOptimizerHostedModelArgs args)
public AiOptimizerHostedModel(String name, AiOptimizerHostedModelArgs args, CustomResourceOptions options)
type: castai:index/aiOptimizer:AiOptimizerHostedModel
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.
resource "castai_ai_optimizer_hosted_model" "name" {
# resource properties
}Parameters
- name string
- The unique name of the resource.
- args AiOptimizerHostedModelArgs
- The arguments to resource properties.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- resource_name str
- The unique name of the resource.
- args AiOptimizerHostedModelArgs
- The arguments to resource properties.
- opts ResourceOptions
- Bag of options to control resource's behavior.
- ctx Context
- Context object for the current deployment.
- name string
- The unique name of the resource.
- args AiOptimizerHostedModelArgs
- The arguments to resource properties.
- opts ResourceOption
- Bag of options to control resource's behavior.
- name string
- The unique name of the resource.
- args AiOptimizerHostedModelArgs
- The arguments to resource properties.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- name String
- The unique name of the resource.
- args AiOptimizerHostedModelArgs
- The arguments to resource properties.
- options CustomResourceOptions
- Bag of options to control resource's behavior.
AiOptimizerHostedModel Resource Properties
To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.
Inputs
In Python, inputs that are objects can be passed either as argument classes or as dictionary literals.
The AiOptimizerHostedModel resource accepts the following input properties:
- Cluster
Id string - CAST AI cluster ID where the model will be deployed.
- Model
Specs stringId - ID of the model specs. Can reference a castai.AiOptimizerModelSpecs resource or a pre-existing model specs ID for predefined (CastAI-managed) models.
- Port int
- Port on which the model will be exposed.
- Service string
- Kubernetes service name for the deployed model.
- Edge
Location List<string>Ids - List of edge location IDs where the model can be deployed.
- Fallback
Pulumi.
Cast AI. Inputs. Ai Optimizer Hosted Model Fallback - Fallback model settings.
- Hibernation
Pulumi.
Cast AI. Inputs. Ai Optimizer Hosted Model Hibernation - Automatic hibernation settings.
- Horizontal
Autoscaling Pulumi.Cast AI. Inputs. Ai Optimizer Hosted Model Horizontal Autoscaling - Horizontal autoscaling settings.
- Node
Template stringName - Node template name for model deployment.
- Vllm
Config Pulumi.Cast AI. Inputs. Ai Optimizer Hosted Model Vllm Config - vLLM configuration for HuggingFace models.
- Cluster
Id string - CAST AI cluster ID where the model will be deployed.
- Model
Specs stringId - ID of the model specs. Can reference a castai.AiOptimizerModelSpecs resource or a pre-existing model specs ID for predefined (CastAI-managed) models.
- Port int
- Port on which the model will be exposed.
- Service string
- Kubernetes service name for the deployed model.
- Edge
Location []stringIds - List of edge location IDs where the model can be deployed.
- Fallback
Ai
Optimizer Hosted Model Fallback Args - Fallback model settings.
- Hibernation
Ai
Optimizer Hosted Model Hibernation Args - Automatic hibernation settings.
- Horizontal
Autoscaling AiOptimizer Hosted Model Horizontal Autoscaling Args - Horizontal autoscaling settings.
- Node
Template stringName - Node template name for model deployment.
- Vllm
Config AiOptimizer Hosted Model Vllm Config Args - vLLM configuration for HuggingFace models.
- cluster_
id string - CAST AI cluster ID where the model will be deployed.
- model_
specs_ stringid - ID of the model specs. Can reference a castai.AiOptimizerModelSpecs resource or a pre-existing model specs ID for predefined (CastAI-managed) models.
- port number
- Port on which the model will be exposed.
- service string
- Kubernetes service name for the deployed model.
- edge_
location_ list(string)ids - List of edge location IDs where the model can be deployed.
- fallback object
- Fallback model settings.
- hibernation object
- Automatic hibernation settings.
- horizontal_
autoscaling object - Horizontal autoscaling settings.
- node_
template_ stringname - Node template name for model deployment.
- vllm_
config object - vLLM configuration for HuggingFace models.
- cluster
Id String - CAST AI cluster ID where the model will be deployed.
- model
Specs StringId - ID of the model specs. Can reference a castai.AiOptimizerModelSpecs resource or a pre-existing model specs ID for predefined (CastAI-managed) models.
- port Integer
- Port on which the model will be exposed.
- service String
- Kubernetes service name for the deployed model.
- edge
Location List<String>Ids - List of edge location IDs where the model can be deployed.
- fallback
Ai
Optimizer Hosted Model Fallback - Fallback model settings.
- hibernation
Ai
Optimizer Hosted Model Hibernation - Automatic hibernation settings.
- horizontal
Autoscaling AiOptimizer Hosted Model Horizontal Autoscaling - Horizontal autoscaling settings.
- node
Template StringName - Node template name for model deployment.
- vllm
Config AiOptimizer Hosted Model Vllm Config - vLLM configuration for HuggingFace models.
- cluster
Id string - CAST AI cluster ID where the model will be deployed.
- model
Specs stringId - ID of the model specs. Can reference a castai.AiOptimizerModelSpecs resource or a pre-existing model specs ID for predefined (CastAI-managed) models.
- port number
- Port on which the model will be exposed.
- service string
- Kubernetes service name for the deployed model.
- edge
Location string[]Ids - List of edge location IDs where the model can be deployed.
- fallback
Ai
Optimizer Hosted Model Fallback - Fallback model settings.
- hibernation
Ai
Optimizer Hosted Model Hibernation - Automatic hibernation settings.
- horizontal
Autoscaling AiOptimizer Hosted Model Horizontal Autoscaling - Horizontal autoscaling settings.
- node
Template stringName - Node template name for model deployment.
- vllm
Config AiOptimizer Hosted Model Vllm Config - vLLM configuration for HuggingFace models.
- cluster_
id str - CAST AI cluster ID where the model will be deployed.
- model_
specs_ strid - ID of the model specs. Can reference a castai.AiOptimizerModelSpecs resource or a pre-existing model specs ID for predefined (CastAI-managed) models.
- port int
- Port on which the model will be exposed.
- service str
- Kubernetes service name for the deployed model.
- edge_
location_ Sequence[str]ids - List of edge location IDs where the model can be deployed.
- fallback
Ai
Optimizer Hosted Model Fallback Args - Fallback model settings.
- hibernation
Ai
Optimizer Hosted Model Hibernation Args - Automatic hibernation settings.
- horizontal_
autoscaling AiOptimizer Hosted Model Horizontal Autoscaling Args - Horizontal autoscaling settings.
- node_
template_ strname - Node template name for model deployment.
- vllm_
config AiOptimizer Hosted Model Vllm Config Args - vLLM configuration for HuggingFace models.
- cluster
Id String - CAST AI cluster ID where the model will be deployed.
- model
Specs StringId - ID of the model specs. Can reference a castai.AiOptimizerModelSpecs resource or a pre-existing model specs ID for predefined (CastAI-managed) models.
- port Number
- Port on which the model will be exposed.
- service String
- Kubernetes service name for the deployed model.
- edge
Location List<String>Ids - List of edge location IDs where the model can be deployed.
- fallback Property Map
- Fallback model settings.
- hibernation Property Map
- Automatic hibernation settings.
- horizontal
Autoscaling Property Map - Horizontal autoscaling settings.
- node
Template StringName - Node template name for model deployment.
- vllm
Config Property Map - vLLM configuration for HuggingFace models.
Outputs
All input properties are implicitly available as output properties. Additionally, the AiOptimizerHostedModel resource produces the following output properties:
- Cloud
Provider string - Cloud provider.
- Current
Replicas int - Current number of replicas.
- Id string
- The provider-assigned unique ID for this managed resource.
- Namespace string
- Kubernetes namespace.
- Region string
- Region the model is deployed in.
- Status string
- Hosted model status.
- Status
Reason string - Reason for the current status.
- Cloud
Provider string - Cloud provider.
- Current
Replicas int - Current number of replicas.
- Id string
- The provider-assigned unique ID for this managed resource.
- Namespace string
- Kubernetes namespace.
- Region string
- Region the model is deployed in.
- Status string
- Hosted model status.
- Status
Reason string - Reason for the current status.
- cloud_
provider string - Cloud provider.
- current_
replicas number - Current number of replicas.
- id string
- The provider-assigned unique ID for this managed resource.
- namespace string
- Kubernetes namespace.
- region string
- Region the model is deployed in.
- status string
- Hosted model status.
- status_
reason string - Reason for the current status.
- cloud
Provider String - Cloud provider.
- current
Replicas Integer - Current number of replicas.
- id String
- The provider-assigned unique ID for this managed resource.
- namespace String
- Kubernetes namespace.
- region String
- Region the model is deployed in.
- status String
- Hosted model status.
- status
Reason String - Reason for the current status.
- cloud
Provider string - Cloud provider.
- current
Replicas number - Current number of replicas.
- id string
- The provider-assigned unique ID for this managed resource.
- namespace string
- Kubernetes namespace.
- region string
- Region the model is deployed in.
- status string
- Hosted model status.
- status
Reason string - Reason for the current status.
- cloud_
provider str - Cloud provider.
- current_
replicas int - Current number of replicas.
- id str
- The provider-assigned unique ID for this managed resource.
- namespace str
- Kubernetes namespace.
- region str
- Region the model is deployed in.
- status str
- Hosted model status.
- status_
reason str - Reason for the current status.
- cloud
Provider String - Cloud provider.
- current
Replicas Number - Current number of replicas.
- id String
- The provider-assigned unique ID for this managed resource.
- namespace String
- Kubernetes namespace.
- region String
- Region the model is deployed in.
- status String
- Hosted model status.
- status
Reason String - Reason for the current status.
Look up Existing AiOptimizerHostedModel Resource
Get an existing AiOptimizerHostedModel resource’s state with the given name, ID, and optional extra properties used to qualify the lookup.
public static get(name: string, id: Input<ID>, state?: AiOptimizerHostedModelState, opts?: CustomResourceOptions): AiOptimizerHostedModel@staticmethod
def get(resource_name: str,
id: str,
opts: Optional[ResourceOptions] = None,
cloud_provider: Optional[str] = None,
cluster_id: Optional[str] = None,
current_replicas: Optional[int] = None,
edge_location_ids: Optional[Sequence[str]] = None,
fallback: Optional[AiOptimizerHostedModelFallbackArgs] = None,
hibernation: Optional[AiOptimizerHostedModelHibernationArgs] = None,
horizontal_autoscaling: Optional[AiOptimizerHostedModelHorizontalAutoscalingArgs] = None,
model_specs_id: Optional[str] = None,
namespace: Optional[str] = None,
node_template_name: Optional[str] = None,
port: Optional[int] = None,
region: Optional[str] = None,
service: Optional[str] = None,
status: Optional[str] = None,
status_reason: Optional[str] = None,
vllm_config: Optional[AiOptimizerHostedModelVllmConfigArgs] = None) -> AiOptimizerHostedModelfunc GetAiOptimizerHostedModel(ctx *Context, name string, id IDInput, state *AiOptimizerHostedModelState, opts ...ResourceOption) (*AiOptimizerHostedModel, error)public static AiOptimizerHostedModel Get(string name, Input<string> id, AiOptimizerHostedModelState? state, CustomResourceOptions? opts = null)public static AiOptimizerHostedModel get(String name, Output<String> id, AiOptimizerHostedModelState state, CustomResourceOptions options)resources: _: type: castai:index/aiOptimizer:AiOptimizerHostedModel get: id: ${id}import {
to = castai_ai_optimizer_hosted_model.example
id = "${id}"
}
- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- resource_name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- Cloud
Provider string - Cloud provider.
- Cluster
Id string - CAST AI cluster ID where the model will be deployed.
- Current
Replicas int - Current number of replicas.
- Edge
Location List<string>Ids - List of edge location IDs where the model can be deployed.
- Fallback
Pulumi.
Cast AI. Inputs. Ai Optimizer Hosted Model Fallback - Fallback model settings.
- Hibernation
Pulumi.
Cast AI. Inputs. Ai Optimizer Hosted Model Hibernation - Automatic hibernation settings.
- Horizontal
Autoscaling Pulumi.Cast AI. Inputs. Ai Optimizer Hosted Model Horizontal Autoscaling - Horizontal autoscaling settings.
- Model
Specs stringId - ID of the model specs. Can reference a castai.AiOptimizerModelSpecs resource or a pre-existing model specs ID for predefined (CastAI-managed) models.
- Namespace string
- Kubernetes namespace.
- Node
Template stringName - Node template name for model deployment.
- Port int
- Port on which the model will be exposed.
- Region string
- Region the model is deployed in.
- Service string
- Kubernetes service name for the deployed model.
- Status string
- Hosted model status.
- Status
Reason string - Reason for the current status.
- Vllm
Config Pulumi.Cast AI. Inputs. Ai Optimizer Hosted Model Vllm Config - vLLM configuration for HuggingFace models.
- Cloud
Provider string - Cloud provider.
- Cluster
Id string - CAST AI cluster ID where the model will be deployed.
- Current
Replicas int - Current number of replicas.
- Edge
Location []stringIds - List of edge location IDs where the model can be deployed.
- Fallback
Ai
Optimizer Hosted Model Fallback Args - Fallback model settings.
- Hibernation
Ai
Optimizer Hosted Model Hibernation Args - Automatic hibernation settings.
- Horizontal
Autoscaling AiOptimizer Hosted Model Horizontal Autoscaling Args - Horizontal autoscaling settings.
- Model
Specs stringId - ID of the model specs. Can reference a castai.AiOptimizerModelSpecs resource or a pre-existing model specs ID for predefined (CastAI-managed) models.
- Namespace string
- Kubernetes namespace.
- Node
Template stringName - Node template name for model deployment.
- Port int
- Port on which the model will be exposed.
- Region string
- Region the model is deployed in.
- Service string
- Kubernetes service name for the deployed model.
- Status string
- Hosted model status.
- Status
Reason string - Reason for the current status.
- Vllm
Config AiOptimizer Hosted Model Vllm Config Args - vLLM configuration for HuggingFace models.
- cloud_
provider string - Cloud provider.
- cluster_
id string - CAST AI cluster ID where the model will be deployed.
- current_
replicas number - Current number of replicas.
- edge_
location_ list(string)ids - List of edge location IDs where the model can be deployed.
- fallback object
- Fallback model settings.
- hibernation object
- Automatic hibernation settings.
- horizontal_
autoscaling object - Horizontal autoscaling settings.
- model_
specs_ stringid - ID of the model specs. Can reference a castai.AiOptimizerModelSpecs resource or a pre-existing model specs ID for predefined (CastAI-managed) models.
- namespace string
- Kubernetes namespace.
- node_
template_ stringname - Node template name for model deployment.
- port number
- Port on which the model will be exposed.
- region string
- Region the model is deployed in.
- service string
- Kubernetes service name for the deployed model.
- status string
- Hosted model status.
- status_
reason string - Reason for the current status.
- vllm_
config object - vLLM configuration for HuggingFace models.
- cloud
Provider String - Cloud provider.
- cluster
Id String - CAST AI cluster ID where the model will be deployed.
- current
Replicas Integer - Current number of replicas.
- edge
Location List<String>Ids - List of edge location IDs where the model can be deployed.
- fallback
Ai
Optimizer Hosted Model Fallback - Fallback model settings.
- hibernation
Ai
Optimizer Hosted Model Hibernation - Automatic hibernation settings.
- horizontal
Autoscaling AiOptimizer Hosted Model Horizontal Autoscaling - Horizontal autoscaling settings.
- model
Specs StringId - ID of the model specs. Can reference a castai.AiOptimizerModelSpecs resource or a pre-existing model specs ID for predefined (CastAI-managed) models.
- namespace String
- Kubernetes namespace.
- node
Template StringName - Node template name for model deployment.
- port Integer
- Port on which the model will be exposed.
- region String
- Region the model is deployed in.
- service String
- Kubernetes service name for the deployed model.
- status String
- Hosted model status.
- status
Reason String - Reason for the current status.
- vllm
Config AiOptimizer Hosted Model Vllm Config - vLLM configuration for HuggingFace models.
- cloud
Provider string - Cloud provider.
- cluster
Id string - CAST AI cluster ID where the model will be deployed.
- current
Replicas number - Current number of replicas.
- edge
Location string[]Ids - List of edge location IDs where the model can be deployed.
- fallback
Ai
Optimizer Hosted Model Fallback - Fallback model settings.
- hibernation
Ai
Optimizer Hosted Model Hibernation - Automatic hibernation settings.
- horizontal
Autoscaling AiOptimizer Hosted Model Horizontal Autoscaling - Horizontal autoscaling settings.
- model
Specs stringId - ID of the model specs. Can reference a castai.AiOptimizerModelSpecs resource or a pre-existing model specs ID for predefined (CastAI-managed) models.
- namespace string
- Kubernetes namespace.
- node
Template stringName - Node template name for model deployment.
- port number
- Port on which the model will be exposed.
- region string
- Region the model is deployed in.
- service string
- Kubernetes service name for the deployed model.
- status string
- Hosted model status.
- status
Reason string - Reason for the current status.
- vllm
Config AiOptimizer Hosted Model Vllm Config - vLLM configuration for HuggingFace models.
- cloud_
provider str - Cloud provider.
- cluster_
id str - CAST AI cluster ID where the model will be deployed.
- current_
replicas int - Current number of replicas.
- edge_
location_ Sequence[str]ids - List of edge location IDs where the model can be deployed.
- fallback
Ai
Optimizer Hosted Model Fallback Args - Fallback model settings.
- hibernation
Ai
Optimizer Hosted Model Hibernation Args - Automatic hibernation settings.
- horizontal_
autoscaling AiOptimizer Hosted Model Horizontal Autoscaling Args - Horizontal autoscaling settings.
- model_
specs_ strid - ID of the model specs. Can reference a castai.AiOptimizerModelSpecs resource or a pre-existing model specs ID for predefined (CastAI-managed) models.
- namespace str
- Kubernetes namespace.
- node_
template_ strname - Node template name for model deployment.
- port int
- Port on which the model will be exposed.
- region str
- Region the model is deployed in.
- service str
- Kubernetes service name for the deployed model.
- status str
- Hosted model status.
- status_
reason str - Reason for the current status.
- vllm_
config AiOptimizer Hosted Model Vllm Config Args - vLLM configuration for HuggingFace models.
- cloud
Provider String - Cloud provider.
- cluster
Id String - CAST AI cluster ID where the model will be deployed.
- current
Replicas Number - Current number of replicas.
- edge
Location List<String>Ids - List of edge location IDs where the model can be deployed.
- fallback Property Map
- Fallback model settings.
- hibernation Property Map
- Automatic hibernation settings.
- horizontal
Autoscaling Property Map - Horizontal autoscaling settings.
- model
Specs StringId - ID of the model specs. Can reference a castai.AiOptimizerModelSpecs resource or a pre-existing model specs ID for predefined (CastAI-managed) models.
- namespace String
- Kubernetes namespace.
- node
Template StringName - Node template name for model deployment.
- port Number
- Port on which the model will be exposed.
- region String
- Region the model is deployed in.
- service String
- Kubernetes service name for the deployed model.
- status String
- Hosted model status.
- status
Reason String - Reason for the current status.
- vllm
Config Property Map - vLLM configuration for HuggingFace models.
Supporting Types
AiOptimizerHostedModelFallback, AiOptimizerHostedModelFallbackArgs
- Enabled bool
- Model string
- Provider
Id string
- Enabled bool
- Model string
- Provider
Id string
- enabled bool
- model string
- provider_
id string
- enabled Boolean
- model String
- provider
Id String
- enabled boolean
- model string
- provider
Id string
- enabled bool
- model str
- provider_
id str
- enabled Boolean
- model String
- provider
Id String
AiOptimizerHostedModelHibernation, AiOptimizerHostedModelHibernationArgs
AiOptimizerHostedModelHibernationHibernateCondition, AiOptimizerHostedModelHibernationHibernateConditionArgs
- Duration string
- Time period for the condition evaluation.
- Request
Count int - Request count threshold. Value of 0 is treated as not set.
- Duration string
- Time period for the condition evaluation.
- Request
Count int - Request count threshold. Value of 0 is treated as not set.
- duration string
- Time period for the condition evaluation.
- request_
count number - Request count threshold. Value of 0 is treated as not set.
- duration String
- Time period for the condition evaluation.
- request
Count Integer - Request count threshold. Value of 0 is treated as not set.
- duration string
- Time period for the condition evaluation.
- request
Count number - Request count threshold. Value of 0 is treated as not set.
- duration str
- Time period for the condition evaluation.
- request_
count int - Request count threshold. Value of 0 is treated as not set.
- duration String
- Time period for the condition evaluation.
- request
Count Number - Request count threshold. Value of 0 is treated as not set.
AiOptimizerHostedModelHibernationResumeCondition, AiOptimizerHostedModelHibernationResumeConditionArgs
- Duration string
- Time period for the condition evaluation.
- Request
Count int - Request count threshold. Value of 0 is treated as not set.
- Duration string
- Time period for the condition evaluation.
- Request
Count int - Request count threshold. Value of 0 is treated as not set.
- duration string
- Time period for the condition evaluation.
- request_
count number - Request count threshold. Value of 0 is treated as not set.
- duration String
- Time period for the condition evaluation.
- request
Count Integer - Request count threshold. Value of 0 is treated as not set.
- duration string
- Time period for the condition evaluation.
- request
Count number - Request count threshold. Value of 0 is treated as not set.
- duration str
- Time period for the condition evaluation.
- request_
count int - Request count threshold. Value of 0 is treated as not set.
- duration String
- Time period for the condition evaluation.
- request
Count Number - Request count threshold. Value of 0 is treated as not set.
AiOptimizerHostedModelHorizontalAutoscaling, AiOptimizerHostedModelHorizontalAutoscalingArgs
- Max
Replicas int - Min
Replicas int - Target
Metric string - Target
Value double - Enabled bool
- Max
Replicas int - Min
Replicas int - Target
Metric string - Target
Value float64 - Enabled bool
- max_
replicas number - min_
replicas number - target_
metric string - target_
value number - enabled bool
- max
Replicas Integer - min
Replicas Integer - target
Metric String - target
Value Double - enabled Boolean
- max
Replicas number - min
Replicas number - target
Metric string - target
Value number - enabled boolean
- max_
replicas int - min_
replicas int - target_
metric str - target_
value float - enabled bool
- max
Replicas Number - min
Replicas Number - target
Metric String - target
Value Number - enabled Boolean
AiOptimizerHostedModelVllmConfig, AiOptimizerHostedModelVllmConfigArgs
- Hugging
Face stringToken - HuggingFace token. Mutually exclusive with secret_name.
- Secret
Name string - Kubernetes secret name containing the HuggingFace token.
- Hugging
Face stringToken - HuggingFace token. Mutually exclusive with secret_name.
- Secret
Name string - Kubernetes secret name containing the HuggingFace token.
- hugging_
face_ stringtoken - HuggingFace token. Mutually exclusive with secret_name.
- secret_
name string - Kubernetes secret name containing the HuggingFace token.
- hugging
Face StringToken - HuggingFace token. Mutually exclusive with secret_name.
- secret
Name String - Kubernetes secret name containing the HuggingFace token.
- hugging
Face stringToken - HuggingFace token. Mutually exclusive with secret_name.
- secret
Name string - Kubernetes secret name containing the HuggingFace token.
- hugging_
face_ strtoken - HuggingFace token. Mutually exclusive with secret_name.
- secret_
name str - Kubernetes secret name containing the HuggingFace token.
- hugging
Face StringToken - HuggingFace token. Mutually exclusive with secret_name.
- secret
Name String - Kubernetes secret name containing the HuggingFace token.
Package Details
- Repository
- castai castai/pulumi-castai
- License
- Apache-2.0
- Notes
- This Pulumi package is based on the
castaiTerraform Provider.
Viewing docs for CAST AI v8.60.0
published on Wednesday, Aug 19, 2026 by CAST AI
published on Wednesday, Aug 19, 2026 by CAST AI