CfnInferenceComponentProps Struct
Properties for defining a CfnInferenceComponent.
| Source | |
|---|---|
| Type last changed |
Example
ts
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import { aws_sagemaker as sagemaker } from 'aws-cdk-lib';
const cfnInferenceComponentProps: sagemaker.CfnInferenceComponentProps = {
endpointName: 'endpointName',
// the properties below are optional
deploymentConfig: {
autoRollbackConfiguration: {
alarms: [{
alarmName: 'alarmName',
}],
},
rollingUpdatePolicy: {
maximumBatchSize: {
type: 'type',
value: 123,
},
maximumExecutionTimeoutInSeconds: 123,
rollbackMaximumBatchSize: {
type: 'type',
value: 123,
},
waitIntervalInSeconds: 123,
},
},
endpointArn: 'endpointArn',
inferenceComponentName: 'inferenceComponentName',
runtimeConfig: {
copyCount: 123,
currentCopyCount: 123,
desiredCopyCount: 123,
placementStatus: [{
currentCopyCount: 123,
instanceType: 'instanceType',
}],
},
specification: {
baseInferenceComponentName: 'baseInferenceComponentName',
computeResourceRequirements: {
maxMemoryRequiredInMb: 123,
minMemoryRequiredInMb: 123,
numberOfAcceleratorDevicesRequired: 123,
numberOfCpuCoresRequired: 123,
},
container: {
artifactUrl: 'artifactUrl',
containerMetricsConfig: {
metricsEndpoints: [{
metricsEndpointPath: 'metricsEndpointPath',
// the properties below are optional
metricPublishFrequencyInSeconds: 123,
}],
},
deployedImage: {
resolutionTime: 'resolutionTime',
resolvedImage: 'resolvedImage',
specifiedImage: 'specifiedImage',
},
environment: {
environmentKey: 'environment',
},
image: 'image',
},
currentDataCacheConfig: {
enableCaching: false,
},
dataCacheConfig: {
enableCaching: false,
},
modelName: 'modelName',
schedulingConfig: {
availabilityZoneBalance: {
enforcementMode: 'enforcementMode',
// the properties below are optional
maxImbalance: 123,
},
placementStrategy: 'placementStrategy',
},
startupParameters: {
containerStartupHealthCheckTimeoutInSeconds: 123,
modelDataDownloadTimeoutInSeconds: 123,
},
},
specifications: [{
instanceType: 'instanceType',
// the properties below are optional
computeResourceRequirements: {
maxMemoryRequiredInMb: 123,
minMemoryRequiredInMb: 123,
numberOfAcceleratorDevicesRequired: 123,
numberOfCpuCoresRequired: 123,
},
container: {
artifactUrl: 'artifactUrl',
containerMetricsConfig: {
metricsEndpoints: [{
metricsEndpointPath: 'metricsEndpointPath',
// the properties below are optional
metricPublishFrequencyInSeconds: 123,
}],
},
environment: {
environmentKey: 'environment',
},
image: 'image',
},
currentDataCacheConfig: {
enableCaching: false,
},
dataCacheConfig: {
enableCaching: false,
},
modelName: 'modelName',
schedulingConfig: {
availabilityZoneBalance: {
enforcementMode: 'enforcementMode',
// the properties below are optional
maxImbalance: 123,
},
placementStrategy: 'placementStrategy',
},
startupParameters: {
containerStartupHealthCheckTimeoutInSeconds: 123,
modelDataDownloadTimeoutInSeconds: 123,
},
}],
tags: [{
key: 'key',
value: 'value',
}],
variantName: 'variantName',
};
python
from aws_cdk import CfnTag
# The code below shows an example of how to instantiate this type.
# The values are placeholders you should change.
from aws_cdk import aws_sagemaker as sagemaker
cfn_inference_component_props = sagemaker.CfnInferenceComponentProps(
endpoint_name="endpointName",
# the properties below are optional
deployment_config=sagemaker.CfnInferenceComponent.InferenceComponentDeploymentConfigProperty(
auto_rollback_configuration=sagemaker.CfnInferenceComponent.AutoRollbackConfigurationProperty(
alarms=[sagemaker.CfnInferenceComponent.AlarmProperty(
alarm_name="alarmName"
)]
),
rolling_update_policy=sagemaker.CfnInferenceComponent.InferenceComponentRollingUpdatePolicyProperty(
maximum_batch_size=sagemaker.CfnInferenceComponent.InferenceComponentCapacitySizeProperty(
type="type",
value=123
),
maximum_execution_timeout_in_seconds=123,
rollback_maximum_batch_size=sagemaker.CfnInferenceComponent.InferenceComponentCapacitySizeProperty(
type="type",
value=123
),
wait_interval_in_seconds=123
)
),
endpoint_arn="endpointArn",
inference_component_name="inferenceComponentName",
runtime_config=sagemaker.CfnInferenceComponent.InferenceComponentRuntimeConfigProperty(
copy_count=123,
current_copy_count=123,
desired_copy_count=123,
placement_status=[sagemaker.CfnInferenceComponent.InferenceComponentPlacementStatusProperty(
current_copy_count=123,
instance_type="instanceType"
)]
),
specification=sagemaker.CfnInferenceComponent.InferenceComponentSpecificationProperty(
base_inference_component_name="baseInferenceComponentName",
compute_resource_requirements=sagemaker.CfnInferenceComponent.InferenceComponentComputeResourceRequirementsProperty(
max_memory_required_in_mb=123,
min_memory_required_in_mb=123,
number_of_accelerator_devices_required=123,
number_of_cpu_cores_required=123
),
container=sagemaker.CfnInferenceComponent.InferenceComponentContainerSpecificationProperty(
artifact_url="artifactUrl",
container_metrics_config=sagemaker.CfnInferenceComponent.ContainerMetricsConfigProperty(
metrics_endpoints=[sagemaker.CfnInferenceComponent.MetricsEndpointProperty(
metrics_endpoint_path="metricsEndpointPath",
# the properties below are optional
metric_publish_frequency_in_seconds=123
)]
),
deployed_image=sagemaker.CfnInferenceComponent.DeployedImageProperty(
resolution_time="resolutionTime",
resolved_image="resolvedImage",
specified_image="specifiedImage"
),
environment={
"environment_key": "environment"
},
image="image"
),
current_data_cache_config=sagemaker.CfnInferenceComponent.InferenceComponentDataCacheConfigProperty(
enable_caching=False
),
data_cache_config=sagemaker.CfnInferenceComponent.InferenceComponentDataCacheConfigProperty(
enable_caching=False
),
model_name="modelName",
scheduling_config=sagemaker.CfnInferenceComponent.InferenceComponentSchedulingConfigProperty(
availability_zone_balance=sagemaker.CfnInferenceComponent.InferenceComponentAvailabilityZoneBalanceProperty(
enforcement_mode="enforcementMode",
# the properties below are optional
max_imbalance=123
),
placement_strategy="placementStrategy"
),
startup_parameters=sagemaker.CfnInferenceComponent.InferenceComponentStartupParametersProperty(
container_startup_health_check_timeout_in_seconds=123,
model_data_download_timeout_in_seconds=123
)
),
specifications=[sagemaker.CfnInferenceComponent.InferenceComponentSpecificationForInstanceTypeProperty(
instance_type="instanceType",
# the properties below are optional
compute_resource_requirements=sagemaker.CfnInferenceComponent.InferenceComponentComputeResourceRequirementsProperty(
max_memory_required_in_mb=123,
min_memory_required_in_mb=123,
number_of_accelerator_devices_required=123,
number_of_cpu_cores_required=123
),
container=sagemaker.CfnInferenceComponent.InferenceComponentContainerSpecificationForInstanceTypeProperty(
artifact_url="artifactUrl",
container_metrics_config=sagemaker.CfnInferenceComponent.ContainerMetricsConfigProperty(
metrics_endpoints=[sagemaker.CfnInferenceComponent.MetricsEndpointProperty(
metrics_endpoint_path="metricsEndpointPath",
# the properties below are optional
metric_publish_frequency_in_seconds=123
)]
),
environment={
"environment_key": "environment"
},
image="image"
),
current_data_cache_config=sagemaker.CfnInferenceComponent.InferenceComponentDataCacheConfigProperty(
enable_caching=False
),
data_cache_config=sagemaker.CfnInferenceComponent.InferenceComponentDataCacheConfigProperty(
enable_caching=False
),
model_name="modelName",
scheduling_config=sagemaker.CfnInferenceComponent.InferenceComponentSchedulingConfigProperty(
availability_zone_balance=sagemaker.CfnInferenceComponent.InferenceComponentAvailabilityZoneBalanceProperty(
enforcement_mode="enforcementMode",
# the properties below are optional
max_imbalance=123
),
placement_strategy="placementStrategy"
),
startup_parameters=sagemaker.CfnInferenceComponent.InferenceComponentStartupParametersProperty(
container_startup_health_check_timeout_in_seconds=123,
model_data_download_timeout_in_seconds=123
)
)],
tags=[CfnTag(
key="key",
value="value"
)],
variant_name="variantName"
)
java
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import software.amazon.awscdk.services.sagemaker.*;
CfnInferenceComponentProps cfnInferenceComponentProps = CfnInferenceComponentProps.builder()
.endpointName("endpointName")
// the properties below are optional
.deploymentConfig(InferenceComponentDeploymentConfigProperty.builder()
.autoRollbackConfiguration(AutoRollbackConfigurationProperty.builder()
.alarms(List.of(AlarmProperty.builder()
.alarmName("alarmName")
.build()))
.build())
.rollingUpdatePolicy(InferenceComponentRollingUpdatePolicyProperty.builder()
.maximumBatchSize(InferenceComponentCapacitySizeProperty.builder()
.type("type")
.value(123)
.build())
.maximumExecutionTimeoutInSeconds(123)
.rollbackMaximumBatchSize(InferenceComponentCapacitySizeProperty.builder()
.type("type")
.value(123)
.build())
.waitIntervalInSeconds(123)
.build())
.build())
.endpointArn("endpointArn")
.inferenceComponentName("inferenceComponentName")
.runtimeConfig(InferenceComponentRuntimeConfigProperty.builder()
.copyCount(123)
.currentCopyCount(123)
.desiredCopyCount(123)
.placementStatus(List.of(InferenceComponentPlacementStatusProperty.builder()
.currentCopyCount(123)
.instanceType("instanceType")
.build()))
.build())
.specification(InferenceComponentSpecificationProperty.builder()
.baseInferenceComponentName("baseInferenceComponentName")
.computeResourceRequirements(InferenceComponentComputeResourceRequirementsProperty.builder()
.maxMemoryRequiredInMb(123)
.minMemoryRequiredInMb(123)
.numberOfAcceleratorDevicesRequired(123)
.numberOfCpuCoresRequired(123)
.build())
.container(InferenceComponentContainerSpecificationProperty.builder()
.artifactUrl("artifactUrl")
.containerMetricsConfig(ContainerMetricsConfigProperty.builder()
.metricsEndpoints(List.of(MetricsEndpointProperty.builder()
.metricsEndpointPath("metricsEndpointPath")
// the properties below are optional
.metricPublishFrequencyInSeconds(123)
.build()))
.build())
.deployedImage(DeployedImageProperty.builder()
.resolutionTime("resolutionTime")
.resolvedImage("resolvedImage")
.specifiedImage("specifiedImage")
.build())
.environment(Map.of(
"environmentKey", "environment"))
.image("image")
.build())
.currentDataCacheConfig(InferenceComponentDataCacheConfigProperty.builder()
.enableCaching(false)
.build())
.dataCacheConfig(InferenceComponentDataCacheConfigProperty.builder()
.enableCaching(false)
.build())
.modelName("modelName")
.schedulingConfig(InferenceComponentSchedulingConfigProperty.builder()
.availabilityZoneBalance(InferenceComponentAvailabilityZoneBalanceProperty.builder()
.enforcementMode("enforcementMode")
// the properties below are optional
.maxImbalance(123)
.build())
.placementStrategy("placementStrategy")
.build())
.startupParameters(InferenceComponentStartupParametersProperty.builder()
.containerStartupHealthCheckTimeoutInSeconds(123)
.modelDataDownloadTimeoutInSeconds(123)
.build())
.build())
.specifications(List.of(InferenceComponentSpecificationForInstanceTypeProperty.builder()
.instanceType("instanceType")
// the properties below are optional
.computeResourceRequirements(InferenceComponentComputeResourceRequirementsProperty.builder()
.maxMemoryRequiredInMb(123)
.minMemoryRequiredInMb(123)
.numberOfAcceleratorDevicesRequired(123)
.numberOfCpuCoresRequired(123)
.build())
.container(InferenceComponentContainerSpecificationForInstanceTypeProperty.builder()
.artifactUrl("artifactUrl")
.containerMetricsConfig(ContainerMetricsConfigProperty.builder()
.metricsEndpoints(List.of(MetricsEndpointProperty.builder()
.metricsEndpointPath("metricsEndpointPath")
// the properties below are optional
.metricPublishFrequencyInSeconds(123)
.build()))
.build())
.environment(Map.of(
"environmentKey", "environment"))
.image("image")
.build())
.currentDataCacheConfig(InferenceComponentDataCacheConfigProperty.builder()
.enableCaching(false)
.build())
.dataCacheConfig(InferenceComponentDataCacheConfigProperty.builder()
.enableCaching(false)
.build())
.modelName("modelName")
.schedulingConfig(InferenceComponentSchedulingConfigProperty.builder()
.availabilityZoneBalance(InferenceComponentAvailabilityZoneBalanceProperty.builder()
.enforcementMode("enforcementMode")
// the properties below are optional
.maxImbalance(123)
.build())
.placementStrategy("placementStrategy")
.build())
.startupParameters(InferenceComponentStartupParametersProperty.builder()
.containerStartupHealthCheckTimeoutInSeconds(123)
.modelDataDownloadTimeoutInSeconds(123)
.build())
.build()))
.tags(List.of(CfnTag.builder()
.key("key")
.value("value")
.build()))
.variantName("variantName")
.build();
csharp
// Install: dotnet add package Amazon.CDK.Lib
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
using Amazon.CDK.AWS.Sagemaker;
var cfnInferenceComponentProps = new CfnInferenceComponentProps {
EndpointName = "endpointName",
// the properties below are optional
DeploymentConfig = new InferenceComponentDeploymentConfigProperty {
AutoRollbackConfiguration = new AutoRollbackConfigurationProperty {
Alarms = new [] { new AlarmProperty {
AlarmName = "alarmName"
} }
},
RollingUpdatePolicy = new InferenceComponentRollingUpdatePolicyProperty {
MaximumBatchSize = new InferenceComponentCapacitySizeProperty {
Type = "type",
Value = 123
},
MaximumExecutionTimeoutInSeconds = 123,
RollbackMaximumBatchSize = new InferenceComponentCapacitySizeProperty {
Type = "type",
Value = 123
},
WaitIntervalInSeconds = 123
}
},
EndpointArn = "endpointArn",
InferenceComponentName = "inferenceComponentName",
RuntimeConfig = new InferenceComponentRuntimeConfigProperty {
CopyCount = 123,
CurrentCopyCount = 123,
DesiredCopyCount = 123,
PlacementStatus = new [] { new InferenceComponentPlacementStatusProperty {
CurrentCopyCount = 123,
InstanceType = "instanceType"
} }
},
Specification = new InferenceComponentSpecificationProperty {
BaseInferenceComponentName = "baseInferenceComponentName",
ComputeResourceRequirements = new InferenceComponentComputeResourceRequirementsProperty {
MaxMemoryRequiredInMb = 123,
MinMemoryRequiredInMb = 123,
NumberOfAcceleratorDevicesRequired = 123,
NumberOfCpuCoresRequired = 123
},
Container = new InferenceComponentContainerSpecificationProperty {
ArtifactUrl = "artifactUrl",
ContainerMetricsConfig = new ContainerMetricsConfigProperty {
MetricsEndpoints = new [] { new MetricsEndpointProperty {
MetricsEndpointPath = "metricsEndpointPath",
// the properties below are optional
MetricPublishFrequencyInSeconds = 123
} }
},
DeployedImage = new DeployedImageProperty {
ResolutionTime = "resolutionTime",
ResolvedImage = "resolvedImage",
SpecifiedImage = "specifiedImage"
},
Environment = new Dictionary<string, string> {
{ "environmentKey", "environment" }
},
Image = "image"
},
CurrentDataCacheConfig = new InferenceComponentDataCacheConfigProperty {
EnableCaching = false
},
DataCacheConfig = new InferenceComponentDataCacheConfigProperty {
EnableCaching = false
},
ModelName = "modelName",
SchedulingConfig = new InferenceComponentSchedulingConfigProperty {
AvailabilityZoneBalance = new InferenceComponentAvailabilityZoneBalanceProperty {
EnforcementMode = "enforcementMode",
// the properties below are optional
MaxImbalance = 123
},
PlacementStrategy = "placementStrategy"
},
StartupParameters = new InferenceComponentStartupParametersProperty {
ContainerStartupHealthCheckTimeoutInSeconds = 123,
ModelDataDownloadTimeoutInSeconds = 123
}
},
Specifications = new [] { new InferenceComponentSpecificationForInstanceTypeProperty {
InstanceType = "instanceType",
// the properties below are optional
ComputeResourceRequirements = new InferenceComponentComputeResourceRequirementsProperty {
MaxMemoryRequiredInMb = 123,
MinMemoryRequiredInMb = 123,
NumberOfAcceleratorDevicesRequired = 123,
NumberOfCpuCoresRequired = 123
},
Container = new InferenceComponentContainerSpecificationForInstanceTypeProperty {
ArtifactUrl = "artifactUrl",
ContainerMetricsConfig = new ContainerMetricsConfigProperty {
MetricsEndpoints = new [] { new MetricsEndpointProperty {
MetricsEndpointPath = "metricsEndpointPath",
// the properties below are optional
MetricPublishFrequencyInSeconds = 123
} }
},
Environment = new Dictionary<string, string> {
{ "environmentKey", "environment" }
},
Image = "image"
},
CurrentDataCacheConfig = new InferenceComponentDataCacheConfigProperty {
EnableCaching = false
},
DataCacheConfig = new InferenceComponentDataCacheConfigProperty {
EnableCaching = false
},
ModelName = "modelName",
SchedulingConfig = new InferenceComponentSchedulingConfigProperty {
AvailabilityZoneBalance = new InferenceComponentAvailabilityZoneBalanceProperty {
EnforcementMode = "enforcementMode",
// the properties below are optional
MaxImbalance = 123
},
PlacementStrategy = "placementStrategy"
},
StartupParameters = new InferenceComponentStartupParametersProperty {
ContainerStartupHealthCheckTimeoutInSeconds = 123,
ModelDataDownloadTimeoutInSeconds = 123
}
} },
Tags = new [] { new CfnTag {
Key = "key",
Value = "value"
} },
VariantName = "variantName"
};
go
// Install: go get github.com/aws/aws-cdk-go/awscdk/v2
// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import "github.com/aws/aws-cdk-go/awscdk"
cfnInferenceComponentProps := &CfnInferenceComponentProps{
EndpointName: jsii.String("endpointName"),
// the properties below are optional
DeploymentConfig: &InferenceComponentDeploymentConfigProperty{
AutoRollbackConfiguration: &AutoRollbackConfigurationProperty{
Alarms: []interface{}{
&AlarmProperty{
AlarmName: jsii.String("alarmName"),
},
},
},
RollingUpdatePolicy: &InferenceComponentRollingUpdatePolicyProperty{
MaximumBatchSize: &InferenceComponentCapacitySizeProperty{
Type: jsii.String("type"),
Value: jsii.Number(123),
},
MaximumExecutionTimeoutInSeconds: jsii.Number(123),
RollbackMaximumBatchSize: &InferenceComponentCapacitySizeProperty{
Type: jsii.String("type"),
Value: jsii.Number(123),
},
WaitIntervalInSeconds: jsii.Number(123),
},
},
EndpointArn: jsii.String("endpointArn"),
InferenceComponentName: jsii.String("inferenceComponentName"),
RuntimeConfig: &InferenceComponentRuntimeConfigProperty{
CopyCount: jsii.Number(123),
CurrentCopyCount: jsii.Number(123),
DesiredCopyCount: jsii.Number(123),
PlacementStatus: []interface{}{
&InferenceComponentPlacementStatusProperty{
CurrentCopyCount: jsii.Number(123),
InstanceType: jsii.String("instanceType"),
},
},
},
Specification: &InferenceComponentSpecificationProperty{
BaseInferenceComponentName: jsii.String("baseInferenceComponentName"),
ComputeResourceRequirements: &InferenceComponentComputeResourceRequirementsProperty{
MaxMemoryRequiredInMb: jsii.Number(123),
MinMemoryRequiredInMb: jsii.Number(123),
NumberOfAcceleratorDevicesRequired: jsii.Number(123),
NumberOfCpuCoresRequired: jsii.Number(123),
},
Container: &InferenceComponentContainerSpecificationProperty{
ArtifactUrl: jsii.String("artifactUrl"),
ContainerMetricsConfig: &ContainerMetricsConfigProperty{
MetricsEndpoints: []interface{}{
&MetricsEndpointProperty{
MetricsEndpointPath: jsii.String("metricsEndpointPath"),
// the properties below are optional
MetricPublishFrequencyInSeconds: jsii.Number(123),
},
},
},
DeployedImage: &DeployedImageProperty{
ResolutionTime: jsii.String("resolutionTime"),
ResolvedImage: jsii.String("resolvedImage"),
SpecifiedImage: jsii.String("specifiedImage"),
},
Environment: map[string]*string{
"environmentKey": jsii.String("environment"),
},
Image: jsii.String("image"),
},
CurrentDataCacheConfig: &InferenceComponentDataCacheConfigProperty{
EnableCaching: jsii.Boolean(false),
},
DataCacheConfig: &InferenceComponentDataCacheConfigProperty{
EnableCaching: jsii.Boolean(false),
},
ModelName: jsii.String("modelName"),
SchedulingConfig: &InferenceComponentSchedulingConfigProperty{
AvailabilityZoneBalance: &InferenceComponentAvailabilityZoneBalanceProperty{
EnforcementMode: jsii.String("enforcementMode"),
// the properties below are optional
MaxImbalance: jsii.Number(123),
},
PlacementStrategy: jsii.String("placementStrategy"),
},
StartupParameters: &InferenceComponentStartupParametersProperty{
ContainerStartupHealthCheckTimeoutInSeconds: jsii.Number(123),
ModelDataDownloadTimeoutInSeconds: jsii.Number(123),
},
},
Specifications: []interface{}{
&InferenceComponentSpecificationForInstanceTypeProperty{
InstanceType: jsii.String("instanceType"),
// the properties below are optional
ComputeResourceRequirements: &InferenceComponentComputeResourceRequirementsProperty{
MaxMemoryRequiredInMb: jsii.Number(123),
MinMemoryRequiredInMb: jsii.Number(123),
NumberOfAcceleratorDevicesRequired: jsii.Number(123),
NumberOfCpuCoresRequired: jsii.Number(123),
},
Container: &InferenceComponentContainerSpecificationForInstanceTypeProperty{
ArtifactUrl: jsii.String("artifactUrl"),
ContainerMetricsConfig: &ContainerMetricsConfigProperty{
MetricsEndpoints: []interface{}{
&MetricsEndpointProperty{
MetricsEndpointPath: jsii.String("metricsEndpointPath"),
// the properties below are optional
MetricPublishFrequencyInSeconds: jsii.Number(123),
},
},
},
Environment: map[string]*string{
"environmentKey": jsii.String("environment"),
},
Image: jsii.String("image"),
},
CurrentDataCacheConfig: &InferenceComponentDataCacheConfigProperty{
EnableCaching: jsii.Boolean(false),
},
DataCacheConfig: &InferenceComponentDataCacheConfigProperty{
EnableCaching: jsii.Boolean(false),
},
ModelName: jsii.String("modelName"),
SchedulingConfig: &InferenceComponentSchedulingConfigProperty{
AvailabilityZoneBalance: &InferenceComponentAvailabilityZoneBalanceProperty{
EnforcementMode: jsii.String("enforcementMode"),
// the properties below are optional
MaxImbalance: jsii.Number(123),
},
PlacementStrategy: jsii.String("placementStrategy"),
},
StartupParameters: &InferenceComponentStartupParametersProperty{
ContainerStartupHealthCheckTimeoutInSeconds: jsii.Number(123),
ModelDataDownloadTimeoutInSeconds: jsii.Number(123),
},
},
},
Tags: []CfnTag{
&CfnTag{
Key: jsii.String("key"),
Value: jsii.String("value"),
},
},
VariantName: jsii.String("variantName"),
}
Properties
deploymentConfigoptionalIResolvable | CfnInferenceComponent.deployment_configoptionaltyping.Union[IResolvable, InferenceComponentDeploymentConfigProperty]deploymentConfigoptionalIResolvableDeploymentConfigoptionalIResolvableDeploymentConfigoptionalinterface{} #The deployment configuration for an endpoint, which contains the desired deployment strategy and rollback configurations.
endpointArnoptionalstringendpoint_arnoptionalstrendpointArnoptionalStringEndpointArnoptionalstringEndpointArnoptional*string #The Amazon Resource Name (ARN) of the endpoint that hosts the inference component.
endpointNamestringendpoint_namestrendpointNameStringEndpointNamestringEndpointName*string required #The name of the endpoint that hosts the inference component.
inferenceComponentNameoptionalstringinference_component_nameoptionalstrinferenceComponentNameoptionalStringInferenceComponentNameoptionalstringInferenceComponentNameoptional*string #The name of the inference component.
runtimeConfigoptionalIResolvable | CfnInferenceComponent.runtime_configoptionaltyping.Union[IResolvable, InferenceComponentRuntimeConfigProperty]runtimeConfigoptionalIResolvableRuntimeConfigoptionalIResolvableRuntimeConfigoptionalinterface{} #The runtime config for the inference component.
specificationoptionalIResolvable | CfnInferenceComponent.specificationoptionaltyping.Union[IResolvable, InferenceComponentSpecificationProperty]specificationoptionalIResolvableSpecificationoptionalIResolvableSpecificationoptionalinterface{} #The specification for the inference component, for an endpoint with a single instance type.
Specify exactly one of Specification or Specifications. InstanceType is not accepted here; use Specifications for per instance type configuration.
specificationsoptionalIResolvable | IResolvable | CfnInferenceComponent.specificationsoptionaltyping.Union[IResolvable, typing.List[typing.Union[IResolvable, InferenceComponentSpecificationForInstanceTypeProperty]]]specificationsoptionalIResolvableSpecificationsoptionalIResolvableSpecificationsoptionalinterface{} #A list of specification objects for the inference component, one per instance type.
The service requires at least two entries; use the singular Specification for a single instance type.
tagsoptionalCfnTag[]tagsoptionaltyping.List[CfnTag]tagsoptionalList<CfnTag>TagsoptionalCfnTag[]Tagsoptional*[]CfnTag #An array of tags to apply to the resource.
variantNameoptionalstringvariant_nameoptionalstrvariantNameoptionalStringVariantNameoptionalstringVariantNameoptional*string #The name of the production variant that hosts the inference component.