Type object
Schema URL https://catalog.lintel.tools/schemas/schemastore/serverless-framework-configuration/_shared/latest--aws-sagemaker-inferenceexperiment.json
Parent schema serverless-framework-configuration
Type: object

Resource Type definition for AWS::SageMaker::InferenceExperiment. Source:- No source definition found, add manually please

Properties

Name string | Aws_CF_FunctionString required

The name for the inference experiment.

Type string | Aws_CF_FunctionString required

The type of the inference experiment that you want to run.

RoleArn string | Aws_CF_FunctionString required

The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker can assume to access model artifacts and container images, and manage Amazon SageMaker Inference endpoints for model deployment.

EndpointName string | Aws_CF_FunctionString required

The name of the endpoint used to run the inference experiment.

ModelVariants ModelVariantConfig[] required

An array of ModelVariantConfig objects. Each ModelVariantConfig object in the array describes the infrastructure configuration for the corresponding variant.

maxItems=2
Description string | Aws_CF_FunctionString

The description of the inference experiment.

Schedule object

The duration for which you want the inference experiment to run.

2 nested properties
StartTime string | Aws_CF_FunctionString

The timestamp at which the inference experiment started or will start.

EndTime string | Aws_CF_FunctionString

The timestamp at which the inference experiment ended or will end.

KmsKey string | Aws_CF_FunctionString

The AWS Key Management Service (AWS KMS) key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.

DataStorageConfig object

The Amazon S3 location and configuration for storing inference request and response data.

3 nested properties
Destination string | Aws_CF_FunctionString required

The Amazon S3 bucket where the inference request and response data is stored.

KmsKey string | Aws_CF_FunctionString

The AWS Key Management Service key that Amazon SageMaker uses to encrypt captured data at rest using Amazon S3 server-side encryption.

ContentType object

Configuration specifying how to treat different headers. If no headers are specified SageMaker will by default base64 encode when capturing the data.

2 nested properties
CsvContentTypes string[]

The list of all content type headers that SageMaker will treat as CSV and capture accordingly.

minItems=1maxItems=10
JsonContentTypes string[]

The list of all content type headers that SageMaker will treat as JSON and capture accordingly.

minItems=1maxItems=10
ShadowModeConfig object

The configuration of ShadowMode inference experiment type. Use this field to specify a production variant which takes all the inference requests, and a shadow variant to which Amazon SageMaker replicates a percentage of the inference requests. For the shadow variant also specify the percentage of requests that Amazon SageMaker replicates.

2 nested properties
SourceModelVariantName string | Aws_CF_FunctionString required

The name of the production variant, which takes all the inference requests.

ShadowModelVariants ShadowModelVariantConfig[] required

List of shadow variant configurations.

minItems=1maxItems=1
Tags Tag[]

An array of key-value pairs to apply to this resource.

maxItems=50
StatusReason string | Aws_CF_FunctionString

The error message or client-specified reason from the StopInferenceExperiment API, that explains the status of the inference experiment.

DesiredState string | Aws_CF_FunctionString

The desired state of the experiment after starting or stopping operation.

Definitions

EndpointName string | Aws_CF_FunctionString

The name of the endpoint used to run the inference experiment.

EndpointMetadata object

The metadata of the endpoint on which the inference experiment ran.

EndpointName string | Aws_CF_FunctionString required

The name of the endpoint used to run the inference experiment.

EndpointConfigName string | Aws_CF_FunctionString

The name of the endpoint configuration.

EndpointStatus string | Aws_CF_FunctionString

The status of the endpoint. For possible values of the status of an endpoint.

CaptureContentTypeHeader object

Configuration specifying how to treat different headers. If no headers are specified SageMaker will by default base64 encode when capturing the data.

CsvContentTypes string[]

The list of all content type headers that SageMaker will treat as CSV and capture accordingly.

minItems=1maxItems=10
JsonContentTypes string[]

The list of all content type headers that SageMaker will treat as JSON and capture accordingly.

minItems=1maxItems=10
DataStorageConfig object

The Amazon S3 location and configuration for storing inference request and response data.

Destination string | Aws_CF_FunctionString required

The Amazon S3 bucket where the inference request and response data is stored.

KmsKey string | Aws_CF_FunctionString

The AWS Key Management Service key that Amazon SageMaker uses to encrypt captured data at rest using Amazon S3 server-side encryption.

ContentType object

Configuration specifying how to treat different headers. If no headers are specified SageMaker will by default base64 encode when capturing the data.

2 nested properties
CsvContentTypes string[]

The list of all content type headers that SageMaker will treat as CSV and capture accordingly.

minItems=1maxItems=10
JsonContentTypes string[]

The list of all content type headers that SageMaker will treat as JSON and capture accordingly.

minItems=1maxItems=10
InferenceExperimentSchedule object

The duration for which you want the inference experiment to run.

StartTime string | Aws_CF_FunctionString

The timestamp at which the inference experiment started or will start.

EndTime string | Aws_CF_FunctionString

The timestamp at which the inference experiment ended or will end.

RealTimeInferenceConfig object

The infrastructure configuration for deploying the model to a real-time inference endpoint.

InstanceType string | Aws_CF_FunctionString required

The instance type the model is deployed to.

InstanceCount integer required

The number of instances of the type specified by InstanceType.

ModelInfrastructureConfig object

The configuration for the infrastructure that the model will be deployed to.

InfrastructureType string | Aws_CF_FunctionString required

The type of the inference experiment that you want to run.

RealTimeInferenceConfig object required

The infrastructure configuration for deploying the model to a real-time inference endpoint.

2 nested properties
InstanceType string | Aws_CF_FunctionString required

The instance type the model is deployed to.

InstanceCount integer required

The number of instances of the type specified by InstanceType.

ModelVariantConfig object

Contains information about the deployment options of a model.

ModelName string | Aws_CF_FunctionString required

The name of the Amazon SageMaker Model entity.

VariantName string | Aws_CF_FunctionString required

The name of the variant.

InfrastructureConfig object required

The configuration for the infrastructure that the model will be deployed to.

2 nested properties
InfrastructureType string | Aws_CF_FunctionString required

The type of the inference experiment that you want to run.

RealTimeInferenceConfig object required

The infrastructure configuration for deploying the model to a real-time inference endpoint.

2 nested properties
InstanceType string | Aws_CF_FunctionString required

The instance type the model is deployed to.

InstanceCount integer required

The number of instances of the type specified by InstanceType.

ShadowModelVariantConfig object

The name and sampling percentage of a shadow variant.

ShadowModelVariantName string | Aws_CF_FunctionString required

The name of the shadow variant.

SamplingPercentage integer required

The percentage of inference requests that Amazon SageMaker replicates from the production variant to the shadow variant.

max=100
ShadowModeConfig object

The configuration of ShadowMode inference experiment type. Use this field to specify a production variant which takes all the inference requests, and a shadow variant to which Amazon SageMaker replicates a percentage of the inference requests. For the shadow variant also specify the percentage of requests that Amazon SageMaker replicates.

SourceModelVariantName string | Aws_CF_FunctionString required

The name of the production variant, which takes all the inference requests.

ShadowModelVariants ShadowModelVariantConfig[] required

List of shadow variant configurations.

minItems=1maxItems=1
Tag object

A key-value pair to associate with a resource.

Key string | Aws_CF_FunctionString required

The key name of the tag. You can specify a value that is 1 to 127 Unicode characters in length and cannot be prefixed with aws:. You can use any of the following characters: the set of Unicode letters, digits, whitespace, _, ., /, =, +, and -.

Value string | Aws_CF_FunctionString required

The value for the tag. You can specify a value that is 1 to 255 Unicode characters in length and cannot be prefixed with aws:. You can use any of the following characters: the set of Unicode letters, digits, whitespace, _, ., /, =, +, and -.