| Column Name | Column Data Type |
|---|
inference_recommendations_job_name Required Input Column
The name of a previously completed Inference Recommender job. | VARCHAR |
endpoint_name Input Column
The name of an endpoint benchmarked during a previously completed Inference Recommender job. | VARCHAR |
recommendation_id Input Column
The recommendation ID of a previously completed inference recommendation. | VARCHAR |
scaling_policy_objective Input Column
An object representing the anticipated traffic pattern for an endpoint that you specified in the request. | STRUCT(
"min_invocations_per_minute" BIGINT,
"max_invocations_per_minute" BIGINT
) |
Show child fields- scaling_policy_objective.max_invocations_per_minute
The maximum number of expected requests to your endpoint per minute. - scaling_policy_objective.min_invocations_per_minute
The minimum number of expected requests to your endpoint per minute.
|
target_cpu_utilization_per_core Input Column
The percentage of how much utilization you want an instance to use before autoscaling, which you specified in the request. The default value is 50%. | BIGINT |
_aws_profile Input Column
The AWS profile defines the AWS identity used. It can be defined via credentials or by assuming a IAM role. | STRUCT(
"type" VARCHAR,
"name" VARCHAR,
"account_id" VARCHAR,
"via_profile_name" VARCHAR,
"assumed_role_arn" VARCHAR,
"organization" STRUCT(
"account_name" VARCHAR,
"id" VARCHAR,
"tags" STRUCT(
"key" VARCHAR,
"value" VARCHAR
)[],
"master_account" STRUCT(
"id" VARCHAR,
"email" VARCHAR
),
"parents" STRUCT(
"type" VARCHAR,
"id" VARCHAR,
"name" VARCHAR,
"tags" STRUCT(
"key" VARCHAR,
"value" VARCHAR
)[]
)[]
)
) |
Show child fields- _aws_profile.account_id
The AWS account id - _aws_profile.assumed_role_arn
The ARN of the assumed role - _aws_profile.name
The unique name of the profile. - _aws_profile.organization
Information about this profile's membership in the AWS organization. Show child fields- _aws_profile.organization.account_name
The name of account speciifed by the organization - _aws_profile.organization.id
The organization id - _aws_profile.organization.master_account
Show child fields- _aws_profile.organization.master_account.email
The organization master account email address - _aws_profile.organization.master_account.id
The organization master account id
- _aws_profile.organization.parents[]
Show child fields- _aws_profile.organization.parents[].id
The id of the parent - _aws_profile.organization.parents[].name
The name of the parent - _aws_profile.organization.parents[].tags[]
Show child fields- _aws_profile.organization.parents[].tags[].key
- _aws_profile.organization.parents[].tags[].value
- _aws_profile.organization.parents[].type
The type of parent can be an organization unit or a root
- _aws_profile.organization.tags[]
Show child fields- _aws_profile.organization.tags[].key
- _aws_profile.organization.tags[].value
- _aws_profile.type
The type of profile, either 'credentials' or 'assumed_role' - _aws_profile.via_profile_name
This IAM role for this profile is assumed by first utilizing another profile with this name to obtain credentials.
|
dynamic_scaling_configuration
An object with the recommended values for you to specify when creating an autoscaling policy. | STRUCT(
"min_capacity" BIGINT,
"max_capacity" BIGINT,
"scale_in_cooldown" BIGINT,
"scale_out_cooldown" BIGINT,
"scaling_policies" STRUCT(
"target_tracking" STRUCT(
"metric_specification" STRUCT(
"predefined" STRUCT(
"predefined_metric_type" VARCHAR
),
"customized" STRUCT(
"metric_name" VARCHAR,
"namespace" VARCHAR,
"statistic" VARCHAR
)
),
"target_value" DOUBLE
)
)[]
) |
Show child fields- dynamic_scaling_configuration.max_capacity
The recommended maximum capacity to specify for your autoscaling policy. - dynamic_scaling_configuration.min_capacity
The recommended minimum capacity to specify for your autoscaling policy. - dynamic_scaling_configuration.scale_in_cooldown
The recommended scale in cooldown time for your autoscaling policy. - dynamic_scaling_configuration.scale_out_cooldown
The recommended scale out cooldown time for your autoscaling policy. - dynamic_scaling_configuration.scaling_policies[]
Show child fields- dynamic_scaling_configuration.scaling_policies[].target_tracking
A target tracking scaling policy. Includes support for predefined or customized metrics. Show child fields- dynamic_scaling_configuration.scaling_policies[].target_tracking.metric_specification
An object containing information about a metric. Show child fields- dynamic_scaling_configuration.scaling_policies[].target_tracking.metric_specification.customized
Information about a customized metric. Show child fields- dynamic_scaling_configuration.scaling_policies[].target_tracking.metric_specification.customized.metric_name
The name of the customized metric. - dynamic_scaling_configuration.scaling_policies[].target_tracking.metric_specification.customized.namespace
The namespace of the customized metric. - dynamic_scaling_configuration.scaling_policies[].target_tracking.metric_specification.customized.statistic
The statistic of the customized metric.
- dynamic_scaling_configuration.scaling_policies[].target_tracking.metric_specification.predefined
Information about a predefined metric. Show child fields- dynamic_scaling_configuration.scaling_policies[].target_tracking.metric_specification.predefined.predefined_metric_type
The metric type. You can only apply SageMaker metric types to SageMaker endpoints.
- dynamic_scaling_configuration.scaling_policies[].target_tracking.target_value
The recommended target value to specify for the metric when creating a scaling policy.
|
metric
An object with a list of metrics that were benchmarked during the previously completed Inference Recommender job. | STRUCT(
"invocations_per_instance" BIGINT,
"model_latency" BIGINT
) |
Show child fields- metric.invocations_per_instance
The number of invocations sent to a model, normalized by InstanceCount in each ProductionVariant. 1/numberOfInstances is sent as the value on each request, where numberOfInstances is the number of active instances for the ProductionVariant behind the endpoint at the time of the request. - metric.model_latency
The interval of time taken by a model to respond as viewed from SageMaker. This interval includes the local communication times taken to send the request and to fetch the response from the container of a model and the time taken to complete the inference in the container.
|