SageMaker Compilation Job

Docs > DDSQL Reference > Data Directory > SageMaker Compilation Job

An AWS SageMaker Compilation Job optimizes trained machine learning models for deployment on specific hardware targets such as CPUs, GPUs, or edge devices. It converts models into an efficient format that improves performance and reduces latency without changing accuracy. This helps accelerate inference and lower resource costs when running predictions.

aws.sagemaker_compilation_job

Fields

ID	Type	Data Type	Description
_key	core	string
account_id	core	string
compilation_end_time	core	timestamp	The time when the model compilation job on a compilation job instance ended. For a successful or stopped job, this is when the job's model artifacts have finished uploading. For a failed job, this is when Amazon SageMaker AI detected that the job failed.
compilation_job_arn	core	string	The Amazon Resource Name (ARN) of the model compilation job.
compilation_job_name	core	string	The name of the model compilation job.
compilation_job_status	core	string	The status of the model compilation job.
compilation_start_time	core	timestamp	The time when the model compilation job started the CompilationJob instances. You are billed for the time between this timestamp and the timestamp in the CompilationEndTime field. In Amazon CloudWatch Logs, the start time might be later than this time. That's because it takes time to download the compilation job, which depends on the size of the compilation job container.
creation_time	core	timestamp	The time that the model compilation job was created.
derived_information	core	json	Information that SageMaker Neo automatically derived about the model.
failure_reason	core	string	If a model compilation job failed, the reason it failed.
inference_image	core	string	The inference image to use when compiling a model. Specify an image only if the target device is a cloud instance.
input_config	core	json	Information about the location in Amazon S3 of the input model artifacts, the name and shape of the expected data inputs, and the framework in which the model was trained.
last_modified_time	core	timestamp	The time that the status of the model compilation job was last modified.
model_artifacts	core	json	Information about the location in Amazon S3 that has been configured for storing the model artifacts used in the compilation job.
model_digests	core	json	Provides a BLAKE2 hash value that identifies the compiled model artifacts in Amazon S3.
model_package_version_arn	core	string	The Amazon Resource Name (ARN) of the versioned model package that was provided to SageMaker Neo when you initiated a compilation job.
output_config	core	json	Information about the output location for the compiled model and the target device that the model runs on.
role_arn	core	string	The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI assumes to perform the model compilation job.
stopping_condition	core	json	Specifies a limit to how long a model compilation job can run. When the job reaches the time limit, Amazon SageMaker AI ends the compilation job. Use this API to cap model training costs.
tags	core	hstore
vpc_config	core	json	A VpcConfig object that specifies the VPC that you want your compilation job to connect to. Control access to your models by configuring the VPC. For more information, see Protect Compilation Jobs by Using an Amazon Virtual Private Cloud.