Using AWS SageMaker Endpoint - Revision history

PSuthar: Final edit

2024-08-14T18:51:38Z

Final edit

PSuthar at 19:13, 13 August 2024

2024-08-13T19:13:47Z

PSuthar at 19:11, 13 August 2024

2024-08-13T19:11:58Z

PSuthar: Add sagemaker endpoint initial content

2024-08-13T19:04:02Z

Add sagemaker endpoint initial content

PSuthar: Initial SM Endpoint

2024-08-12T19:28:58Z

Initial SM Endpoint

New page

To empower demanding workloads and specialized use cases with tailored compute resources, we leverage both managed HPC platforms on AWS and Azure as well as customizable virtual machines. This approach offers the best of both worlds.

== What is SageMaker Endpoint? ==
Amazon SageMaker is a fully managed machine learning service that enables data scientists and developers to build, train, and deploy machine learning models at scale. One of the key features of SageMaker is the ability to deploy machine learning models as endpoints, which can be invoked to make predictions on new data.

===Benefits of SageMaker Endpoint===
*'''Scalability:'''
*

@@ Line 16: / Line 16: @@
 * Select the model you created in the previous step.
 * Click on “Create endpoint”. Your SageMaker endpoint is now ready to be invoked.
 Remember: It's crucial to delete or scale down your endpoint when not actively in use to avoid unnecessary charges.

@@ Line 4: / Line 4: @@
 Amazon SageMaker is a fully managed machine learning service that enables data scientists and developers to build, train, and deploy machine learning models at scale. One of the key features of SageMaker is the ability to deploy machine learning models as endpoints, which can be invoked to make predictions on new data. Real-time inference is ideal for inference workloads where you have real-time, interactive, low latency requirements. You can deploy your model to SageMaker hosting services and get an endpoint that can be used for inference. These endpoints are fully managed and support autoscaling.
-=== Prerequisite for setting up SageMaker Endpoint (Model Artifact)===
+== Prerequisite for setting up SageMaker Endpoint (Model Artifact)==
 * After you are done with the modeling phase you can store the trained model on your project allocated s3 bucket.
 * Open the SageMaker console and open "Inference" on left panel and click on “Create model".
@@ Line 11: / Line 11: @@
 * Specify any additional configuration settings (e.g., instance type, number of instances).
-=== Setting up a SageMaker Endpoint ===
+== Setting up a SageMaker Endpoint ==
 * Open the SageMaker console and open "Inference" on left panel and click on “Create endpoint”.
 * Give your endpoint a name and choose the appropriate configuration settings (e.g., instance type, number of instances).

← Older revision		Revision as of 19:11, 13 August 2024
Line 16:		Line 16:
	* Select the model you created in the previous step.		* Select the model you created in the previous step.
	* Click on “Create endpoint”. Your SageMaker endpoint is now ready to be invoked.		* Click on “Create endpoint”. Your SageMaker endpoint is now ready to be invoked.
		+
		+	Remember: It's crucial to delete or scale down your endpoint when not actively in use to avoid unnecessary charges.

@@ Line 1: / Line 1: @@
-To empower demanding workloads and specialized use cases with tailored compute resources, we leverage both managed HPC platforms on AWS and Azure as well as customizable virtual machines. This approach offers the best of both worlds.
+Amazon SageMaker is a managed ML service that helps you build and train models and then deploy them into a production-ready hosted environment.
 == What is SageMaker Endpoint? ==
-Amazon SageMaker is a fully managed machine learning service that enables data scientists and developers to build, train, and deploy machine learning models at scale. One of the key features of SageMaker is the ability to deploy machine learning models as endpoints, which can be invoked to make predictions on new data.
+Amazon SageMaker is a fully managed machine learning service that enables data scientists and developers to build, train, and deploy machine learning models at scale. One of the key features of SageMaker is the ability to deploy machine learning models as endpoints, which can be invoked to make predictions on new data. Real-time inference is ideal for inference workloads where you have real-time, interactive, low latency requirements. You can deploy your model to SageMaker hosting services and get an endpoint that can be used for inference. These endpoints are fully managed and support autoscaling.
-===Benefits of SageMaker Endpoint===
+=== Prerequisite for setting up SageMaker Endpoint (Model Artifact)===
-*'''Scalability:'''
+* After you are done with the modeling phase you can store the trained model on your project allocated s3 bucket.
+* Open the SageMaker console and open "Inference" on left panel and click on “Create model".