AWS re:Post Knowledge Center Feedback Survey

Help us improve the AWS re:Post Knowledge Center by sharing your feedback in a brief survey. Your input can influence how we create and update our content to better support your AWS journey.

Sagemaker endpoint scaling issues

"errorCode": "ResourceLimitExceeded", "errorMessage": "The account-level service limit 'ml.p3.8xlarge for endpoint usage' is 1 Instances, with current utilization of 2 Instances and a request delta of 3 Instances. Please contact AWS support to request an increase for this limit."

Topics: Machine Learning & AI Storage
Tags: Amazon SageMaker Machine Learning & AI
Language: English

Apprentus

asked 3 years ago525 views

1 Answer

Newest
Most votes
Most comments

Accepted Answer

I understand that you enabled the Auto scaling for SageMaker Endpoint with the instance type "ml.p3.8xlarge" and found that scaling was not happened due to the following error.

-"errorCode": "ResourceLimitExceeded",

Please go forward with a limit increase for "ml.p3.8xlarge" to 5.

Check this link for further information : https://docs.aws.amazon.com/sagemaker/latest/dg/regions-quotas.html#regions-quotas-quotas

Wael

answered 3 years ago

EXPERT

Oleksii Bebych

reviewed 2 years ago

Relevant content

Best Practices for Fast Scaling SageMaker Async Endpoint from 0 to 1 Instance for Single Requests
Yuval Mehta
asked 2 years ago
My Sagemaker Asynchronous Endpoint goes down to zero instances after 10 minutes.
AlArgente
asked a year ago
What are the limitations with the Data capture on Sagemaker AI Endpoint Config?
George
asked 3 months ago
The CPU Utilization metric for Sagemaker Endpoint is empty.
Vad
asked 3 years ago
How do I troubleshoot auto scaling issues for SageMaker AI endpoints?
AWS OFFICIALUpdated a year ago
How do I prevent or troubleshoot out of memory issues in an Amazon SageMaker endpoint?
AWS OFFICIALUpdated a year ago
Why does CloudWatch show that my SageMaker endpoint CPU or GPU utilization is greater than 100%?
AWS OFFICIALUpdated 2 years ago
How do I troubleshoot issues with my Amazon SageMaker AI Serverless Inference endpoint?
AWS OFFICIALUpdated 10 months ago
Inferentia and Trainium Service Quotas
EXPERT
Burtoft, Jim
published 2 years ago
How do I resolve the Amazon SageMaker AI endpoint error “Unable to locate at least 2 availability zone(s) with the requested instance type that overlap with SageMaker subnets”?
EXPERT
Avinash
published 4 months ago

Sagemaker endpoint scaling issues

Add your answer

Relevant content