Savings Plans Applicability to ML instances

0

ML instances are not specifically listed under the available instance types for Savings Plans: https://aws.amazon.com/savingsplans/pricing/ But there is nothing that explicitly excludes them.

Are ML instances (https://aws.amazon.com/sagemaker/pricing/instance-types/) covered under the compute or instance savings plans?

AWS
已提問 4 年前檢視次數 360 次
2 個答案
0
已接受的答案

Savings plans only apply to EC2 (compute and EC2 instance savings plans) and Fargate instances (compute savings plans). They do not apply to other services, such as SageMaker.

For cost optimization, SageMaker supports spot instances for training jobs, and for the hosting of real-time inference endpoints, look at:

  • right-sizing and auto-scaling the endpoint
  • Using elastic inference or inf1 instances (support for inf1 in SageMaker is on the roadmap)
  • Compiling models with Neo to optimize model performance (for rightsizing)
  • Using inference pipelines instead of multiple model endpoints
  • Hosting in multi-model endpoints
  • Hosting in self-managed compute, such as EC2 with RI, Lambda, or Fargate/spot.

Elastic inference, Neo, inference pipelines and multi-model endpoints work well in some, but not all use-cases, depending on use case, model framework, complexity, size, etc. so it will require some investigation and experimentation to figure out of they’re right for you, but they can help reduce inference cost significantly.

已回答 4 年前
0

Since the accepted answer was posted 2 years ago, we've actually launched Savings Plans for SageMaker already, so for more information check out this page: https://aws.amazon.com/savingsplans/ml-pricing/

profile pictureAWS
專家
已回答 2 年前

您尚未登入。 登入 去張貼答案。

一個好的回答可以清楚地回答問題並提供建設性的意見回饋,同時有助於提問者的專業成長。

回答問題指南