1300 659 575    hello@polarseven.com
  • Partners
  • About Us
  • Contact
Service Desk   Let's Talk
PolarSeven PolarSeven PolarSeven PolarSeven
  • Services
    • View all Services
      • Advisory & Consulting
      • Cloud Build, Migration & Transformation
      • DevOps & Automation
      • Cloud & Cost Optimisation
      • Security & Compliance
      • Cloud Dev & App Modernisation
      • Data, Analytics & IoT
      • Remote Working
      • Well-Architected Framework Review
      • Managed Cloud
    • Industry Solutions
      • Public Sector
      • Education
    • The PolarSeven Methodology
    • Remote Working

      Powered by AWS

  • Case Studies
  • Blogs
  • AWS Meetups
  • Resources
    • AWS Cost Optimisation eBook
PolarSeven PolarSeven
  • Services
    • View all Services
      • Advisory & Consulting
      • Cloud Build, Migration & Transformation
      • DevOps & Automation
      • Cloud & Cost Optimisation
      • Security & Compliance
      • Cloud Dev & App Modernisation
      • Data, Analytics & IoT
      • Remote Working
      • Well-Architected Framework Review
      • Managed Cloud
    • Industry Solutions
      • Public Sector
      • Education
    • The PolarSeven Methodology
    • Remote Working

      Powered by AWS

  • Case Studies
  • Blogs
  • AWS Meetups
  • Resources
    • AWS Cost Optimisation eBook
  • Saturday, 24 March 2018

Amazon Sagemaker Now Uses Auto-scaling

Amazon SageMaker has allowed users to create, train, and deploy their own machine learning models. SageMaker is designed to make machine learning much simpler and easier to manage. In the past, AWS clients have used it to successfully handle Jupyter notebooks and manage distributed training. They have also deployed models to SageMaker hosting for inferences in order to integrate machine learning with their applications.

Now, AWS has announced an easier means to manage production ML models. Amazon SageMaker will now have Auto Scaling, which will automatically scale the number of instances depending on a designated policy.

Previously, users needed to specify the instance type and number of instances at each endpoint to create the scale need for their inferences. Should the inference volume change, you would need to change the number or type of instance, or both, that support each endpoint to match that shift.

Now, Amazon SageMaker makes this process easier. Instead of needing to monitor the inference volume and changing the endpoints, you only need to create a scaling policy for AWS Auto Scaling to use. This will adjust the number of instances as needed depending on the actual workloads, the data of which can be provided by Amazon Cloudwatch metrics and target values defined in the policy. This lowers the cost of adjusting capacity while keeping steady performance.

Pay-as-you-go pricing still applies for the computer power used with AWS SageMaker, meaning you do not have to pay for unused capacity during non-active periods. More info is available at the Amazon SageMaker documentation.

Auto scaling for AWS SageMaker is now available for US East (N. Virginia & Ohio), EU (Ireland), and US West (Oregon).

If you would like to learn how to apply AWS services to your business, kindly contact us here at PolarSeven.

 

 

 

 

  • Facebook
  • Twitter
  • Tumblr
  • Pinterest
  • Google+
  • LinkedIn
  • E-Mail
Discover More
Read More
  • Wednesday, 23 September 2020

Hire DevOps or Utilise DevOps as a Service?

According to a recent report, the market value of DevOps will grow to US$17 billion by 2026. That means IT... read more →
Read More
  • Thursday, 13 August 2020

Five Essentials for Developing Modern Applications

Modern Applications is what we refer to cloud-native software built with today’s agility, performance and security needs in mind. It... read more →
  • Case studies
  • Services
  • Resources

Article Categories

  • Articles
  • AWS
  • AWS Industry News
  • AWS User Group
  • Cloud Computing
  • Cloud Security and Compliance
  • Containers
  • DevOps Automation
  • Miscellaneous
  • PolarSeven News
  • Remote Work
AWS Sydney User Group

Tags

Amazon AppStream 2.0 Amazon Web Services Amazon WorkSpaces application modernisation applications app modernisation AppStream AppStream 2.0 AWS aws devops AWS Spot Instances CFO Chief financial Officer cloud application security Cloud Migration cloud security Containerisation Containers continuous delivery automation DevOps devops outsourcing devops services ecs eks Fargate iaas kubernetes Landing Zones legacy applications Meetup microservices Microsoft Workloads mobile modern applications paas Polar Bear PolarSeven purpose-built databases remote work remote working saas serverless computing Session Manager User Group

Recent Articles

  • Hire DevOps or Utilise DevOps as a Service? September 23, 2020
  • Five Essentials for Developing Modern Applications August 13, 2020
  • New pricing for AWS Spot Instances July 7, 2020

PolarSeven’s vision is to be a customer centric, Amazon Web Services consultancy, where cloud computing is seen as a key enabler to our customers needs and challenges. “We help our customers achieve amazing things…..”

Links

  • Home
  • PolarSeven Methodology
  • Client Case Studies
  • Articles
  • About Us

Contact

Level 2, 13-15 Wentworth Avenue, Sydney, 2000 Phone: 1300 659 575 E-Mail: hello@polarseven.com
@2015-2021 All Rights Reserved | PolarSeven PTY LTD | Terms & Privacy Policy