The AWS Deep Learning Containers are available today with bug fixes to the SageMaker integration with Tensorflow Server and the latest version of SageMaker Debugger. You can launch the new versions of Deep Learning Container on Amazon SageMaker, Amazon Elastic Kubernetes Service (Amazon EKS), self-managed Kubernetes on Amazon EC2, and Amazon Elastic Container Service (Amazon ECS). For a complete list of frameworks and versions supported by the AWS Deep Learning Containers, see release notes . 

Today, we’re reducing the price for Amazon Elastic Kubernetes Service (EKS) by 50% to $0.10 per hour for each Kubernetes cluster that you run.  

You can now use Amazon CloudWatch to see query volume metrics for Amazon Route 53 Resolver endpoints, including the aggregate number of queries that are handled by an outbound Resolver endpoint. This aggregate metric combines query counts from all accounts that are using shared conditional forwarding rules associated with the outbound Resolver endpoint. Additionally, you can view query volume metrics for each IP address that is associated with an inbound or outbound Resolver endpoint. This gives you an even more granular view of how query traffic is flowing amongst the IP addresses that are associated with a given Resolver endpoint. With these metrics, you can see at a glance the activity level for inbound and outbound queries going to and coming from your on-premises networks. 

AWS Key Management Service (KMS) now enables customers to create asymmetric customer master keys (CMKs) and generate data key pairs in all regions where AWS KMS is available, except in the AWS China (Beijing) Region, operated by Sinnet and the AWS China (Ningxia) Region, operated by NWCD.  

Amazon Personalize is now available in Asia Pacific (Seoul) region. Amazon Personalize is a machine learning service which enables you to personalize your website, app, ads, emails, and more, with custom machine learning models which can be created in Amazon Personalize, with no prior machine learning experience.  

You can now easily stop a pipeline execution in CodePipeline. Previously, you had to either (a) disable transitions between stages and wait for a new pipeline execution to supersede the current pipeline execution; or (b) wait for active action executions to time out.  

AWS Control Tower announces the availability of lifecycle event notifications. A lifecycle event marks the completion of a Control Tower action that can change the state of resources such as organizational units (OUs), accounts and guardrails that are created and managed by Control Tower. Lifecycle events are recorded as AWS CloudTrail events and delivered to Amazon EventBridge as events, and the event log states if the Control Tower action completed successfully or not.

EBS direct APIs for Snapshots are now available in ten additional regions: US East (Ohio), US West (N. California), Canada (Central), Europe (London), Europe (Stockholm), Europe (Paris), Asia Pacific (Mumbai), Asia Pacific (Seoul), Asia Pacific (Sydney), and South America (São Paulo).

Today, we are reducing the price of CloudEndure Disaster Recovery by 80% to $0.028 per hour per server, or an estimated $20 per month per server. CloudEndure Disaster Recovery minimizes downtime and data loss by providing fast, reliable recovery of physical, virtual, and cloud-based servers to AWS. 

We’re excited to announce the launch of the new AWS Game Tech Starter Pack. This digital training curriculum covers key features of Amazon GameLift and Amazon Lumberyard, as well as how AWS analytics solutions, such as Amazon Kinesis and Amazon EMR, can lead to insights to solve real-world problems with games. The curriculum features four courses: Amazon GameLift Primer, Amazon Lumberyard Primer, Data Analytics Fundamentals, and Why Analytics for Games. They feature a combined eight hours of digital video content intended for back-end game developers, operation engineers, architects, designers, producers, artists, data scientists, analysts, and business leaders.