You can now attach multiple Amazon Elastic Inference accelerators to a single Amazon EC2 instance. With this capability, you can use a single EC2 instance in an auto-scaling group when you are running inference for multiple models. By attaching multiple accelerators to a single instance, you can avoid deploying multiple auto-scaling groups of CPU or GPU instances for your inference and lower your operating costs.

Amazon AppStream 2.0 is now in scope under AWS’s latest System and Organizational Controls (SOC) audit cycle. This SOC compliance certification applies to all AWS Regions where Amazon AppStream 2.0 is available.  

Amazon Athena is now available in the AWS South America (São Paulo) region.  

This Quick Start deploys an end-to-end .NET serverless continuous integration (CI) and continuous delivery (CD) pipeline on the Amazon Web Services (AWS) Cloud in about 40 minutes.

Amazon CloudFront access logs provide detailed information about every user request that CloudFront receives. Starting today, seven additional data fields will now appear in your CloudFront access logs to improve visibility into the delivery of your content. For example, with the x-edge-detailed-result-type field you can identify the specific type of error and with the sc-range-start/sc-range-end fields you can determine the requested range details. These new fields are appended to the end of each log entry to maintain backwards-compatibility with the previous log file format. The seven new data points include:

Amazon Polly is a service that turns text into lifelike speech. Today, we are excited to announce the general availability of all Neural Text-to-Speech (NTTS) voices in the Asia Pacific (Sydney) region. NTTS voices, which deliver ground-breaking improvements in speech quality through a new machine learning approach, are also available in US East (N. Virginia), US West (Oregon) and Europe (Ireland). Customers in these four regions can now synthesize 13 NTTS voices (8 US English, 3 UK English, 1 US Spanish and 1 Brazilian Portuguese) in the Polly portfolio. In addition, 2 speaking style voices – Newscaster and Conversational , built using NTTS technology are also available in US English (Matthew and Joanna) starting today.

Amazon Simple Queue Service (SQS) now publishes 1-minute metrics to Amazon CloudWatch, providing you more granular monitoring for queue status with continuous visibility into operations of your queues in order to quickly respond to changes in your workloads. Previously, Amazon SQS published metrics to Amazon CloudWatch in 5 minute intervals. 

Starting today, AWS Security Token Service is announcing support for AWS PrivateLink in Asia Pacific (Hong Kong), Asia Pacific (Mumbai), Asia Pacific (Osaka), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Sydney), Canada (Central), EU (Frankfurt), EU (London), EU (Paris), EU (Stockholm), South America (Sao Paolo), and US West (N. California) regions, enabling you to route data between your Amazon Virtual Private Cloud (VPC) and Security Token Service entirely within the AWS network. 

Starting today, Amazon EC2 M5ad and R5ad instances are available in the AWS Asia Pacific (Tokyo) Region. In addition, 8xlarge and 16xlarge sizes of M5ad and R5ad instances are now also available in the Canada (Central) Regions.

Amazon Lex is now a U.S. Health Insurance Portability and Accountability Act of 1996 (HIPAA) eligible service. Customers can now use Amazon Lex to process user input that contains protected health information (PHI).