Amazon Web Services has announced the general availability of Amazon EC2 G7 instances, which provide high-performance GPU acceleration for AI inference, graphics, and data analytics workloads. These instances are powered by NVIDIA RTX PRO 4500 Blackwell Server Edition GPUs and custom sixth-generation Intel Xeon Scalable processors, resulting in up to 4.6x AI inference performance and up to 2.1x graphics performance compared to the previous G6 instances. The G7 instances also deliver faster performance for GPU-accelerated analytics on Amazon EMR and Amazon Elastic Kubernetes Service (EKS). Key improvements include faster GPU memory, high-performance networking and storage, and advanced video encoding and decoding engines. The G7 instances come in seven sizes, supporting up to 8 NVIDIA RTX PRO 4500 Blackwell Server Edition GPUs, up to 256 GB of total GPU memory, and up to 700 Gbps of network bandwidth. They also support multiple operating systems, including Amazon Linux, Ubuntu, RHEL, and Windows Server, with comprehensive NVIDIA driver integration. To get started, users can launch G7 instances from the Amazon EC2 console, with multiple purchasing options available, including On-Demand, Savings Plans, and Spot Instances. The G7 instances are currently available in two AWS regions, US East (Ohio) and US West (Oregon), with plans for future regional expansion.

Source: AWS