NVIDIA and AWS have launched EC2 G7 instances powered by NVIDIA RTX PRO 4500 GPUs, enhancing AI production capabilities. These instances offer substantial performance improvements, enabling enterprises to deploy AI and data analytics workloads at scale with lower operational complexity.
NVIDIA and Amazon Web Services (AWS) have partnered to introduce EC2 G7 instances, incorporating NVIDIA RTX PRO 4500 Blackwell Server Edition GPUs. This collaboration aims to enhance the production of AI systems, focusing on low-latency inference and efficient GPU performance.
The new G7 instances deliver up to 4.6 times the AI inference performance and up to 2.1 times the graphics performance compared to the previous G6 instances. Additionally, they significantly accelerate GPU-optimized data analytics on AWS, catering to various enterprise workloads.
EC2 G7 instances support configurations with one to eight GPUs and provide 256GB of total GPU memory. The infrastructure also boasts 700 Gbps of EFA-enabled networking and up to 7.6TB of NVMe SSD storage, allowing customers to customize their resources for specific workloads without over-provisioning.
The versatile design of G7 instances suits various applications, supporting not just AI inference but also graphics-intensive tasks across media, entertainment, simulation, and analytics. This flexibility aims to provide enterprises with the necessary tools for modern computation requirements.
G7 instances can be accessed via AWS Deep Learning AMIs, Deep Learning Containers, and services like Amazon EMR and Amazon EKS, making them readily available for organizations aiming to enhance their AI capabilities.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
NVIDIA and AWS have launched EC2 G7 instances powered by NVIDIA RTX PRO 4500 GPUs, enhancing AI production capabilities. These instances offer substantial performance improvements, enabling enterprises to deploy AI and data analytics workloads at scale with lower operational complexity.