From NVIDIA: 2024-12-04 13:30:45

Generative AI is revolutionizing industries, with a growing need for efficient inference solutions. AWS announced an expanded collaboration with NVIDIA at the AWS re:Invent conference. NVIDIA NIM microservices are now available on AWS Marketplace, Amazon Bedrock Marketplace, and Amazon SageMaker JumpStart, simplifying deployment of optimized inference for various AI models.

NVIDIA NIM, part of the NVIDIA AI Enterprise software platform, offers easy-to-use microservices for secure deployment of high-performance AI model inference. Prebuilt containers support a wide range of AI models and can be deployed across AWS services like EC2, EKS, and SageMaker. Developers can access over 100 NIM microservices for common models on the NVIDIA API catalog.

Key NIM microservices now available on AWS include NVIDIA Nemotron-4, Llama 3.1 8B-Instruct, Llama 3.1 70B-Instruct, and Mixtral 8x7B Instruct v0.1. These models enhance performance and generate diverse synthetic data for various domains. SoftServe has developed six generative AI solutions accelerated by NVIDIA NIM and AWS services, available on AWS Marketplace.

Developers can deploy NVIDIA NIM microservices on AWS to achieve high-performance AI with optimized inference containers. Visit the NVIDIA API catalog to explore models and request a developer license or 90-day NVIDIA AI Enterprise trial license for deploying microservices on AWS. NIM microservices are also available on AWS Marketplace, Amazon Bedrock Marketplace, and Amazon SageMaker JumpStart.



Read more at NVIDIA: NVIDIA NIM on AWS Supercharges AI Inference