Red Hat has expanded its collaboration with Amazon Web Services (AWS) to run generative AI inference with Red Hat AI on AWS AI chips, Red Hat said on 2 December 2025.
Red Hat AI Inference Server, powered by vLLM, will be able to run on AWS Inferentia2 and AWS Trainium3. Red Hat said this will give up to 30-40% better price performance than current comparable GPU-based Amazon EC2 instances.
Red Hat and AWS developed an AWS Neuron operator for Red Hat OpenShift, OpenShift AI and Red Hat OpenShift Service on AWS, giving customers a supported way to run AI workloads on AWS accelerators. The community operator is now available in the OpenShift OperatorHub.
Red Hat also released the amazon.ai Certified Ansible Collection for Ansible Automation Platform to orchestrate AI services on AWS.
The companies are working together on an AWS AI chip plugin for the open-source vLLM project. Red Hat said it is the top commercial contributor to vLLM.