Red Hat has announced Red Hat AI Factory with Nvidia, a new co-engineered platform that combines Red Hat AI Enterprise and Nvidia AI Enterprise into a single stack for building and scaling AI applications. It’s aimed at organizations moving from pilot projects to full production systems that require tighter control over infrastructure and costs.
The platform brings together Red Hat’s enterprise Linux and AI tooling with Nvidia’s accelerated computing software and runs on systems from Cisco, Dell Technologies, Lenovo, and Supermicro.
Enterprise AI spending is forecast to exceed $1 trillion by 2029, driven in part by agentic AI applications that rely on constant inference. That has increased pressure on infrastructure, especially GPU capacity and model serving efficiency.
The new platform will address those demands across on premises, cloud, and edge environments. It supports high performance inference, model tuning, customization, and agent deployment, while maintaining centralized management.
Red Hat AI Factory with Nvidia stack
The stack includes pre-configured models such as IBM Granite, Nvidia Nemotron, and Nvidia Cosmos open models, delivered as Nvidia NIM microservices. Organizations can also refine models against internal data using Nvidia NeMo, reducing tuning time and cost.
For inference, the platform integrates vLLM, Nvidia TensorRT-LLM, and Nvidia Dynamo. It also includes built in observability tools to track performance and service levels, helping IT teams align model workloads with available GPU resources.
GPU orchestration is handled through pooled infrastructure with on demand allocation. Automatic checkpointing protects long running jobs and reduces the risk of data loss during interruptions.
Security is anchored in Red Hat Enterprise Linux, with compliance controls and isolation built in from the start. Nvidia DOCA microservices boost that layer with runtime protections intended to support zero trust architectures across hybrid deployments.
Chris Wright, CTO and SVP, Global Engineering, Red Hat, said: “The shift from AI experimentation to industrial-scale, enterprise-wide production requires a fundamental change in how we manage the AI computing stack. We’re accelerating the path to deploy AI and move quickly to production using Red Hat AI Factory with Nvidia. With a stable, high-performance foundation driven by our proven hybrid cloud offerings, we’re enabling our customers to own their AI strategy and scale with the same rigor they apply to their core IT platforms.”
Justin Boitano, VP, Enterprise AI Platforms, Nvidia, said: “Enterprises are building AI factories that turn data into intelligence at scale during inference, requiring production-grade infrastructure and software that span the hybrid cloud. Red Hat AI Factory with Nvidia provides the software foundation that helps organizations keep pace with rapid infrastructure innovation while reliably building and deploying the next generation of agentic AI applications.”
Hardware partners including Cisco, Dell Technologies, Lenovo, and Supermicro have confirmed support for the platform across their AI focused systems. Distribution and integration partners such as TD SYNNEX and WWT have also said they will offer the stack to customers.
Red Hat AI Factory with Nvidia is available now.
What do you think about Red Hat AI Factory with Nvidia? Let us know in the comments.
