Red Hat, the world’s leading provider of open source solutions, today announced Red Hat AI Inference Server, a significant step towards democratizing generative AI (gen AI) across the hybrid cloud. A new offering within Red Hat AI, the enterprise-grade inference server is born from the powerful vLLM community project and enhanced by Red Hat’s integration of Neural Magic technologies, offering greater speed, accelerator-efficiency and cost-effectiveness to help deliver Red Hat’s vision of running any gen AI model on any AI accelerator in any cloud environment. Whether deployed standalone or as an integrated component of Red Hat Enterprise Linux AI (RHEL AI) and Red Hat OpenShift AI, this breakthrough platform empowers organizations to more confidently deploy and scale gen AI in production.
Inference is the critical execution engine of AI, where pre-trained models translate data into real-world impact. It’s the pivotal point of user interaction, demanding swift and accurate responses. As gen AI models explode in complexity and production deployments scale, inference can become a significant bottleneck, devouring hardware resources and threatening to cripple responsiveness and inflate operational costs. Robust inference servers are no longer a luxury but a necessity for unlocking the true potential of AI at scale, navigating underlying complexities with greater ease.
Red Hat directly addresses these challenges with Red Hat AI Inference Server – an open inference solution engineered for high performance and equipped with leading model compression and optimization tools. This innovation empowers organizations to fully tap into the transformative power of gen AI by delivering dramatically more responsive user experiences and unparalleled freedom in their choice of AI accelerators, models, and IT environments.
vLLM: Extending inference innovation
Red Hat AI Inference Server builds on the industry-leading vLLM project, which was started by UC Berkeley in mid-2023. The community project delivers high-throughput gen AI inference, support for large input context, multi-GPU model acceleration, support for continuous batching, and more.
vLLM’s broad support for publicly available models – coupled with its day zero integration of leading frontier models including DeepSeek, Gemma, Llama, Llama Nemotron, Mistral, Phi and others, as well as open, enterprise-grade reasoning models like Llama Nemotron – positions it as a de facto standard for future AI inference innovation. Leading frontier model providers are increasingly embracing vLLM, solidifying its critical role in shaping gen AI’s future.
Introducing Red Hat AI Inference Server
Red Hat AI Inference Server packages the leading innovation of vLLM and forges it into the enterprise-grade capabilities of Red Hat AI Inference Server. Red Hat AI Inference Server is available as a standalone containerized offering or as part of both RHEL AI and Red Hat OpenShift AI.
Across any deployment environment, Red Hat Inference Server provides users with a hardened, supported distribution of vLLM along with:
- Intelligent LLM compression tools for dramatically reducing the size of both foundational and fine-tuned AI models, minimizing compute consumption while preserving and potentially enhancing model accuracy.
- Optimized model repository, hosted in the Red Hat AI organization on Hugging Face, offers instant access to a validated and optimized collection of leading AI models ready for inference deployment, helping to accelerate efficiency by 2-4x without compromising model accuracy.
- Red Hat’s enterprise support and decades of expertise in bringing community projects to production environments.
- Third-party support for even greater deployment flexibility, enabling Red Hat AI Inference Server to be deployed on non-Red Hat Linux and Kubernetes platforms pursuant to Red Hat’s 3rd Party Support Policy.
Red Hat’s vision: Any model, any accelerator, any cloud.
The future of AI must be defined by limitless opportunity, not constrained by infrastructure silos. Red Hat sees a horizon where organizations can deploy any model, on any accelerator, across any cloud, delivering an exceptional, more consistent user experience without exorbitant costs. To unlock the true potential of gen AI investments, enterprises require a universal inference platform – a standard for more seamless, high-performance AI innovation, both today and in the years to come.
Just as Red Hat pioneered the open enterprise by transforming Linux into the bedrock of modern IT, the company is now poised to architect the future of AI inference. vLLM’s potential is that of a linchpin for standardized gen AI inference, and Red Hat is committed to building a thriving ecosystem around not just the vLLM community but also llm-d for distributed inference at scale. The vision is clear: regardless of the AI model, the underlying accelerator or the deployment environment, Red Hat intends to make vLLM the definitive open standard for inference across the new hybrid cloud.
Supporting Quotes
Joe Fernandes, vice president and general manager, AI Business Unit, Red Hat
“Inference is where the real promise of gen AI is delivered, where user interactions are met with fast, accurate responses delivered by a given model, but it must be delivered in an effective and cost-efficient way. Red Hat AI Inference Server is intended to meet the demand for high-performing, responsive inference at scale while keeping resource demands low, providing a common inference layer that supports any model, running on any accelerator in any environment.”
Ramine Roane, corporate vice president, AI Product Management, AMD
“In collaboration with Red Hat, AMD delivers out-of-the-box solutions to drive efficient generative AI in the enterprise. Red Hat AI Inference Server enabled on AMD Instinct™ GPUs equips organizations with enterprise-grade, community-driven AI inference capabilities backed by fully validated hardware accelerators.”
Jeremy Foster, senior vice president and general manager, Cisco
“AI workloads need speed, consistency, and flexibility, which is exactly what the Red Hat AI Inference Server is designed to deliver. This innovation offers Cisco and Red Hat opportunities to continue to collaborate on new ways to make AI deployments more accessible, efficient and scalable—helping organizations prepare for what’s next.”
Bill Pearson, vice president, Data Center & AI Software Solutions and Ecosystem, Intel
“Intel is excited to collaborate with Red Hat to enable Red Hat AI Inference Server on Intel® Gaudi® accelerators. This integration will provide our customers with an optimized solution to streamline and scale AI inference, delivering advanced performance and efficiency for a wide range of enterprise AI applications.”
John Fanelli, vice president, Enterprise Software, NVIDIA
“High-performance inference enables models and AI agents not just to answer, but to reason and adapt in real time. With open, full-stack NVIDIA accelerated computing and Red Hat AI Inference Server, developers can run efficient reasoning at scale across hybrid clouds, and deploy with confidence using Red Hat Inference Server with the new NVIDIA Enterprise AI validated design.”
