AI Inference Server
Serve models with vLLM and model compression to reduce GPU usage and cost per query.
⌘K
Red Hat Partner · Costa Rica and Mexico
Red Hat AI
A trusted foundation to develop and deploy enterprise AI solutions with any model, any agent and any accelerator, across the hybrid cloud.
3
Pillars: inference, data and agents
vLLM
Open source inference engine
Open
Powered by open projects such as vLLM and InstructLab
24/7
Premium support available
What Is It
What is Red Hat AI?
Red Hat AI is Red Hat's enterprise AI platform to bring models and agents into production across hybrid cloud. It rests on three pillars: fast, efficient inference with vLLM, models connected to your own data, and AI agents with governance and control. It includes components such as Red Hat AI Inference, Red Hat Enterprise Linux AI and Red Hat OpenShift AI.
Its open approach lets you choose the model, the accelerator (NVIDIA, AMD or Intel) and the cloud, optimize inference cost and keep your data under your control, in your data center, in public clouds or at the edge.
- Efficient inference with vLLM and optimized models
- Model customization with your own data using InstructLab
- MLOps with pipelines, registry and model monitoring in OpenShift AI
- Deployment in the data center, public cloud and edge with data control
Key Features
Key capabilities
Red Hat Enterprise Linux AI
A RHEL image ready to develop, test and run Granite models with alignment tools such as InstructLab.
Red Hat OpenShift AI
MLOps platform on Kubernetes to train, tune, serve and monitor predictive and generative AI models.
Validated models
Access to third-party models validated and optimized to run on the platform.
Flexible accelerators
Support for accelerators from multiple vendors, without locking into a single architecture.
RAG and AI agents
Foundation to build assistants, RAG workflows and agents connected to your business data.
Implementation
How we take it to production
A proven process from assessment to operations, with a single accountable team.
1
Use case identification
We prioritize AI use cases with clear return: customer service, document analysis, development and operations.
2
Architecture and capacity
We size GPU, networking and storage, and choose the right combination of Red Hat AI.
3
Secure implementation
We deploy the platform with access controls, data isolation and compliance from the start.
4
Operations and optimization
We monitor performance and inference cost, and evolve models and workflows with your team.
Use Cases
Use cases
Internal assistants and RAG
Answers grounded in your documentation and knowledge bases, without your data leaving your control.
Low-cost inference
Reduce cost per query by optimizing model serving with vLLM.
Predictive AI and MLOps
Operate fraud detection, predictive maintenance or demand models with repeatable cycles.
AI at the edge
Bring inference close to the data: branches, plants and remote infrastructure.
Ecosystem
Certified and compatible with your ecosystem
Works with the leading clouds, vendors and enterprise platforms.
NVIDIAAMDIntelIBM GraniteHugging FaceMicrosoft AzureAWSGoogle Cloud
Related Red Hat products
More Red Hat solutions with TUTARI
Coverage
Commercial coverage in Costa Rica and Mexico
We serve companies with local contact, remote or onsite delivery, and the same service standard in both countries.
Costa Rica
We help companies in Costa Rica bring AI use cases into production with Red Hat AI, sizing capacity and keeping data under your control.
Request assessmentMexico
We help companies in Mexico design and deploy AI platforms with Red Hat AI, with security, data governance and support in Spanish and English.
Request assessment
Expert Analysis
TUTARI, your Red Hat partner for enterprise AI in Latin America
TUTARI S.A. — Red Hat Partner
TUTARI S.A. is a Red Hat partner for Costa Rica, Mexico and Latin America. We help organizations bring generative and predictive AI into production with Red Hat AI, focused on security and data control.
We combine AI platforms with managed cybersecurity: workload isolation, access control, 24/7 monitoring and vulnerability management across the whole chain, from the model to the infrastructure.
TUTARI prioritizes use cases, sizes capacity and operates the platform with support in Spanish and English.
FAQ
Frequently asked questions about Red Hat AI
Answers to the most common questions about our services
What does Red Hat AI include?
What does Red Hat AI include?
Red Hat AI brings together inference with vLLM, models connected to your data and agents with governance, built on components such as Red Hat AI Inference, Red Hat Enterprise Linux AI and Red Hat OpenShift AI, from efficient model serving to the full AI life cycle.
Can I use my own models and data?
Can I use my own models and data?
Yes. You can run open source or Red Hat validated models and customize them with your data, keeping them on your infrastructure.
What hardware do I need?
What hardware do I need?
It depends on the models and workload. Red Hat AI supports NVIDIA, AMD and Intel accelerators, and TUTARI helps you size capacity.
How is Red Hat AI acquired?
How is Red Hat AI acquired?
Through a Red Hat subscription, based on the component and environment size. TUTARI advises you on the most suitable scheme.
Take your AI strategy to production with Red Hat AI
Let's assess your use cases and design an efficient, secure AI platform under your control.
