How to Deploy AI Models with Hugging Face – Hands-On Course
I recently spent some time working through a comprehensive tutorial on the Hugging Face ecosystem, and it got me thinking about how far we’ve come in the way we build and ship AI systems. Not just models—but complete, end-to-end pipelines that resemble something closer to an operating system than a loose collection of tools. That […]
Read More
3 things to know about Red Hat AI 3
- Frank
- October 14, 2025
- Agentic AI
- AI
- AI control
- AI costs
- ai governance
- AI innovation
- AI paradox
- AI platform
- AI scalability
- artificial intelligence
- cost management in AI
- Efficient model inferencing
- Enterprise AI
- GenAI
- Generative AI
- GPU as a service
- Hybrid Cloud
- Hybrid Cloud AI
- IT operations
- large language models
- LLM
- Machine Learning
- MLOps
- Model as a service
- model inferencing
- open source AI
- OpenShift AI
- operational efficiency in AI
- Red Hat
- red hat ai
- Red Hat AI 3
- Red Hat AI3
- scaling AI
- Sherard Griffin
Imagine you’re driving an old pickup truck, reliable but a bit worn, down the scenic route of innovation. Up ahead, the road splits—one path winds along the safe, familiar flatlands of traditional IT, and the other, a challenging mountainous trail marked “Artificial Intelligence.” You want to take that adventurous AI path, don’t you? But looking […]
Read More
The economics of optimized AI models | Red Hat Explains
- Frank
- August 18, 2025
- AI
- AI cost optimization
- AI deployment
- AI efficiency
- AI innovation
- AIOps
- data distillation
- GPU
- InstructLab
- Knowledge Distillation
- large language models
- LLM Compressor
- LLM Economics
- MLOps
- Model Compression
- Pruning
- quantization
- RAG
- Red Hat
- red hat ai
- Retrieval-Augmented Generation
- Speculative Decoding
- technology costs
- vLLM
Imagine you’ve just bought a sports car. It’s sleek, powerful, and cutting-edge. However, there’s a catch—the engine requires an astronomical amount of fuel, which not only costs a fortune but also demands rare fuel types that are hard to come by. This dilemma is analogous to the challenge companies face with large language models (LLMs) […]
Read More
How to scale AI with MLOps
Have you ever packed a backpack for a long, challenging hike up a mountain? If you have, you know that it’s not just about stuffing in your gear—every item is chosen with care, considering both its necessity and utility. This is not unlike the other intricate world of MLOps, or Machine Learning Operations, which beautifully […]
Read More
How to Run AI Model Inference with Red Hat AI
- Frank
- May 28, 2025
- AI Accuracy
- AI Budget
- AI Cost Reduction
- AI deployment
- AI Infrastructure
- AI model inference
- AI Performance
- Batching AI
- Caching AI
- Cedric Clyburn
- Distillation AI
- Enterprise AI
- GPU Optimization
- Inference Engine
- Llama models
- LLM Optimization
- Machine Learning Operations
- MLOps
- Model Serving
- open source AI
- Pruning AI
- quantization
- Red Hat
- red hat ai
- Red Hat OpenShift AI
- Tokens per second
- vLLM
For many organizations, the conversation around artificial intelligence (AI) often revolves around training models. However, a less-discussed, yet critical aspect of AI implementation is model inference. This is the stage where your AI model is put to work, making predictions based on the data it has been trained on. Interestingly, it is this inference stage […]
Read More
The Future of Farming: AI in the Fields
- Frank
- October 15, 2024
- AI
- AI farming
- AI on Kubernetes
- Ai on OpenShift
- AI/ML
- artificial intelligence
- Data Science
- DevOps
- foundation models
- huggingface
- llms
- Machine Learning
- ML
- ML on Kubernetes
- ML on OpenShift
- MLOps
- OpenShift
- OpenShift AI
- OpenShift Data Science
- RAG
- Red Hat
- retrieval augmented generation
In agriculture, a revolution is quietly unfolding, one that marries the ancient art of farming with the cutting-edge advancements of artificial intelligence (AI). This fusion promises to transform the way we cultivate our crops, making farming more efficient, sustainable, and, surprisingly, a bit more digital. At the heart of this transformation is a project that […]
Read More
AI 101: What’s the difference between DevOps and MLOps?
Prasanth Anbalagan (Senior Principal Technical Marketing Manager for AI) will share the differences and similarities between DevOps and MLOps.
Read More
How to Navigate MLOps with Third-Party Foundation Models
In fast-moving ecosystem of artificial intelligence (AI) and machine learning (ML), the integration of third-party foundation models into the development pipeline has emerged as a pivotal strategy for accelerating innovation and enhancing model performance. However, effectively incorporating these advanced models into the Machine Learning Operations (MLOps) workflow requires a nuanced understanding of both the technical […]
Read More
Unlocking the Potential of AI: The Role of Consistent Platforms
- Frank
- February 22, 2024
- AI
- AI on Kubernetes
- Ai on OpenShift
- AI/ML
- artificial intelligence
- Data Science
- data science pipelines
- DevOps
- foundation models
- Generative AI
- Jupyter
- Kubeflow
- Machine Learning
- ML
- ML on Kubernetes
- ML on OpenShift
- MLOps
- model pipelines
- Model Serving
- ODH
- Open Data Hub
- OpenShift
- OpenShift AI
- Red Hat
AI isn’t going away. OpenShift AI helps customers solve some of their challenges by operationalizing both traditional and generative AI projects. Why should customers think of Red Hat for AI? Steven Huels, GM for Red Hat’s AI Business Unit, describes how OpenShift AI provides a consistent and flexible AI platform for an ever-changing ecosystem as […]
Read More
LLMOps Demystified: A Deep Dive into Large Language Model Operations
Machine learning operations (MLOps) is an important process to make sure Machine Learning applications remain operational, but before you apply the same process to your large language models (LLM), Martin explains why and how LLMs need to be treated differently and the process known as LLMOps
Read More