Category: AI/ML
-
Fine Tuning Granite With InstructLab Multi Phase Alignment (Red Hat Gen AI Series, Part 10)
Run lab-multiphase training on RHEL AI to tune Granite on your own docs, read the checkpoints MT-Bench actually picks, and avoid the restart prompt that wipes hours of work.
-
InstructLab Taxonomy and Synthetic Data Generation on RHEL AI (Red Hat Gen AI Series, Part 9)
Building an InstructLab knowledge taxonomy and running synthetic data generation on RHEL AI, from qna.yaml seed examples to the training JSONL that Part 10 tunes on.
-
Serving Granite Locally With ilab and vLLM (Red Hat Gen AI Series, Part 8)
Serving Granite on one RHEL AI box with ilab model serve and vLLM, from the first token to a locked down endpoint, including the tensor parallel error nearly everyone hits on day one.
-
Installing RHEL AI From the Bootable Image to First Boot (Red Hat Gen AI Series, Part 7)
RHEL AI ships as a whole bootable operating system, not a package you add to Linux. Here is how to stand up a first box: download the image, size the disks, write a safe Kickstart, log in to the registry and get Granite downloaded before you serve it.
-
Choosing a First Model and Accelerator for Red Hat AI (Red Hat Gen AI Series, Part 6)
Sizing a first Granite model and GPU for Red Hat AI is a memory problem, not a benchmark one. Here is how weights, KV cache and the InstructLab training floor decide what you actually buy or rent.
-
InstructLab and the LAB Method for Taxonomy Driven Alignment (Red Hat Gen AI Series, Part 5)
InstructLab turns a handful of hand written questions into thousands of training examples. Here is how the LAB method and a taxonomy tree tune a Granite model on your own documents.
-
Red Hat AI Hybrid Cloud Deployment, and Where It Actually Runs (Red Hat Gen AI Series, Part 4)
Red Hat AI runs on bare metal, in your private cloud, on public cloud GPU instances and in air gapped sites. Here is how to place a self hosted GenAI project when its data cannot leave the building.
-
RHEL AI vs RHEL vs OpenShift AI, and Where a Project Belongs (Red Hat Gen AI Series, Part 3)
RHEL, RHEL AI and OpenShift AI get confused constantly. One is an operating system, one runs a single model on one server, one runs many across a cluster. Here is how to pick the right one for a project, with the trade offs named.
-
Granite Model Family and Choosing a Size Under Apache 2.0 (Red Hat Gen AI Series, Part 2)
Granite 4.0 comes in four practical sizes under Apache 2.0. Here is how total versus active parameters decide GPU memory, and why H-Tiny, not H-Small, is the right first model for a self hosted support assistant.
-
Red Hat AI Explained, and How RHEL AI, OpenShift AI and the Inference Server Fit (Red Hat Gen AI Series, Part 1)
Red Hat AI is not one product but three: RHEL AI, OpenShift AI and the AI Inference Server. Here is what each does, the open source thesis behind them, and where to start when you have used a hosted model API but never run your own inference.
-
Path to AI Engineer, and What to Learn Next (AI Engineering Series, Part 30)
Thirty parts on, here is the honest version of the AI engineering career path: what the market pays, which routes into the role actually work, what a hiring loop tests, and a twelve month plan to close the gaps this series left open.
-
Choosing and Switching Providers Without a Rewrite (AI Engineering Series, Part 29)
Provider lock in for an LLM application does not live in the API call. I compare six portability strategies with measured latency overhead, show the compatibility endpoint failure that cost us three days, and name the one I would ship.
Architect’s Toolkit
PJ’s Tools
VMware Cloud Foundation
- VCF Documentation
- VCF 9 Planning & Preparation Workbook
- VCF Bill of Materials (BoM)
- VMware Compatibility Guide
- VMware Interoperability Matrix
- VMware Configuration Maximums
- VMware Ports & Protocols
- VMware Hands-on Labs
- RVTools Download
Nutanix
AI & Cloud-Native Platform
- NVIDIA Build (Model Catalog)
- NVIDIA AI Enterprise Reference Architecture
- NVIDIA NIM Performance Benchmarking
- NVIDIA NGC Catalog
- NeMo Microservices Helm Chart
- Helm Charts Repository
- Hugging Face Models
Architecture & Design
About the Author
Dr Pranay Jha
Dr. Pranay Jha is a Cloud and AI Consultant with 18+ years of experience in hybrid cloud, virtualization, and enterprise infrastructure transformation. He specializes in VMware technologies, multi-cloud strategy, and Generative AI solutions. He holds a PhD in Computer Applications with research focused on Cloud and AI, has published multiple research papers, and has been a VMware vExpert since 2016 and a VMUG Community Leader.
You May Have Missed
