-
VKS Cluster Sizing: VM Classes, Node Pools and Control-Plane Topology (VKS Series, Part 5)
Node size in VKS comes from a VM class, not a free-form number. Here is how VM classes, node pools and the one-or-three control plane decision actually shape a cluster.
-
Provisioning VKS Clusters: ClusterClass and the Cluster API Workflow (VKS Series, Part 4)
Provisioning a VKS cluster is a Cluster API workflow, not a wizard. Here is the manifest, the deprecated API to avoid, and how to read the cluster lifecycle honestly.
-
Enabling vSphere Supervisor and the VKS Runtime in VCF 9 (VKS Series, Part 3)
Two gates stand between a workload domain and a running VKS cluster: a healthy Supervisor and a content library. Here are the prerequisites, and the blockers that actually bite.
-
VKS Architecture: Supervisor, Namespaces and Workload Clusters (VKS Series, Part 2)
The Supervisor, vSphere Namespaces and workload clusters look alike and behave nothing alike. Here is how the three layers fit together, and where tenancy actually lives.
-
What vSphere Kubernetes Service Is and Why It Replaced TKG (VKS Series, Part 1)
VKS is Tanzu Kubernetes Grid Service renamed, not a new product. Here is what actually changed under the rename, where VKS sits in VCF 9, and who it is really for.
-
The Economics and Future of Generative AI: An Honest Take (GenAI Series, Part 30)
An honest take to close the series: why GPU utilization is the real cost lever, a blunt verdict on the hype, what is actually coming, and a recap with reading paths.
-
Mixture-of-Experts and Where AI Architecture Is Heading (GenAI Series, Part 29)
Mixture-of-experts models hold enormous capacity but activate only a few experts per token, so they run cheaply. How MoE works, its memory catch, and the trends to watch.
-
What It Takes to Train a Model Across Thousands of GPUs (GenAI Series, Part 28)
Training a frontier model coordinates thousands of GPUs for months. How data, tensor, pipeline and expert parallelism, the memory math, and checkpointing make it possible.
-
On-Prem vs Cloud vs Hybrid for GenAI: An Honest Verdict (GenAI Series, Part 27)
Where should generative AI run? An honest framework weighing data sovereignty, the cost crossover, and control, and why most large organisations end up hybrid.
-
The Network and Storage Behind Large-Scale AI (GenAI Series, Part 26)
At scale, the network between GPUs is often the real bottleneck. How NVLink, InfiniBand and RoCE, collective operations like all-reduce, and high-throughput storage keep GPUs fed.
-
Scaling Inference: The Latency vs Throughput Trade-Off (GenAI Series, Part 25)
Scaling AI inference means choosing a point on the latency-versus-throughput curve. How batching, tensor and pipeline parallelism, and autoscaling on the right signal work.
-
vLLM vs TensorRT-LLM vs SGLang: Which Inference Engine, and When (GenAI Series, Part 24)
The inference engine decides whether a GPU serves five users or fifty. How continuous batching and paged attention work, and when to choose vLLM, TensorRT-LLM, SGLang or NIM.
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.
Recommendations & Endorsements
Pranay has very deep technical knowledge and exceptional capabilities. He has strong ability to well-manage complex situations and deliver the customer expectations with high standards of satisfaction. We worked together in one of most complex migration projects and Pranay delivered flawlessly.
Pranay was my VMware Architect on one of our financial accounts at IBM. He was instrumental in documenting and recommending our reference architecture. As a Chief Architect, you are only as good as your team that supports you. Pranay was top notch.
Pranay is proactive, result oriented, responsible and technically sound. Always ready to put all his energy to get the job done. Exceptional troubleshooting skills in Windows Server, virtualization and VMware — a great asset to any company.
Pranay is one of the most talented and dedicated persons I have ever worked with. His vast knowledge from different domains enables him to discuss and help on almost every topic in IT. Needless to say, he is expert of experts in VMware.
DrJha