Architecting Observable & Resilient Cloud Infrastructure with GitOps→
Sep 10, 2026A practical deep-dive into establishing declarative Kubernetes clusters with ArgoCD, Terraform IaC, and zero-drift GitOps pipelines.
#Kubernetes#Terraform
Local LLM Setup Baits: Common Pitfalls, Fake Benchmark Claims, and Reality Checks→
Jun 25, 2026Exposing clickbait local LLM claims: Why extreme 2-bit quantization degrades coherence, context window VRAM spikes, and real hardware guidelines.
Agentic Monitoring in Production: Replacing Static Dashboards with Autonomous Diagnostic Agents→
Jun 04, 2026Moving beyond static Grafana dashboards: How autonomous LLM agents tail logs, analyze stack traces, and remediate production outages.
Terraform in Production: A No-Nonsense Guide to GitOps, Remote State, and CI/CD→
May 28, 2026A production-aware guide on managing Terraform at scale: locking remote state, building secure OIDC pipelines with GitHub Actions, and enforcing strict GitOps.
The Rise of AMD AI Halo Chips: APUs, ROCm, and Unified Memory Workloads→
May 12, 2026Exploring AMD Strix Halo APUs, high-bandwidth unified memory architecture, and local 70B LLM inference using ROCm.
Cloud GPU Infrastructure: Navigating AWS H100s, RunPod, and Serverless GPUs→
Apr 22, 2026An practical cost and performance comparison of AWS EC2, RunPod, and Modal serverless GPUs for AI training and inference workloads.
Running Open-Weights LLMs on Budget GPUs: Benchmarking RX 6500 XT, GTX 1660, Arc A750, and RX 6600→
Apr 05, 2026A practical comparative benchmark of budget consumer GPUs (RX 6500 XT, GTX 1660 Super, Arc A750, RTX 3050, RX 6600) running quantised LLMs (Llama-3, Qwen-2.5).
MLOps in Production: Building Automated Pipeline Infrastructure with Kubeflow & MLflow→
Mar 18, 2026Architecting end-to-end MLOps automation with Kubeflow pipelines, MLflow experiment tracking, and automated drift detection.
Optimizing LLM Inference: Quantization, Speculative Decoding, and vLLM→
Feb 28, 2026A practical handbook for optimizing open-source LLM inference using PagedAttention, FP8 quantization, and speculative decoding.
Building Production-Grade RAG Systems: From Vector Indexing to Hybrid Search→
Feb 14, 2026A practical guide to building reliable RAG architectures using hybrid dense-sparse search, metadata filtering, and cross-encoder reranking.
What the heck is Ansible anyways?→
Jan 19, 2026A beginner-friendly introduction to Ansible automation.
Welcome to YahyaOnCloud→
Jan 19, 2026The official launch post for YahyaOnCloud blog platform.
Starting with Go Programming→
Apr 11, 2024Deep dive into Golang basics and why it is the language of the cloud.