State of Model Inference in 2026
A field guide to model inference architecture in 2026, covering execution engines, distributed runtimes, KV state, routing, gateways, Kubernetes, deployment patterns, and production maturity.
AxS's Journal
Systems and Software Engineering notes
A passion for building beautiful, reliable, user-friendly systems.
Field notes from a Staff Engineer building distributed systems, data-intensive services, cloud native, MLOps, SRE, and AI infrastructure systems in production.
01 / Kubernetes02 / MLOps03 / SRE
~/Featured
~/Recent
AI-Native Platform Patterns: From Deployment to Behavioral Outcome
Why AI changes the unit of operation from software deployment to behavioral outcome, with eighteen production patterns for inference, agents, knowledge, and operations.
The Production-Ready Path to KServe with GitOps
Learn how to deploy and manage KServe inference services using ArgoCD and GitOps principles. A complete guide to building a declarative, version-controlled, production-grade AI serving platform on Kubernetes.
The Ultimate Guide to KServe
Discover how KServe provides a standardized, cloud-native interface for deploying, managing, and scaling GenAI LLMs and Machine Learning services on Kubernetes.
AI-Native Observability: Watching the Right Signals in the AI Era
Our monitoring tools are dangerously outdated, leaving us blind to the “AI Grey Areas” where systems appear perfect while failing silently. Are we building a future of invisible failures?
How to Fail at Terraform?
Teams rarely fail Terraform on syntax. They fail on design and discipline: monolith configs, copy-paste sprawl, laptop applies, and no policy or tests.