KServe vs Ray Serve vs BentoML: Model Serving on Kubernetes ADR
Compare KServe, Ray Serve and BentoML for model serving on Kubernetes: autoscaling, GPU, LLM support, canaries, operations. Decision record for 2026.
vLLM 0.28 to 0.30 Migration: Model Runner V2 Default, Breaking Changes
Upgrading vLLM 0.28 to 0.30: Model Runner V2 is now default, MRV1 removal targeted for v0.32, new flags, removed env vars and a safe rollout checklist.
Kubernetes 1.37 Gang Scheduling vs Volcano, Kueue and YuniKorn
Kubernetes 1.37 promotes PodGroup and gang scheduling to beta and adds CompositePodGroup. Do you still need Volcano, Kueue or YuniKorn?
TwinOps: The Operational Lifecycle Architecture for Digital Twins (2026)
TwinOps applies DevOps discipline to digital twins: model versioning, continuous state sync, validation gates, drift detection, and closed-loop control across the twin lifecycle.
Feature Store Architecture: Online/Offline Parity and Point-in-Time Correctness
A feature store architecture deep-dive: online/offline parity, point-in-time correct joins, materialization, and the registry - how to stop training/serving skew in production ML.
Edge MLOps Pipelines for Industrial IoT: 2026 Production Architecture
Production-grade edge MLOps pipeline for industrial IoT — training, packaging, OTA delivery, drift detection, and rollback under network constraints.
NVIDIA L4 + VMware for AI Inference (2026 Update)
NVIDIA L4 on VMware vSphere for AI inference, updated for 2026 — vGPU vs passthrough, sizing, L4 vs L40S, and a reference deployment with the cost math.
LLM Evaluation Pipelines: LLM-as-Judge Done Right (2026)
Build an LLM evaluation pipeline that you can trust — golden sets, LLM-as-judge pitfalls, calibration, drift detection, and a reference workflow.