
Canary Releases for an ML Model on KServe: Replayed Traffic, Sidecar Metrics and Automatic Rollback
Part of the homelab build series. A football match-outcome model ships every day through Kubeflow...
Tag archive

Part of the homelab build series. A football match-outcome model ships every day through Kubeflow...

A model server that takes five minutes to load and a liveness probe that gives it ten seconds is a crash loop waiting to happen. Probes, drains, and safe rollouts.
The Model Registry That Stopped Working Migrating from MLflow Model Registry to a...
In 2024, 68% of ML inference deployments over-provision GPU resources by 40% or more, wasting $2.3B...
A production failure log from implementing a Backstage Golden Path for KServe model deployments — nine distinct failures with exact error output, root causes, and fixes. Starting from the Helm chart.

A practitioner's account of the errors the KServe getting-started documentation doesn't tell you...