posts tagged #Platform-Engineering

~/posts/kubernetes-gang-scheduling-workload-api 17 min · 3485 words

// KEP-4671 landed gang scheduling in Kubernetes 1.37 beta, behind a feature gate that is off by default. A four-node Kind cluster with six fake DRA GPUs shows the partial-placement deadlock, the single field that fixes it, and the two limits nobody documents: the Job field is pruned silently without a second alpha gate, and workload-aware preemption cannot reclaim DRA devices.

~/posts/modelplane-beyond-placement-routing-dynamo-gotchas 22 min · 4548 words

// Part two of the Modelplane fleet inference series, covering the layer above the scheduler. ModelService is a routing policy rather than a load balancer, spec.stack Dynamo swaps the whole gang-scheduling machinery, and four documented gotchas will cost you an afternoon each.

~/posts/modelplane-fleet-inference 29 min · 5971 words

// A hands-on tour of Modelplane, the Crossplane-based control plane for AI inference across a fleet of GPU clusters. Two regions on Kind with fake DRA GPUs, the platform/developer contract written in DRA's own vocabulary, fleet-level drain, and the release trap that costs you two APIs.

~/posts/choragos-multi-agent-orchestrator 26 min · 5350 words

// Choragos runs a team of AI coding agents with a real division of labour: an orchestrator that plans and delegates, workers with their own context, model and credentials, and a delegate/work-done protocol carrying work between them. A walkthrough of v0.11.2 with config recipes for real teams.

~/posts/introducing-sphragis-eu-ai-act-compliance-gateway 17 min · 3410 words

// Sphragis is a self-hosted Go gateway that strips PII out of every LLM request and response before it leaves your network and writes a tamper-evident, hash-chained audit log. A walkthrough of the v0.3.0 release: local redaction, reversible tokenization, multi-provider routing, and OpenTimestamps anchoring.

~/posts/oauth2-proxy 21 min · 4283 words

// MCP servers like DBHub expose databases, filesystems, and code execution over HTTP with zero authentication. Learn how to deploy OAuth2-Proxy on Kubernetes to add SSO, group-based access control, and session management to any MCP server without changing a single line of code.

~/posts/pdb-management-operator 13 min · 2756 words

// Learn how to automate Pod Disruption Budget management in Kubernetes using the PDB Management Operator. This guide explores the operator's architecture, dual configuration model, enforcement modes, and demonstrates how to use it for enterprise-grade availability management in ODA Canvas environments.