Kubernetes
7 posts tagged #kubernetes
7 posts on Kubernetes, spread across Production AI Engineering (3), AI Coding Tools & Workflow (2), Local LLM Hardware (1) — most read: “vLLM Self-Hosted LLM Production Checklist: Auth + Quotas” and “How to Show Kubernetes Context in Starship Prompt”.
Cloud and DevOps vLLM Self-Hosted LLM Production Checklist: Auth + Quotas
A production-first checklist for self-hosting an OpenAI-compatible vLLM endpoint: auth, per-tenant quotas, streaming SSE, queueing, and redaction-safe logs.
Developer Tools How to Show Kubernetes Context in Starship Prompt
Build a fast Starship prompt that shows Kubernetes context/namespace safely, profiles slow modules (Git + k8s), and avoids leaking cluster names in demos.
Cloud and DevOps eBPF vs Sidecars: Kubernetes Observability Migration Plan
A pragmatic migration plan for Kubernetes teams moving from Envoy sidecars to node-level eBPF observability, with P99 validation and telemetry cost controls baked in.
Cloud and DevOps Transparent Huge Pages + Postgres: Stop P99 Latency Cliffs
THP isn’t “free performance” for Postgres. Here are the exact Linux settings to avoid p99 latency cliffs, plus a validation loop and Kubernetes guardrails.
Technology Docker Compose vs Kubernetes for AI/ML: When to Use Which
A practical decision guide for AI teams: when Docker Compose is enough for a single GPU box, when Kubernetes is mandatory, and the cleanest migration triggers for serving and training.
Developer Tools Docker vs Podman 2026: Which Runtime Should You Use?
I'd pick Docker for teams that need a mature ecosystem and fast onboarding, and Podman for rootless, daemonless production environments where security and systemd integration matter. Here's the fault line I hit running both in real projects.
Cloud and DevOps eBPF Monitoring vs Sidecars: How Datadog Uses eBPF
Sidecar proxies had a good run, but eBPF is eating the service mesh from the kernel up. Here's how Datadog's bet on kernel-level observability is reshaping cloud-native monitoring.
Keep exploring
Close to this topic, not on this page.