Skip to content
Skip to documentation content
Browse documentation
In progress Page being written

Helm values

Every value the LLMKube Helm chart accepts. Defaults are tuned for a small cluster; this page documents what to override at scale.

What this page will cover

  • controller.image, controller.resources, controller.replicas: shaping the controller deployment.
  • monitoring.podMonitor / serviceMonitor: opting into Prometheus scraping.
  • metalAgent.evictionEnabled, memoryPressureWarning, memoryPressureCritical: memory-pressure protection knobs.
  • webhooks.enabled and admissionReviews.enabled for clusters that need validating webhooks off.
Read the source on GitHub
LLMKube LLMKube

Kubernetes for Local LLMs. Deploy, manage, and scale AI inference workloads with production-grade orchestration.

© 2026 Defilan Technologies LLC

Community

Built for the Kubernetes and AI communities

LLMKube is not affiliated with or endorsed by the Cloud Native Computing Foundation or the Kubernetes project. Kubernetes® is a registered trademark of The Linux Foundation.