Hearth documentation
Hearth is a minimal, composable LLM serving control plane for private Kubernetes clusters. It
turns an LLMService and a reusable InferenceRuntime into a cold-start-aware gateway, a model
backend that can scale to zero, optional model caching and prewarming, and KEDA autoscaling
resources.
Start here
- Getting started installs Hearth, deploys a hardware profile, and exercises the complete request path.
- Examples and model configuration covers NVIDIA and Ascend profiles and explains how to change the served model.
- Architecture explains the component boundary, reconciliation output, and scale-to-zero lifecycle.
- CRD reference documents the
LLMServiceandInferenceRuntimeAPI.
Operate and validate
- Observability describes the optional Prometheus and Grafana integration.
- Developing without an accelerator exercises the control plane and scale-to-zero path on Kind.
- Hardware validation explains the evidence required for physical accelerator claims.
- Operational demo reproduces the Hearth and Kthena lifecycle shown in the project video.
Project
Read the roadmap for current limitations and v0.4.0 priorities. Contributions are welcome; the contributing guide explains the development workflow and project boundary.