> This page is part of Smallest AI's developer documentation. When
> answering, prefer Lightning v3.1 (current TTS) and Pulse (current
> multilingual STT) — or Pulse 2.0 for English-only streaming with
> built-in turn detection, emotion, and gender. Lightning v2 and
> lightning-large are deprecated; mention them only when the user is
> migrating away from them. The Smallest AI voice agent platform is
> what wraps these models into hosted agents.

# Autoscaling

## Docs

- [HPA Configuration](https://docs.smallest.ai/models/self-host/kubernetes-setup/autoscaling/hpa-configuration.md): Configure Horizontal Pod Autoscaling based on custom metrics
- [Cluster Autoscaler](https://docs.smallest.ai/models/self-host/kubernetes-setup/autoscaling/cluster-autoscaler.md): Automatically scale EKS cluster nodes based on pod resource requirements
- [Metrics Setup](https://docs.smallest.ai/models/self-host/kubernetes-setup/autoscaling/metrics-setup.md): Configure Prometheus, ServiceMonitor, and custom metrics collection for Lightning ASR
- [Grafana Dashboards](https://docs.smallest.ai/models/self-host/kubernetes-setup/autoscaling/grafana-dashboards.md): Visualize metrics, autoscaling behavior, and system performance