8eb88a3116f0f47143ed552676208396b8f5da85
Infrastructure readiness for RunPod inference workloads: - runpod-inference.yaml: ConfigMap with pod creation payloads for RTX 4090, A40 (single+dual), and custom templates - runpod-lb-configmap.yaml: nginx least-conn load balancer for inference endpoint distribution (Deployment + ClusterIP Service) - runpod-provision.sh: bash provisioner script — reads RUNPOD_API_KEY/HF_TOKEN, creates pods via GraphQL, polls until RUNNING, outputs endpoint URLs. Does NOT spin up any pods (dry-run flag available).
infrastructure
Personal infrastructure-as-code for Legion (k3s home server) and supporting tooling.
| Doc | What it covers |
|---|---|
AGENTS.md |
Full reference: machines, secrets, services, domains, namespaces, common operations |
servers/legion/README.md |
What's running on Legion and how deployment works |
servers/legion/RUNBOOK.md |
Disaster recovery — full restore from scratch |
Quick start
cd servers/legion
direnv allow
terraform plan
terraform apply
Push to servers/ to deploy app changes via Argo CD.
Languages
HCL
78.4%
Shell
17.5%
Python
2.6%
Dockerfile
1.5%