Erich Blume 0d1c2eb81a Deploy Ollama LLM server on ringtail with GPU time-slicing ... Add Ollama as a new ArgoCD-managed service on ringtail's k3s cluster: - Deployment with main ollama container and model-sync sidecar - Declarative model list (qwen2.5:14b, deepseek-r1:14b, phi4:14b, gemma3:12b) - hostPath PV on /mnt/storage1/ollama for fast local model storage - Tailscale ingress at ollama.ops.eblu.me - Enable GPU time-slicing (replicas: 2) on nvidia-device-plugin so Frigate and Ollama can share the RTX 4080 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>		2026-03-02 20:01:45 -08:00
..
feature	Add HA for CV and Docs: zero-downtime deploys (#273)	2026-02-26 07:53:21 -08:00
.gitkeep	Add towncrier changelog system (#86)	2026-02-03 11:48:13 -08:00
feature-ollama-ringtail.feature.md	Deploy Ollama LLM server on ringtail with GPU time-slicing	2026-03-02 20:01:45 -08:00