eblume/blumeops
1
1
Fork 0
Code Issues Pull requests Projects Releases 65 Packages Wiki Activity Actions

Deploy Ollama LLM server on ringtail #277

Merged
eblume merged 5 commits from feature/ollama-ringtail into main 2026-03-02 20:39:52 -08:00
Conversation 1 Commits 5 Files changed 15 +292
eblume commented 2026-03-02 20:02:14 -08:00
Owner
Copy link

Summary

  • Deploy Ollama as a new ArgoCD-managed service on ringtail's k3s cluster with GPU acceleration
  • Declarative model management via models.txt + sidecar sync script (mirrors kiwix torrent pattern)
  • Initial models: qwen2.5:14b, deepseek-r1:14b, phi4:14b, gemma3:12b
  • hostPath PV on /mnt/storage1/ollama for fast local model storage (200Gi)
  • Tailscale ingress at ollama.ops.eblu.me for API access from tailnet
  • Enable GPU time-slicing (replicas: 2) on nvidia-device-plugin so Frigate and Ollama share the RTX 4080

Deployment and Testing

  • Deploy nvidia-device-plugin changes first: argocd app sync nvidia-device-plugin
  • Verify GPU time-slicing: kubectl describe node ringtail --context=k3s-ringtail shows nvidia.com/gpu: 2
  • Sync apps app with --revision feature/ollama-ringtail
  • Set ollama app to branch: argocd app set ollama --revision feature/ollama-ringtail && argocd app sync ollama
  • Verify model-sync sidecar pulls models: kubectl logs -n ollama deploy/ollama -c model-sync --context=k3s-ringtail
  • Test API: curl https://ollama.ops.eblu.me/api/tags
  • Test inference: curl https://ollama.ops.eblu.me/api/generate -d '{"model":"qwen2.5:14b","prompt":"Hello"}'
  • Verify Frigate still works after GPU sharing change
  • After merge: argocd app set ollama --revision main && argocd app sync ollama
## Summary - Deploy Ollama as a new ArgoCD-managed service on ringtail's k3s cluster with GPU acceleration - Declarative model management via `models.txt` + sidecar sync script (mirrors kiwix torrent pattern) - Initial models: `qwen2.5:14b`, `deepseek-r1:14b`, `phi4:14b`, `gemma3:12b` - hostPath PV on `/mnt/storage1/ollama` for fast local model storage (200Gi) - Tailscale ingress at `ollama.ops.eblu.me` for API access from tailnet - Enable GPU time-slicing (`replicas: 2`) on nvidia-device-plugin so Frigate and Ollama share the RTX 4080 ## Deployment and Testing - [ ] Deploy nvidia-device-plugin changes first: `argocd app sync nvidia-device-plugin` - [ ] Verify GPU time-slicing: `kubectl describe node ringtail --context=k3s-ringtail` shows `nvidia.com/gpu: 2` - [ ] Sync `apps` app with `--revision feature/ollama-ringtail` - [ ] Set ollama app to branch: `argocd app set ollama --revision feature/ollama-ringtail && argocd app sync ollama` - [ ] Verify model-sync sidecar pulls models: `kubectl logs -n ollama deploy/ollama -c model-sync --context=k3s-ringtail` - [ ] Test API: `curl https://ollama.ops.eblu.me/api/tags` - [ ] Test inference: `curl https://ollama.ops.eblu.me/api/generate -d '{"model":"qwen2.5:14b","prompt":"Hello"}'` - [ ] Verify Frigate still works after GPU sharing change - [ ] After merge: `argocd app set ollama --revision main && argocd app sync ollama`
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>
eblume reviewed 2026-03-02 20:04:54 -08:00
argocd/manifests/ollama/deployment.yaml Outdated
@ -0,0 +81,4 @@
- name: sync-script
configMap:
name: ollama-sync-script
defaultMode: 493
eblume commented 2026-03-02 20:03:36 -08:00
Author
Owner
Copy link

this... can't be right. there must be a way to use octal or u=,g=,o= or something. Try a string?

this... can't be right. there must be a way to use octal or u=,g=,o= or something. Try a string?
eblume marked this conversation as resolved 
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The ollama/ollama container image doesn't include curl. Use `ollama list`
and `ollama pull` commands directly, which are always available.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Proxies to the Tailscale ingress at ollama.tail8d86e.ts.net.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
eblume merged commit 31d925814f into main 2026-03-02 20:39:52 -08:00
Sign in to join this conversation.
Reviewers
No reviewers
Labels
Clear labels
No items
No labels
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
eblume/blumeops!277
No description provided.