fizzlepoof/truenas-stacks
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

homelab: sync post-migration repo and n8n runtime audit
Some checks failed
secret-guardrails / artifact-secret-scan (push) Has been cancelled
Details
secret-guardrails / gitleaks (push) Has been cancelled
Details

Browse Source
This commit is contained in:
Fizzlepoof
2026-05-22 23:04:33 +00:00
parent d62a391cbf
commit bec21292de
28 changed files with 6291 additions and 430 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
docs/servers/ROCINANTE.md
View File

@@ -6,7 +6,7 @@ Heavy AI inference server.
| Component | Details |
|-----------|---------|
| **IP** | 10.5.1.112 |
| **IP** | 10.5.30.112 |
| **GPU** | NVIDIA RTX 4090 (24 GB VRAM) |
| **Role** | Heavy AI inference (Ollama) |
@@ -23,13 +23,13 @@ Ollama runs on port `11434` and hosts the large-model ("heavy") tier.
| `gemma3:27b` | Multimodal / vision |
> **LiteLLM tier:** Rocinante is the **"heavy"** tier in LiteLLM `config.yaml`.
> Heavy-tier requests from OpenWebUI and n8n route to `http://10.5.1.112:11434`.
> Heavy-tier requests from OpenWebUI and n8n route to `http://10.5.30.112:11434`.
## Current operational note
- During Doris validation from N.O.M.A.D. on 2026-05-21, `10.5.1.112` did not answer ping and did not accept connections on `11434` or `8787`.
- During Doris validation from N.O.M.A.D. on 2026-05-21, `10.5.30.112` did not answer ping and did not accept connections on `11434` or `8787`.
- Treat Rocinante-hosted Ollama heavy-tier traffic and CUDA Whisper as currently unreachable from N.O.M.A.D. until host/network reachability is restored.
- Re-validate from N.O.M.A.D. with `curl http://10.5.1.112:11434/api/tags` and `curl http://10.5.1.112:8787/health` after recovery.
- Re-validate from N.O.M.A.D. with `curl http://10.5.30.112:11434/api/tags` and `curl http://10.5.30.112:8787/health` after recovery.
## Notes