docs: gestion cluster + script funk-cluster mis à jour

- admin/cluster.md : nouveau guide démarrage/arrêt (funk-start/stop/--k8s)
- admin/README.md : lien vers cluster.md
- admin/systeme.md : services llama-server mis à jour (GPU + 2 CPU)
- ansible/roles/litellm/files/funk-cluster : script versionné
  (talosctl fix, storage-01 shutdown, --k8s optionnel, stop timeout)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
alkatrazz 2026-05-13 02:11:21 +02:00
parent 07b94fe8a8
commit a1826fe339
4 changed files with 543 additions and 2 deletions

View file

@ -35,7 +35,9 @@ sudo systemctl list-units --type=service --state=running
| storage-01 | `hermes-agent` | Agent IA (gateway + cron) |
| gpu-01 | `chronyd` | NTP |
| gpu-01 | `sshd` | SSH |
| gpu-01 | `llama-server` | Inférence LLM — Qwen2.5-7B via ROCm 7.x |
| gpu-01 | `llama-server` | Inférence GPU — Qwen3-8B via ROCm 7.x (port 1234) |
| gpu-01 | `llama-server-system` | Inférence CPU — Qwen3-1.7B (port 1236, 14 threads) |
| gpu-01 | `llama-server-monitor` | Inférence CPU — Qwen3-1.7B (port 1237, 14 threads) |
---