chore(gpu-01): retire les serveurs llama CPU system/monitor/dev (inutilisés) (#31)

Trois instances llama-server CPU manuelles (hors Ansible) tournaient sur gpu-01
sans servir : déjà orphelines de LiteLLM (alias absents de config.yaml, d'où le
bruit "Invalid model name"). Suppression complète :

gpu-01 (opérationnel, déjà fait) :
- systemctl disable --now + rm des units llama-server-{system,monitor,dev}
- ports firewall 1235/1236/1237 fermés

Repo :
- monitoring : scrape jobs (values.yaml) + alertes LlamaServer{System,Monitor}Down
  (alerts-ai.yaml) retirés → plus de "target down"/alertes fantômes ; panneaux de
  statut dashboard-infrastructure recyclés (system→llama-embed, monitor supprimé).
- docs admin/ + hermes-skills (souls funk-ai/brain, SKILL agent-delegation) mises à
  jour : inventaire modèles, profils Hermès system/monitor sans backend (à repointer
  sur qwen3-8b), litellm, ops, monitoring.

Les profils Hermès system/monitor existent toujours mais sans backend dédié.
Dashboards Grafana dashboard-ai (panneaux graphiques CPU) laissés tels quels
(cosmétique, séries vides, aucune alerte).

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
ALI YESILKAYA 2026-06-20 13:25:50 +02:00 committed by GitHub
parent ef15ba25e0
commit 470c69881c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
17 changed files with 90 additions and 147 deletions

View file

@ -1413,33 +1413,15 @@ data:
"color": {"mode": "thresholds"},
"thresholds": {"mode": "absolute", "steps": [{"color": "red", "value": null}, {"color": "green", "value": 1}]},
"unit": "none",
"mappings": [{"type": "value", "options": {"1": {"text": "llama-server system", "color": "green", "index": 0}, "0": {"text": "ARRÊTÉ", "color": "red", "index": 1}}}]
"mappings": [{"type": "value", "options": {"1": {"text": "llama-embed nomic", "color": "green", "index": 0}, "0": {"text": "ARRÊTÉ", "color": "red", "index": 1}}}]
},
"overrides": []
},
"gridPos": {"h": 3, "w": 6, "x": 6, "y": 61},
"id": 61,
"options": {"reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}, "textMode": "auto", "colorMode": "background", "graphMode": "none"},
"title": "llama-server CPU system (:1236)",
"targets": [{"datasource": {"type": "prometheus", "uid": "${datasource}"}, "expr": "node_systemd_unit_state{job=\"gpu-01-node\",name=\"llama-server-system.service\",state=\"active\"}", "legendFormat": "", "refId": "A"}],
"type": "stat"
},
{
"datasource": {"type": "prometheus", "uid": "${datasource}"},
"fieldConfig": {
"defaults": {
"color": {"mode": "thresholds"},
"thresholds": {"mode": "absolute", "steps": [{"color": "red", "value": null}, {"color": "green", "value": 1}]},
"unit": "none",
"mappings": [{"type": "value", "options": {"1": {"text": "llama-server monitor", "color": "green", "index": 0}, "0": {"text": "ARRÊTÉ", "color": "red", "index": 1}}}]
},
"overrides": []
},
"gridPos": {"h": 3, "w": 6, "x": 12, "y": 61},
"id": 62,
"options": {"reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}, "textMode": "auto", "colorMode": "background", "graphMode": "none"},
"title": "llama-server CPU monitor (:1237)",
"targets": [{"datasource": {"type": "prometheus", "uid": "${datasource}"}, "expr": "node_systemd_unit_state{job=\"gpu-01-node\",name=\"llama-server-monitor.service\",state=\"active\"}", "legendFormat": "", "refId": "A"}],
"title": "llama-embed nomic (:1238)",
"targets": [{"datasource": {"type": "prometheus", "uid": "${datasource}"}, "expr": "node_systemd_unit_state{job=\"gpu-01-node\",name=\"llama-embed.service\",state=\"active\"}", "legendFormat": "", "refId": "A"}],
"type": "stat"
},
{