llm-server/monitoring/ neu: amdgpu-textfile-collector.py (sysfs-only, atomar, APU-tauglich), Rollen gnmon_collector (node_exporter v1.12.1, SHA256SUMS-verifiziert, 10s-Timer) und gnmon_victoria_metrics (rootless Quadlet, v1.154.1 digest-gepinnt, Scrape 10s, Retention 60d), Workstation- Inventory. Verifikation: PromQL liefert gn_gpu_edge_temp_celsius von der Laptop-APU; Idempotenz changed=0. GNMON-001 v2.0 in die Plattform-Struktur übernommen, GNMON-000-Stand inkl. Alerting-Planlücke aktualisiert. Generated by Mistral Vibe. Co-Authored-By: Mistral Vibe <vibe@mistral.ai>
LLM server ghostnet-ki
This host root contains the executable infrastructure for the physical server at
10.0.0.90, split into one main directory per task area:
| Directory | Purpose |
|---|---|
host/ |
shared server baseline: Ansible control project, host roles and inventories |
llm/ |
LLM serving stack (created with the internal AI vertical slice) |
encoding/ |
CPU-based video encoding workload and its Ansible control project |
monitoring/ |
host-wide monitoring: metrics collector and dashboard |
Reusable roles that are also consumed by other host projects live under
../shared/ansible/.
The versioned architecture and operating documentation remains under
../docs/platform/llm-server/ and
mirrors the same task areas (host/, ai/, encoding/).