Add GPU monitoring services and configurations

- Create systemd service templates for llama_exporter, nvidia_exporter, and podman.
- Add Prometheus configuration template for GPU metrics scraping.
- Introduce variables for GPU monitoring role in main.yml.
- Implement tasks for syncing llama models, including user setup and package installation.
- Update podman tasks to ensure proper sudo access and lingering for the podman user.
- Modify inventory to include gpu_monitoring group.
- Add Terraform modules for deploying Vaultwarden, including ingress and service configurations.
- Create Grafana dashboard for real-time GPU monitoring metrics.
- Update secrets and environment files to include Vaultwarden admin token.

ansible/roles/gpu_monitoring/templates/llama_exporter.service.j2

@@ -0,0 +1,35 @@
+[Unit]
+Description=LLM Inference Metrics Exporter (llama.cpp + Ollama)
+After=network-online.target
+Wants=network-online.target
+
+[Service]
+Type=simple
+User={{ llama_exporter_user }}
+Group={{ llama_exporter_user }}
+WorkingDirectory={{ llama_exporter_install_dir }}
+Environment="LLAMA_EXPORTER_PORT={{ llama_exporter_port }}"
+Environment="LLAMA_EXPORTER_BIND=0.0.0.0"
+Environment="LLAMA_EXPORTER_INTERVAL={{ llama_exporter_scrape_interval }}"
+Environment="LLAMA_EXPORTER_TIMEOUT={{ llama_exporter_scrape_timeout }}"
+{% if llama_exporter_targets and llama_exporter_targets != "" %}
+Environment="LLAMA_TARGETS={{ llama_exporter_targets | to_json }}"
+{% endif %}
+Environment="PATH={{ llama_exporter_venv_bin }}:/usr/bin:/bin"
+ExecStart={{ llama_exporter_venv_bin }}/python3 {{ llama_exporter_script_path }}
+Restart=always
+RestartSec=10
+TimeoutStopSec=10
+StandardOutput=journal
+StandardError=journal
+SyslogIdentifier=llama_exporter
+
+# Security hardening
+ProtectSystem=strict
+ProtectHome=true
+ReadWritePaths={{ llama_exporter_install_dir }} /var/log
+NoNewPrivileges=true
+PrivateTmp=true
+
+[Install]
+WantedBy=multi-user.target