alexandre.pires
350650ecc2
- 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.
18 lines
443 B
Django/Jinja
18 lines
443 B
Django/Jinja
[Unit]
|
|
Description=Podman service for {{ item.name }}
|
|
After=local-fs.target network-online.target
|
|
|
|
[Service]
|
|
Type=oneshot
|
|
User={{ prometheus_user }}
|
|
Group={{ prometheus_group }}
|
|
RemainAfterExit=true
|
|
ExecStart={{ podman_binary | default('/usr/bin/podman') }} start {{ item.name }}
|
|
ExecStop={{ podman_binary | default('/usr/bin/podman') }} stop {{ item.name }}
|
|
|
|
StandardOutput=journal
|
|
StandardError=journal
|
|
|
|
[Install]
|
|
WantedBy=multi-user.target
|