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.
24 lines
850 B
YAML
24 lines
850 B
YAML
---
|
|
# Internal role variables (non-overridable)
|
|
|
|
# Container names
|
|
gpu_monitoring_prometheus_container_name: "prometheus"
|
|
|
|
# Derived paths
|
|
nvidia_exporter_script_path: "{{ nvidia_exporter_install_dir }}/nvidia_gpu_exporter.py"
|
|
nvidia_exporter_venv_bin: "{{ nvidia_exporter_venv_path }}/bin"
|
|
nvidia_exporter_service_name: "nvidia_exporter"
|
|
|
|
amd_exporter_script_path: "{{ amd_exporter_install_dir }}/amd_gpu_exporter.py"
|
|
amd_exporter_venv_bin: "{{ amd_exporter_venv_path }}/bin"
|
|
amd_exporter_service_name: "amdgpu_exporter"
|
|
|
|
llama_exporter_script_path: "{{ llama_exporter_install_dir }}/llama_exporter.py"
|
|
llama_exporter_venv_bin: "{{ llama_exporter_venv_path }}/bin"
|
|
llama_exporter_service_name: "llama_exporter"
|
|
|
|
# Default llama.cpp targets if none provided
|
|
llama_exporter_targets_default:
|
|
- name: "llama-cpp-8012"
|
|
url: "http://localhost:8012"
|