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/tasks/llama_exporter.yml

@@ -0,0 +1,82 @@
+---
+- name: Create llama_exporter group
+  become: true
+  ansible.builtin.group:
+    name: "{{ llama_exporter_user }}"
+    state: present
+    system: true
+
+- name: Create llama_exporter user
+  become: true
+  ansible.builtin.user:
+    name: "{{ llama_exporter_user }}"
+    group: "{{ llama_exporter_user }}"
+    home: "{{ llama_exporter_user_home }}"
+    create_home: true
+    shell: /usr/sbin/nologin
+    system: true
+
+- name: Create llama_exporter install directory
+  become: true
+  ansible.builtin.file:
+    path: "{{ item }}"
+    state: directory
+    owner: "{{ llama_exporter_user }}"
+    group: "{{ llama_exporter_user }}"
+    mode: "0755"
+  loop:
+    - "{{ llama_exporter_install_dir }}"
+    - "{{ llama_exporter_install_dir }}/logs"
+
+- name: Copy llama_exporter script
+  become: true
+  ansible.builtin.copy:
+    src: llama_exporter.py
+    dest: "{{ llama_exporter_script_path }}"
+    owner: "{{ llama_exporter_user }}"
+    group: "{{ llama_exporter_user }}"
+    mode: "0755"
+  notify:
+    - Restart llama_exporter
+
+- name: Create Python virtual environment
+  become: true
+  ansible.builtin.command:
+    cmd: "{{ ansible_facts['python']['executable'] }} -m venv {{ llama_exporter_venv_path }}"
+    creates: "{{ llama_exporter_venv_path }}/bin/activate"
+
+- name: Install Python dependencies in llama_exporter venv
+  become: true
+  ansible.builtin.pip:
+    name:
+      - prometheus-client
+      - requests
+    virtualenv: "{{ llama_exporter_venv_path }}"
+    state: present
+
+- name: Fix ownership of llama_exporter directory
+  become: true
+  ansible.builtin.file:
+    path: "{{ llama_exporter_install_dir }}"
+    owner: "{{ llama_exporter_user }}"
+    group: "{{ llama_exporter_user }}"
+    recurse: true
+
+- name: Generate llama_exporter systemd service
+  become: true
+  ansible.builtin.template:
+    src: llama_exporter.service.j2
+    dest: "/etc/systemd/system/{{ llama_exporter_service_name }}.service"
+    owner: root
+    group: root
+    mode: "0644"
+  notify:
+    - Reload systemd daemon
+    - Restart llama_exporter
+
+- name: Enable llama_exporter service
+  become: true
+  ansible.builtin.systemd:
+    name: "{{ llama_exporter_service_name }}"
+    enabled: true
+    state: started