dda6b91330
- nvidia-driver-595-open (already installed 2026-08-03, idempotent) - Python venv + vLLM 0.26.0 (already installed, idempotent) - Gemma 2 27B model download via HuggingFace hub - systemd vllm-serve.service on port 8000 - Hermes provider integration on carousel-of-progress - vault_hf_token added to group_vars/all/vault - ansible.cfg: vault_password_file set to absolute path - inventory: astro_orbiter group added Run with: env -u ANSIBLE_VAULT_PASSWORD_FILE ansible-playbook -i inventory.yml playbooks/day1_deploy_llm_inference.yml
42 lines
1.3 KiB
YAML
42 lines
1.3 KiB
YAML
---
|
|
# ------------------------------------------------------------------------------
|
|
# FILE: roles/llm-inference/tasks/vllm.yml
|
|
# DESCRIPTION: Phase 3 — Python venv + vLLM install.
|
|
# Idempotent: venv creation and pip install only run if the
|
|
# venv binary or vllm package is absent.
|
|
# Already completed manually on 2026-08-03 — will no-op.
|
|
# ------------------------------------------------------------------------------
|
|
|
|
- name: Create Python venv for vLLM
|
|
ansible.builtin.command:
|
|
cmd: python3 -m venv {{ llm_venv_path }}
|
|
creates: "{{ llm_venv_path }}/bin/python"
|
|
become: true
|
|
become_user: "{{ llm_venv_owner }}"
|
|
|
|
- name: Upgrade pip inside venv
|
|
ansible.builtin.pip:
|
|
name: pip
|
|
state: latest
|
|
virtualenv: "{{ llm_venv_path }}"
|
|
become: true
|
|
become_user: "{{ llm_venv_owner }}"
|
|
|
|
- name: Install vLLM
|
|
ansible.builtin.pip:
|
|
name: vllm
|
|
state: present
|
|
virtualenv: "{{ llm_venv_path }}"
|
|
become: true
|
|
become_user: "{{ llm_venv_owner }}"
|
|
|
|
- name: Verify vLLM is importable
|
|
ansible.builtin.command:
|
|
cmd: "{{ llm_venv_path }}/bin/python -c 'import vllm; print(vllm.__version__)'"
|
|
register: vllm_version
|
|
changed_when: false
|
|
|
|
- name: Print vLLM version
|
|
ansible.builtin.debug:
|
|
msg: "vLLM version: {{ vllm_version.stdout }}"
|