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
25 lines
766 B
YAML
25 lines
766 B
YAML
---
|
|
# ------------------------------------------------------------------------------
|
|
# FILE: roles/llm-inference/defaults/main.yml
|
|
# DESCRIPTION: Overridable defaults for the llm-inference role.
|
|
# Deploy target: astro-orbiter (Dell OptiPlex 7050 SFF, RTX 3090
|
|
# via OCuLink, Ubuntu 24.04.4 LTS).
|
|
# ------------------------------------------------------------------------------
|
|
|
|
# NVIDIA driver
|
|
llm_nvidia_driver_package: nvidia-driver-595-open
|
|
|
|
# Python venv
|
|
llm_venv_path: /home/jarvis/vllm-env
|
|
llm_venv_owner: jarvis
|
|
|
|
# HuggingFace
|
|
llm_hf_cache_dir: /home/jarvis/.cache/huggingface
|
|
llm_hf_model: google/gemma-2-27b-it
|
|
|
|
# vLLM serve
|
|
llm_serve_port: 8000
|
|
llm_serve_host: "0.0.0.0"
|
|
llm_gpu_memory_utilization: "0.90"
|
|
llm_max_model_len: 8192
|