---
# ------------------------------------------------------------------------------
# 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