---
# ------------------------------------------------------------------------------
# FILE: roles/llm-inference-multimodel/meta/main.yml
# ------------------------------------------------------------------------------
galaxy_info:
  role_name: llm_inference_multimodel
  author: rblundon
  license: MIT
  description: >
    Deploys two independent llama-server instances on astro-orbiter's RTX 3090:
    an aux/classification instance (Phi-4-14B Q4_K_M, port 8000) and a
    tool-calling instance (Mistral-Small-24B-Instruct-2501 Q3_K_M, port 8001).
    Built alongside roles/llm-inference (not a replacement); assumes that
    role's CUDA build/driver work is already done. See
    /home/hermes/astro-orbiter-multi-model-plan.md for the full design.
  min_ansible_version: "2.15"
dependencies: []