# ------------------------------------------------------------------------------
# FILE: roles/deploy-vllm/defaults/main.yml
# ROLE: deploy-vllm — vLLM OpenAI-compatible serving stack
# DESIGNED FOR REUSE: astro-orbiter (RTX 3090, 24GB) today, Mac Mini M4 later.
# Host-specific values (VRAM budget, model list, ports) belong in host_vars,
# not here. These are the safe, conservative defaults.
# ------------------------------------------------------------------------------

# --- Python / venv -----------------------------------------------------------
vllm_venv_owner: jarvis
vllm_venv_path: "/home/{{ vllm_venv_owner }}/vllm-serve-env"
vllm_python_min_version: "3.10"
vllm_version_spec: "vllm>=0.5.0"

# --- Model cache ---------------------------------------------------------
vllm_cache_dir: "/home/{{ vllm_venv_owner }}/.vllm-cache"
vllm_hf_hub_cache: "{{ vllm_cache_dir }}/huggingface"

# --- Serving ---------------------------------------------------------------
vllm_serve_host: "0.0.0.0"
vllm_serve_port: 8000
vllm_gpu_memory_utilization: 0.95
vllm_max_model_len: 8192
vllm_dtype: "auto"

# --- Models --------------------------------------------------------------
# Each entry: id (served --model / OpenAI "model" field), hf_repo, role
# (primary/aux/embedding), quantization, and per-model overrides.
# Only models with enabled: true are staged + wired into the systemd unit's
# --model roster consideration. vLLM 0.5.x serves ONE model per process, so
# multi-model = multiple systemd instances (see vllm_instances below) or a
# router in front (out of scope for this role — matches the astro-orbiter
# phased plan: Qwen2.5-32B today, add Qwen3-8B + embedding later).
vllm_models:
  - id: "Qwen2.5-32B-Instruct-AWQ"
    hf_repo: "Qwen/Qwen2.5-32B-Instruct-AWQ"
    role: primary
    quantization: awq
    port: 8000
    max_model_len: "{{ vllm_max_model_len }}"
    gpu_memory_utilization: "{{ vllm_gpu_memory_utilization }}"
    enabled: true
  - id: "Qwen3-8B-AWQ"
    hf_repo: "Qwen/Qwen3-8B-AWQ"
    role: aux
    quantization: awq
    port: 8010
    max_model_len: 32768
    gpu_memory_utilization: 0.15
    enabled: false
  - id: "nomic-embed-text-v1.5"
    hf_repo: "nomic-ai/nomic-embed-text-v1.5"
    role: embedding
    quantization: none
    port: 8020
    max_model_len: 2048
    gpu_memory_utilization: 0.05
    enabled: false

# --- systemd ---------------------------------------------------------------
vllm_service_name: vllm
vllm_service_state: stopped   # deliberate: role stages everything but does NOT
                              # flip production traffic. Cutover is a separate,
                              # explicitly-approved step (see README.md).
vllm_service_enabled: false   # deliberate: do NOT enable for boot by default.
                              # llama-swap is live production on this GPU —
                              # enabling vllm.service means a host reboot would
                              # auto-start it and immediately VRAM-collide with
                              # llama-swap (confirmed failure mode during Phase 5
                              # validation, t_ca1af9fb 2026-08-31). Flip to true
                              # only as part of the deliberate cutover step,
                              # together with tearing down llama-swap.
vllm_restart_policy: always

# --- API key -----------------------------------------------------------
# Source of truth: 1Password op://mk-labs/vllm/api-key (Nick Fury manages).
# This role does NOT generate a key by default — it expects one to already
# exist in 1Password and reads it via `op read` at deploy time (delegate_to
# localhost, where the op CLI is authenticated). Set vllm_generate_api_key
# to true only for first-ever bootstrap when no 1Password item exists yet.
vllm_generate_api_key: false
vllm_api_key_op_ref: "op://mk-labs/vllm/api-key"
vllm_api_key_env_file: "/etc/vllm/api-key.env"

# --- Verification ------------------------------------------------------
vllm_health_check_retries: 30
vllm_health_check_delay: 10