---
# ------------------------------------------------------------------------------
# FILE: roles/llm-inference-multimodel/vars/main.yml
# DESCRIPTION: Role-internal constants (not meant to be overridden per-host).
#              Model URLs/quant filenames live here rather than defaults/ since
#              they're not really "tunable" — they're the specific artifacts
#              named in the approved plan (§1). If Ryan wants a different
#              quant/model, that's a defaults/main.yml override or a plan
#              revision, not a vars/ edit.
# ------------------------------------------------------------------------------

# HuggingFace auth — reuse the same vault token as roles/llm-inference.
# vault_hf_token is defined in group_vars/all/vault.
llm_hf_token: "{{ vault_hf_token }}"

# Expected VRAM subtotals from plan §1 (informational — surfaced in verify.yml
# output so a live nvidia-smi reading can be sanity-checked against the design
# math, not enforced as a hard gate).
llm_aux_expected_vram_gb: 10.0
llm_toolcall_expected_vram_gb: 13.2
llm_combined_expected_vram_gb: 23.2
llm_gpu_total_vram_gb: 24.0