---
# ------------------------------------------------------------------------------
# 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 (deprecated — replaced by llama-server)
# llama-server serve
llm_serve_port: 8000
llm_serve_host: "0.0.0.0"
# NOTE (2026-08-05): --ctx-size is llama.cpp's TOTAL KV cache pool, divided
# evenly across --parallel slots (per-slot context = ctx-size / parallel).
# Previous 8192/4=2048 tokens-per-slot was too small for aux task offload
# (context compression) and caused live rejections: "request (3826 tokens)
# exceeds the available context size (2048 tokens)".
# Sized against measured VRAM on astro-orbiter (RTX 3090, 24576MiB total):
#   - Weights (Q4_K_M, 27B) ~16998MiB resident.
#   - At ctx-size=8192/parallel=4, total llama-server VRAM = 19404MiB
#     (nvidia-smi), i.e. ~2406MiB for KV cache + compute buffers at 8192
#     total context tokens -> ~294KiB/token (pool-wide, incl. buffers).
#   - Model n_ctx_train=8192 is the native max; per-slot context beyond
#     this degrades coherence, so per-slot should cap at 8192.
#   - New sizing: ctx-size=16384, parallel=2 -> 8192 tokens/slot (native
#     max, covers compression's multi-thousand-token inputs with margin).
#     Projected VRAM: 16998 + (~294KiB/token * 16384) ≈ 21.8GB used,
#     leaving ~2.7GB headroom on the 24GB card.
#   - parallel=2 (not 4) trades some concurrency for correct per-slot
#     context; 2 concurrent aux-task requests is enough headroom before
#     the known "3+ simultaneous compressions" GPU bottleneck kicks in.
llm_max_model_len: 16384
llm_gpu_layers: 99              # offload all layers to GPU
llm_parallel_slots: 2           # concurrent request slots -> 8192 tokens/slot (ctx-size / parallel)
llm_gguf_dir: /home/jarvis/models
llm_gguf_path: /home/jarvis/models/gemma-2-27b-it-Q4_K_M.gguf

# Legacy vLLM vars (kept for role documentation, not used by llama-server)
llm_quantization: "bitsandbytes"
llm_gpu_memory_utilization: "0.92"

# Monitoring
llm_gpu_exporter_version: "1.13.1"
llm_gpu_exporter_port: 9835