[Unit]
Description=llama-server (shadow) — Qwen2.5-14B-Instruct Q5_K_M (OpenAI-compatible inference, 64K ctx)
After=network.target nvidia-persistenced.service
Wants=nvidia-persistenced.service

[Service]
Type=simple
User={{ llm_service_user }}
Group={{ llm_service_user }}
Environment="HOME=/home/{{ llm_service_user }}"
ExecStart={{ llm_binary_path }} \
    --model {{ llm_qwen_model_path }} \
    --host 0.0.0.0 \
    --port {{ llm_qwen_port }} \
    --n-gpu-layers {{ llm_qwen_gpu_layers }} \
    --ctx-size {{ llm_qwen_ctx_size }} \
    --flash-attn \
    --cache-type-k q8_0 --cache-type-v q8_0 \
    --batch-size {{ llm_qwen_batch_size }} --ubatch-size {{ llm_qwen_ubatch_size }} \
    --jinja \
    --parallel {{ llm_qwen_parallel }} \
    --metrics
# Shadow-deployment candidate per local-llm-64k-context-recommendation.md.
# NOT yet cleared for production Hermes profile routing — must pass
# scripts/tool-calling-validation.sh AND have verified n_ctx >= 64000 from
# /v1/models before any repoint decision.
# VRAM GATE: as of 2026-08-06, Phi-4(8000)+Mistral(8001) already consume
# ~16.6GB/24GB (7.5GB free). This model's weights alone are ~10-12GB — does
# NOT fit concurrently without freeing VRAM. Do not enable this unit until
# that is resolved (see role README "Qwen shadow deployment — VRAM gate").
Restart=on-failure
RestartSec=10
TimeoutStartSec=600
StandardOutput=journal
StandardError=journal
SyslogIdentifier=llama-server-qwen

[Install]
WantedBy=multi-user.target