[Unit]
Description=llama-server — Qwen3.6-35B-A3B-UD-Q4_K_S (OpenAI-compatible inference, 64K ctx)
Documentation=https://github.com/ggml-org/llama.cpp
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 {{ llm_bind_address }} \
    --port {{ llm_qwen_port }} \
    --n-gpu-layers {{ llm_qwen_gpu_layers }} \
    --ctx-size {{ llm_qwen_ctx_size }} \
    --flash-attn on \
    --cache-type-k q4_0 --cache-type-v q4_0 \
    --batch-size {{ llm_qwen_batch_size }} --ubatch-size {{ llm_qwen_ubatch_size }} \
    --parallel {{ llm_qwen_parallel }} \
    --metrics

# PRODUCTION UNIT — Qwen3.6-35B-A3B-UD-Q4_K_S
# Current as of 2026-08-07 (t_2ffc0f63) — superseded Qwen2.5-14B-Instruct-1M.
# VRAM: ~20,390 MiB / 24,576 MiB (verified 2026-08-07).
# Context: 65536 (64K) with q4_0 KV cache to fit 64K in 24GB headroom.
# DO NOT change --cache-type-k/v — q8_0 requires more VRAM; 24GB is tight.
# DO NOT add --jinja — Qwen3.6's embedded chat template is correct for
#   both chat and tool-calling without an override.
#
# Shadow validation (router mode, port 8003) — see templates/llama-server-router.service.j2
# and playbooks/day1_deploy_llm_router_shadow.yml (t_0cca74a2).
# This unit is the ROLLBACK TARGET — preserved on 8002 until router validation
# passes and Ryan approves cutover.
Restart=on-failure
RestartSec=10
TimeoutStartSec=600
StandardOutput=journal
StandardError=journal
SyslogIdentifier=llama-server-qwen

[Install]
WantedBy=multi-user.target