34 lines
1.1 KiB
Django/Jinja
34 lines
1.1 KiB
Django/Jinja
[Unit]
|
|
Description=llama-server (aux/classification) — Phi-4-14B Q4_K_M (OpenAI-compatible inference)
|
|
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_aux_model_path }} \
|
|
--host {{ llm_bind_address }} \
|
|
--port {{ llm_aux_port }} \
|
|
--ctx-size {{ llm_aux_ctx_size }} \
|
|
--n-gpu-layers {{ llm_aux_gpu_layers }} \
|
|
--parallel {{ llm_aux_parallel }} \
|
|
--metrics
|
|
# NOTE: no --chat-template flag — let llama-server auto-detect Phi-4's own
|
|
# embedded chat template from GGUF metadata (same reasoning as the existing
|
|
# llm-inference role's Gemma unit: explicit overrides risk mismatching the
|
|
# model's actual expected format).
|
|
# NOTE: --host is the private LAN IP (10.1.71.130 by default), NOT 0.0.0.0 —
|
|
# deliberate change from the pre-existing Gemma pattern (plan §5).
|
|
Restart=on-failure
|
|
RestartSec=10
|
|
TimeoutStartSec=600
|
|
StandardOutput=journal
|
|
StandardError=journal
|
|
SyslogIdentifier=llama-server-aux
|
|
|
|
[Install]
|
|
WantedBy=multi-user.target
|