[Unit]
Description=MOSS Transcribe Diarize Service (SGLang Omni)
After=network-online.target

[Service]
Type=simple
User=oraltrainer
WorkingDirectory=/opt/moss-transcribe/MOSS-Transcribe-Diarize
Environment=HF_ENDPOINT=https://hf-mirror.com
ExecStart=/opt/moss-transcribe/MOSS-Transcribe-Diarize/.venv/bin/sgl-omni serve \
  --model-path OpenMOSS-Team/MOSS-Transcribe-Diarize \
  --host 127.0.0.1 \
  --port 8001 \
  --max-running-requests 4 \
  --cuda-graph-max-bs 4 \
  --mem-fraction-static 0.35
Restart=on-failure
RestartSec=10
TimeoutStartSec=1800

[Install]
WantedBy=multi-user.target