The system logs all activity to model_manager.log. You can monitor it in real-time using:
./monitor.shtail -f model_manager.logtail -f model_manager.log | while read line; do echo "$(date +%T) | $line"; done# Watch only scheduler activity
tail -f model_manager.log | grep SCHEDULER
# Watch only job execution
tail -f model_manager.log | grep ENGINE
# Watch queue operations
tail -f model_manager.log | grep QUEUE- File:
model_manager.log(in the ModelManager directory) - Format:
[HH:MM:SS.mmm] [COMPONENT ] Message - Components: SYSTEM, QUEUE, SCHEDULER, ENGINE, MONITOR, REGISTRY, API
- Job submissions and status changes
- Scheduler decisions (load/unload/execute)
- Execution progress
- Resource monitoring (VRAM, loaded models)
- Errors and warnings
Terminal 1 - Run the system:
python main.pyTerminal 2 - Monitor in real-time:
./monitor.shTerminal 3 - Submit jobs:
python test_system.pyPress Ctrl+C in the monitoring terminal. This only stops the monitor, not the system.