Configuration
TokenPrint can be configured via backend environment variables (.env) or CLI flags when starting the backend inspection service.
Environment Variables
| Variable | Default | Description |
|---|---|---|
MODEL_PATH | ./models/qwen2.5-0.5b-instruct.gguf | Path to primary GGUF model file on backend. |
PORT | 8000 | FastAPI backend HTTP and WebSocket port. |
DEVICE | cpu | Inference target (cpu, mps, or cuda). |
CACHE_DIR | ~/.cache/tokenprint | Local directory for downloaded models and trace records. |
Frontend Settings
Frontend configuration options (such as WebGL rendering precision, maximum FPS cap, and auto-scroll behavior) can be adjusted in the App Settings panel or persisted in localStorage.