Dashboard
Live activity, model status, and recent traffic.
How recommendations are chosen
Recommendations consider machine compatibility, installed Backends, model architecture and format, estimated memory, and available memory now. They prefer official current-family checkpoints and comfortable fits; community and experimental text variants remain in All models.
Recommendation slots use catalog format and tier heuristics, not measured benchmarks. Best quality means the largest fitting tier; fastest means the smallest tier.
Multimodal recommendations show image/audio capabilities and missing add-ons. Install required add-ons in Backends before loading with media. Saved load settings are not changed by the recommendation Backend.
Loaded models
On disk
Usage by model
Live counters for recorded Decisions.
Lifetime usage is shared with Dashboard’s model activity. Recent traffic is a separate process-local window; viewing either page does not add requests.
Resetting a model or all statistics also clears matching recent traffic in this app process. Lifetime totals are shared across apps using the same settings file.
Checks cover this app’s Python environment. A passing inference test applies only to its selected model and execution mode.
Inference tests and restoration
Request settings
One simple item ({"state", "question", "options", "gold"?}) or one /v1/systemone request per line; one answer per line in the same order (format: docs/SERVING.md#inference-on-a-jsonl-file). Batch requests go straight to the model: they are not counted in the statistics or the history.
basal-viz loads the bf16 PyTorch weights of basal-1.0, basal-1.5, basal-2.0 or basal-omni into basal-ui’s process (counted in the memory budget) and shows the prompt of every option order, its tokens, the decision after every layer and the calibration. Inspect this decision in the Playground sends the request here and lists what differs from the served decision.
Local-network access without a required API key is not recommended.
API keys
Connect
Start the API server with MCP enabled to use this example.
Snippets describe the running server; saved settings apply after Restart.
Memory & storage
Memory
Defaults
Presets
Appearance
Appearance preferences are saved in this browser.
Color skin
Theme
No output yet.