Skip to content

multi

diapason.engine.multi

Multi-engine wrapper — routes requests to the right backend by model name.

MultiEngine

Bases: InferenceEngine

Wraps multiple engines and routes by model name.

Models from each engine are discovered via list_models(). When generate() or stream() is called, the model name is looked up to find which engine owns it.

stream_full(messages, *, model, **kwargs) async

Delegate stream_full() to the engine that owns the model.