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.