Skip to main content

Module multi_model

Module multi_model 

Source
Expand description

Multi-model serving: manage base models + LoRA adapters with smart routing.

Supports:

  • Multiple base model configurations
  • Hot-swappable LoRA adapter registry
  • Request routing by model ID
  • Model alias resolution
  • Adapter composition (stacking multiple LoRAs)

Structs§

AdapterRef
A reference to a single LoRA adapter with a blending weight.
AdapterStack
Adapter composition: apply multiple LoRA adapters in sequence.
ModelEndpoint
Metadata for a served model variant.
ModelId
A model endpoint identifier.
ModelListEntry
Entry for an OpenAI-compatible /v1/models response.
ModelRegistry
The multi-model registry.
ModelRouter
Smart request router: selects the best model endpoint for a request.

Enums§

EndpointStatus
Status of a model endpoint.
RoutingError
Errors that can occur when routing a request to a model endpoint.