Reference documentation and code samples for the Vertex AI V1 API class Google::Cloud::AIPlatform::V1::SpeculativeDecodingSpec::DraftModelSpeculation.
Draft model speculation works by using the smaller model to generate candidate tokens for speculative decoding.
Inherits
- Object
Extended By
- Google::Protobuf::MessageExts::ClassMethods
Includes
- Google::Protobuf::MessageExts
Methods
#draft_model
def draft_model() -> ::String
Returns
- (::String) — Required. The resource name of the draft model.
#draft_model=
def draft_model=(value) -> ::String
Parameter
- value (::String) — Required. The resource name of the draft model.
Returns
- (::String) — Required. The resource name of the draft model.