Class SpeculativeDecodingSpec.NgramSpeculation

java.lang.Object
com.google.protobuf.AbstractMessageLite
com.google.protobuf.AbstractMessage
com.google.protobuf.GeneratedMessage
com.google.cloud.aiplatform.v1.SpeculativeDecodingSpec.NgramSpeculation
All Implemented Interfaces:
SpeculativeDecodingSpec.NgramSpeculationOrBuilder, com.google.protobuf.Message, com.google.protobuf.MessageLite, com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder, Serializable
Enclosing class:
SpeculativeDecodingSpec

public static final class SpeculativeDecodingSpec.NgramSpeculation extends com.google.protobuf.GeneratedMessage implements SpeculativeDecodingSpec.NgramSpeculationOrBuilder
 N-Gram speculation works by trying to find matching tokens in the
 previous prompt sequence and use those as speculation for generating
 new tokens.
 
Protobuf type google.cloud.aiplatform.v1.SpeculativeDecodingSpec.NgramSpeculation
See Also:
  • Field Details

    • NGRAM_SIZE_FIELD_NUMBER

      public static final int NGRAM_SIZE_FIELD_NUMBER
      See Also:
  • Method Details