llama_batch class final

Input data for llama_decode A llama_batch object can contain input about one or many sequences The provided arrays (i.e. token, embd, pos, etc.) must have size of n_tokens

  • token : the token ids of the input (used when embd is NULL)
  • embd : token embeddings (i.e. float vector of size n_embd) (used when token is NULL)
  • pos : the positions of the respective token in the sequence
  • seq_id : the sequence to which the respective token belongs
  • logits : if zero, the logits for the respective token will not be output
Inheritance
Implemented types
Available extensions

Constructors

llama_batch()

Properties

address Pointer<T>

Available on T, provided by the StructAddress extension

The memory address of the underlying data.
no setter
all_pos_0 int
used if pos == NULL
getter/setter pair
all_pos_1 int
used if pos == NULL
getter/setter pair
all_seq_id int
used if seq_id == NULL
getter/setter pair
embd Pointer<Float>
getter/setter pair
hashCode int
The hash code for this object.
no setterinherited
logits Pointer<Int8>
getter/setter pair
n_seq_id Pointer<Int32>
getter/setter pair
n_tokens int
getter/setter pair
pos Pointer<llama_pos>
getter/setter pair
runtimeType Type
A representation of the runtime type of the object.
no setterinherited
seq_id Pointer<Pointer<llama_seq_id>>
getter/setter pair
token Pointer<llama_token>
getter/setter pair

Methods

noSuchMethod(Invocation invocation) → dynamic
Invoked when a nonexistent method or property is accessed.
inherited
toString() String
A string representation of this object.
inherited

Operators

operator ==(Object other) bool
The equality operator.
inherited