llama_batch_get_one method

llama_batch llama_batch_get_one(
  1. Pointer<llama_token> tokens,
  2. int n_tokens,
  3. int pos_0,
  4. int seq_id,
)

Return batch for single sequence of tokens starting at pos_0

NOTE: this is a helper function to facilitate transition to the new batch API - avoid using it

Implementation

llama_batch llama_batch_get_one(
  ffi.Pointer<llama_token> tokens,
  int n_tokens,
  int pos_0,
  int seq_id,
) {
  return _llama_batch_get_one(
    tokens,
    n_tokens,
    pos_0,
    seq_id,
  );
}