llama_kv_cache_seq_cp method

void llama_kv_cache_seq_cp(
  1. Pointer<llama_context> ctx,
  2. int seq_id_src,
  3. int seq_id_dst,
  4. int p0,
  5. int p1,
)

Copy all tokens that belong to the specified sequence to another sequence Note that this does not allocate extra KV cache memory - it simply assigns the tokens to the new sequence p0 < 0 : 0, p1 p1 < 0 : [p0, inf)

Implementation

void llama_kv_cache_seq_cp(
  ffi.Pointer<llama_context> ctx,
  int seq_id_src,
  int seq_id_dst,
  int p0,
  int p1,
) {
  return _llama_kv_cache_seq_cp(
    ctx,
    seq_id_src,
    seq_id_dst,
    p0,
    p1,
  );
}