ggml_win_part method

Pointer<ggml_tensor> ggml_win_part(
  1. Pointer<ggml_context> ctx,
  2. Pointer<ggml_tensor> a,
  3. int w
)

partition into non-overlapping windows with padding if needed example: a: 768 64 64 1 w: 14 res: 768 14 14 25 used in sam

Implementation

ffi.Pointer<ggml_tensor> ggml_win_part(
  ffi.Pointer<ggml_context> ctx,
  ffi.Pointer<ggml_tensor> a,
  int w,
) {
  return _ggml_win_part(
    ctx,
    a,
    w,
  );
}