I find it a bit hard to justify using the STL when a single <unordered_map> include costs 250ms compile time per compile unit.

The fact that I don't have to step through this in the debugger is also a bonus:

  template <size_t _Offset, size_t _Count = dynamic_extent>
  [[nodiscard]] _LIBCPP_HIDE_FROM_ABI constexpr auto subspan() const noexcept
      -> span<element_type, _Count != dynamic_extent ? _Count : _Extent - _Offset> {
    static_assert(_Offset <= _Extent, "span<T, N>::subspan<Offset, Count>(): Offset out of range");
    static_assert(_Count == dynamic_extent || _Count <= _Extent - _Offset,
                  "span<T, N>::subspan<Offset, Count>(): Offset + Count out of range");

    using _ReturnType = span<element_type, _Count != dynamic_extent ? _Count : _Extent - _Offset>;
    return _ReturnType{data() + _Offset, _Count == dynamic_extent ? size() - _Offset : _Count};
  }