get next token from lexer

! @return whether array creation completed */

! @param[out] dim an integer vector storing the ND array dimensions @return whether reading ND array size vector is successful */

! @return whether object creation completed */

! @brief determine the type and size for a container In the optimized UBJSON format, a type and a size can be provided to allow for a mor

! @param[out] result determined size @param[in,out] is_ndarray for input, `true` means already inside an ndarray vector

! @brief reads a UBJSON string This function is either called after reading the 'S' byte explicitly indicating a string, or in case of an

! @param prefix the previously read or set type prefix @return whether value creation completed */

Conversion constructor. \param rhs float to convert \exception FE_OVERFLOW, ...UNDERFLOW, ...INEXACT according to rounding

Smallest positive subnormal value.

Difference between 1 and next representable value.

Positive infinity.

Largest finite value.

Quiet NaN.

Maximum rounding error in ULP (units in the last place).

Signaling NaN.

@brief return whether the value has a subtype @sa https://json.nlohmann.me/api/byte_container_with_subtype/has_subtype/

Hypotenuse function. This function is exact to rounding for all rounding modes. See also:** Documentation for [std::hypot](https://en.cppreference.co

Called before waiting for new jobs.

Extract exponent. See also:** Documentation for [std::ilogb](https://en.cppreference.com/w/cpp/numeric/math/ilogb). \param arg number to query \return

Called before the work loop.

Runs some initialization after the model is loaded.

@brief return whether value is discarded @sa https://json.nlohmann.me/api/basic_json/is_discarded/