! @return The size of the BSON-encoded string in @a value */

! @return The size of the BSON-encoded unsigned integer in @a j */

\brief cast to milliseconds \param time the time \return the time in milliseconds

\brief check if the file exists \param name the name of the file

\brief check if the file exists \param name the name of the file \return true if the file exists, false otherwise

\brief Check if the model is compatible with the current FLM version \param model_tag the model tag \return true if the model is compatible, false oth

Creates a chroma filter bank, i.e a linear transformation to project spectrogram bins onto chroma bins. Adapted from *librosa*. Args:

@brief clears the contents @sa https://json.nlohmann.me/api/basic_json/clear/

\brief Clear line from cursor to end

@brief clears the binary subtype @sa https://json.nlohmann.me/api/byte_container_with_subtype/clear_subtype/

---------------------------------------------------------------------------

@brief close connection

\brief Show the help shotcut \param input_list, std::vector<std::string>

@brief Configure chat engine parameters from options and request @param options the options JSON object @param request the request JSON object

\brief Override configure_parameter to handle Qwen3-specific parameters

\brief Configure a parameter with type-erased value \param parameter_name the name of the parameter \param value the value to set (can be any type) \r

\brief Configure a parameter with type-erased value \param parameter_name the name of the parameter \param value the value to set (can be any type) \r

\brief Override configure_parameter to handle GPT-oss-specific parameters

\brief Configure a parameter with type-erased value \param parameter_name the name of the parameter \param value the value to set (can be any type) \r

\brief Configure a parameter with type-erased value \param parameter_name the name of the parameter \param value the value to set (can be any type) \r

Computes the output length of a 1D convolution layer according to torch's documentation: https://docs.pytorch.org/docs/stable/generated/torch

can't use the conversion operator because of ambiguity

Converts the 32 bits of a normal float or zero to the bits of a bfloat16.

\brief copy from \param vec the vector

@brief Create a npu_app @return a npu_app object @see npu_app

\brief Create a new line and move cursor to it

@brief Create a runlist @return a runlist object @see xrt::runlist

\brief data \return the data

! @brief check whether a string is UTF-8 encoded The function checks each byte of a string whether it is UTF-8 encoded. The result of the

@brief do accept

0 is S2MM, 1 is MM2S