@brief return whether pointer points to the root document @sa https://json.nlohmann.me/api/json_pointer/empty/

\brief from pretrained \param model_name the model name

\brief get all the models \return all the models in json

\brief get the average speed \return the average speed

\brief Get the max length \return the max length

@brief return whether value is a floating-point number @sa https://json.nlohmann.me/api/basic_json/is_number_float/

return the key of an object iterator

\brief release

AVX-512 optimized rescale and normalize function

AVX-512 optimized main RGB planar entry point

set iterator to a defined past the end

@brief write response from callback (for queued requests)

! @param[in] j JSON value to serialize @param[in] use_count whether to use '#' prefixes (optimized format) @param[in] use_type wheth

@brief access specified array element with bounds checking @sa https://json.nlohmann.me/api/basic_json/at/

\brief AVX2 Convert bfloat16 to float32 \param bf16_vals the bfloat16 values, 128-bits, 8xbf16 \return the float32 values, 256-bits, 8xfloat32

Keys bicubic kernel (a = -0.5) - matches PyTorch antialias=True

@brief returns a const iterator to the first element @sa https://json.nlohmann.me/api/basic_json/cbegin/

Fast conversion from float to uint8 with clamping

AVX512 fast float copy

@brief returns the number of occurrences of a key in a JSON object @sa https://json.nlohmann.me/api/basic_json/count/

@brief get_server_port gets the server port from environment variable FLM_SERVE_PORT @return the server port, default is 52625 if environment variable

@brief return whether type is primitive @sa https://json.nlohmann.me/api/basic_json/is_primitive/

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

Convert frequency from mels to hertz. Args: mels (`float` or `np.ndarray`): The frequency, or multiple frequencies, in m

\brief re-unit the time \param time the time \return the re-unit time

\brief Run the runner

set iterator to a defined beginning

\brief Set the max length \param MAX_L the max length \note The function will set the max length \note The function will update the max length

\brief Show the cursor

! @brief unget current character (read it again on next get) We implement unget by setting variable next_unget to true. The input is not

\brief AVX2 Absolute value \param x the input value, 256-bits, 8xfloat32 \return the absolute value, 256-bits, 8xfloat32

Vectorized bicubic kernel computation for 16 floats

\brief Calculates the SHA256 hash of a file. \param file_path The path to the file. \return A string representing the hex digest of the hash, or an em

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

@brief convert the npu sequence to the npu format @note The function will convert the npu sequence to the npu format @note If the npu sequence is pre-

\brief copy from \param src the source \param size the size

\brief Download content from URL to a string \param url the URL to download from \return the downloaded string

@brief dump the sequence to a uint32 array, return the pointer and size @return std::pair<uint32_t*, size_t>