Description:
We currently provide a Python demo for MiniCPM4 in the LLM-TPU project:

LLM-TPU repository: https://github.com/sophgo/LLM-TPU/tree/main
MiniCPM4 model demo (Python): https://github.com/sophgo/LLM-TPU/tree/main/models/MiniCPM4

Task:
Implement a C++ version of the MiniCPM4 chat/demo that achieves functionality and output quality comparable to the existing Python demo. There is an example in Qwen3, you can also refer to it.

Requirements:
Ensure generated responses are similar in style and quality to the Python demo.