LLM跑在边缘芯片上

模型工具，转换，加载等等
 
 Distributed Llama https://github.com/b4rtaz/distributed-llama?tab=readme-ov-file 
 
 
 语音模型
 
 https://github.com/k2-fsa/sherpa-onnx 
 小智生态 https://github.com/xinnan-tech/xiaozhi-esp32-server