Update README.md

add cpu version readme

README.md

@@ -40,6 +40,7 @@ print(response)
 ```
 
 ### AgentLMs as service
+#### Serving by [vLLM](https://github.com/vllm-project/vllm) (GPU)
 We recommend using [vLLM](https://github.com/vllm-project/vllm) and [FastChat](https://github.com/lm-sys/FastChat) to deploy the model inference service. First, you need to install the corresponding packages (for detailed usage, please refer to the documentation of the two projects):
 ```bash
 pip install vllm
@@ -67,6 +68,16 @@ curl http://localhost:8888/v1/chat/completions \
 -d '{"model": "kagentlms_qwen_7b_mat", "messages": [{"role": "user", "content": "Who is Andy Lau"}]}'
 ```
 
+
+#### Serving by [Lamma.cpp](https://github.com/ggerganov/llama.cpp) (CPU)
+llama-cpp-python offers a web server which aims to act as a drop-in replacement for the OpenAI API. This allows you to use llama.cpp compatible models with any OpenAI compatible client (language libraries, services, etc). The converted model can be found in [kwaikeg/kagentlms_qwen_7b_mat_gguf](https://huggingface.co/kwaikeg/kagentlms_qwen_7b_mat_gguf).
+
+To install the server package and get started:
+```bash
+pip install "llama-cpp-python[server]"
+python3 -m llama_cpp.server --model kagentlms_qwen_7b_mat_gguf/ggml-model-q4_0.gguf --chat_format chatml --port 8888
+```
+
 ### Citation
 ```
 @article{pan2023kwaiagents,