1，视频演示地址

2，项目地址go-llama.cpp

下载并进行编译：

git clone --recurse-submodules https://github.com/go-skynet/go-llama.cpp
cd go-llama.cpp
make libbinding.a

项目中还打了个补丁：

给

编译成功，虽然有一点 warning 警告信息，问题不大。

3，然后运行 llama-2-7b-chat 模型

LIBRARY_PATH=$PWD C_INCLUDE_PATH=$PWD go run ./examples -m "/data/home/test/hf_cache/llama-2-7b-chat.Q2_K.gguf" -t 14

LIBRARY_PATH=$PWD C_INCLUDE_PATH=$PWD go run ./examples -m "/data/home/test/hf_cache/qwen1_5-0_5b-chat-q6_k.gguf" -t 14

error loading model: unknown model architecture: 'qwen2'
llama_load_model_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model '/data/home/test/hf_cache/qwen1_5-0_5b-chat-q6_k.gguf'
load_binding_model: error: unable to load model
Loading the model failed: failed loading model