3分钟快速上手：llama-cpp-python完整安装与配置指南 | 极客日志

3分钟快速上手：llama-cpp-python完整安装与配置指南 | 极客日志

pip install llama-cpp-python

CMAKE_ARGS="-DGGML_CUDA=on" pip install llama-cpp-python

CMAKE_ARGS="-DGGML_METAL=on" pip install llama-cpp-python

CMAKE_ARGS="-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python

pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu

pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu121

from llama_cpp import Llama # 初始化模型（请替换为实际模型路径） llm = Llama(model_path="./models/your-model.gguf") # 进行简单的文本生成测试 output = llm("你好，请介绍一下你自己", max_tokens=32) print(output)

$env:CMAKE_GENERATOR = "MinGW Makefiles" $env:CMAKE_ARGS = "-DGGML_OPENBLAS=on -DCMAKE_C_COMPILER=C:/w64devkit/bin/gcc.exe"

git clone --recurse-submodules https://gitcode.com/gh_mirrors/ll/llama-cpp-python cd llama-cpp-python # 升级pip以确保兼容性 pip install --upgrade pip # 以可编辑模式安装 pip install -e . # 安装服务器功能（可选） pip install -e '.[server]'

from llama_cpp import Llama # 初始化模型并设置参数 llm = Llama( model_path="./models/7B/llama-model.gguf", n_ctx=2048, # 设置上下文窗口大小 n_gpu_layers=-1, # 启用GPU加速 seed=1337 # 设置随机种子 ) # 创建文本补全 response = llm.create_completion( prompt="请解释什么是人工智能", max_tokens=100, temperature=0.7 )

# 创建聊天完成 chat_response = llm.create_chat_completion( messages=[ {"role": "system", "content": "你是一个乐于助人的AI助手"}, {"role": "user", "content": "今天天气怎么样？"} ] )