构建llama.cpp并在linux上使用gpu

使用gpu构建llama.cpp

更多详情参见https://github.com/abetlen/llama-cpp-python,官网网站会随着版本迭代更新。

下载并进入llama.cpp

地址:https://github.com/ggerganov/llama.cpp

可以下载到本地再传到服务器上

bash 复制代码
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp

编译源码(make)

生成./main和./quantize等二进制文件。详见:https://github.com/ggerganov/llama.cpp/blob/master/docs/build.md

使用CPU
bash 复制代码
make
使用GPU
bash 复制代码
make GGML_CUDA=1
可能出现的报错及解决方法

I ccache not found. Consider installing it for faster compilation.

bash 复制代码
sudo apt-get install ccache

Makefile:1002: *** I ERROR: For CUDA versions < 11.7 a target CUDA architecture must be explicitly provided via environment variable CUDA_DOCKER_ARCH, e.g. by running "export CUDA_DOCKER_ARCH=compute_XX" on Unix-like systems, where XX is the minimum compute capability that the code needs to run on. A list with compute capabilities can be found here: https://developer.nvidia.com/cuda-gpus . Stop.

说明cuda版本太低,如果不是自己下载好的,参考该文章nvcc -V 显示的cuda版本和实际版本不一致更换
NOTICE: The 'server' binary is deprecated. Please use 'llama-server' instead.

提示:随版本迭代,命令可能会失效

正确结果

内容很长,只截取了一部分

调用大模型

安装llama.cpp,比较慢

bash 复制代码
CMAKE_ARGS="-DGGML_CUDA=on" pip install llama-cpp-python

调用

python 复制代码
from langchain_community.chat_models import ChatLlamaCpp
from langchain_community.llms import LlamaCpp

local_model = "/data/pretrained/gguf/Meta-Llama-3-8B-Instruct-Q5_K_M.gguf"
llm = ChatLlamaCpp(
    seed=1,
    temperature=0.5,
    model_path=local_model,
    n_ctx=8192,
    n_gpu_layers=64,
    n_batch=12,  # Should be between 1 and n_ctx, consider the amount of VRAM in your GPU.
    max_tokens=8192,
    repeat_penalty=1.5,
    top_p=0.5,
    f16_kv=False,
    verbose=True,
)
messages = [
    (
        "system",
        "You are a helpful assistant that translates English to Chinese. Translate the user sentence.",
    ),
    ("human",
     "OpenAI has a tool calling API that lets you describe tools and their arguments, and have the model return a JSON object with a tool to invoke and the inputs to that tool. tool-calling is extremely useful for building tool-using chains and agents, and for getting structured outputs from models more generally."),
]

ai_msg = llm.invoke(messages)
print(ai_msg.content)

正确打印中存在如下内容,说明找到gpu

ggml_cuda_init: found 2 CUDA devices:
  Device 0: 你的gpu型号, compute capability gpu计算能力, VMM: yes
  Device 1: 你的gpu型号, compute capability gpu计算能力, VMM: yes
llm_load_tensors: offloading 32 repeating layers to GPU
llm_load_tensors:        CPU buffer size =   344.44 MiB
llm_load_tensors:      CUDA0 buffer size =  2932.34 MiB
llm_load_tensors:      CUDA1 buffer size =  2183.15 MiB
相关推荐
我爱学Python!4 小时前
解决复杂查询难题:如何通过 Self-querying Prompting 提高 RAG 系统效率?
人工智能·程序人生·自然语言处理·大模型·llm·大语言模型·rag
任某某01161 天前
第四期书生大模型实战营 - 基础岛闯关作业3 - 浦语提示词工程实践
llm
知来者逆2 天前
DrugLLM——利用大规模语言模型通过 Few-Shot 生成生物制药小分子
人工智能·语言模型·自然语言处理·llm·大语言模型·生物制药
waiting不是违停2 天前
MetaGPT实现多动作Agent
langchain·llm
HuggingFace3 天前
通用辅助生成: 使用任意辅助模型加速解码
llm
用户3157476081353 天前
带你在前端上玩转机器学习,从零去构建,训练一个模型!!
前端·机器学习·llm
Seal软件3 天前
配置NVIDIA Container Runtime和容器运行GPUStack教程
docker·容器·大模型·llm·gpu集群
GPUStack3 天前
配置NVIDIA Container Runtime和容器运行GPUStack教程
docker·容器·大模型·llm·gpu集群
一 铭4 天前
llamaindex实战-Agent-在Agent中和数据库对话(本地部署)
人工智能·chatgpt·大模型·llm