AI大模型部署Ubuntu服务器攻略

一、下载Ollama

在线安装:

在linux中输入命令curl -fsSL https://ollama.com/install.sh | sh
由于在linux下载ollama需要经过外网,网络会不稳定,很容易造成连接超时的问题。

离线安装:

步骤一: 下载Ollama离线版本
在linux服务器中输入命令:lscpu查看服务器型号
然后再该地址中下载Ollama离线版本:
https://github.com/ollama/ollama/releases
步骤二: 下载install.sh文件修改内容
地址为:https://ollama.com/install.sh

修改位置1:
注释掉在线下载ollama的命令
修改位置2:

修改ollama安装地址,将ollama离线版本与install放到一起
install.sh最终修改的版本:

#!/bin/sh
# This script installs Ollama on Linux.
# It detects the current operating system architecture and installs the appropriate version of Ollama.

set -eu

status() { echo ">>> $*" >&2; }
error() { echo "ERROR $*"; exit 1; }
warning() { echo "WARNING: $*"; }

TEMP_DIR=$(mktemp -d)
cleanup() { rm -rf $TEMP_DIR; }
trap cleanup EXIT

available() { command -v $1 >/dev/null; }
require() {
    local MISSING=''
    for TOOL in $*; do
        if ! available $TOOL; then
            MISSING="$MISSING $TOOL"
        fi
    done

    echo $MISSING
}

[ "$(uname -s)" = "Linux" ] || error 'This script is intended to run on Linux only.'

ARCH=$(uname -m)
case "$ARCH" in
    x86_64) ARCH="amd64" ;;
    aarch64|arm64) ARCH="arm64" ;;
    *) error "Unsupported architecture: $ARCH" ;;
esac

IS_WSL2=false

KERN=$(uname -r)
case "$KERN" in
    *icrosoft*WSL2 | *icrosoft*wsl2) IS_WSL2=true;;
    *icrosoft) error "Microsoft WSL1 is not currently supported. Please upgrade to WSL2 with 'wsl --set-version <distro> 2'" ;;
    *) ;;
esac

VER_PARAM="${OLLAMA_VERSION:+?version=$OLLAMA_VERSION}"

SUDO=
if [ "$(id -u)" -ne 0 ]; then
    # Running as root, no need for sudo
    if ! available sudo; then
        error "This script requires superuser permissions. Please re-run as root."
    fi

    SUDO="sudo"
fi

NEEDS=$(require curl awk grep sed tee xargs)
if [ -n "$NEEDS" ]; then
    status "ERROR: The following tools are required but missing:"
    for NEED in $NEEDS; do
        echo "  - $NEED"
    done
    exit 1
fi

status "Downloading ollama..."
# curl --fail --show-error --location --progress-bar -o $TEMP_DIR/ollama "https://ollama.com/download/ollama-linux-${ARCH}${VER_PARAM}"

for BINDIR in /usr/local/bin /usr/bin /bin; do
    echo $PATH | grep -q $BINDIR && break || continue
done

status "Installing ollama to $BINDIR..."
$SUDO install -o0 -g0 -m755 -d $BINDIR
# $SUDO install -o0 -g0 -m755 $TEMP_DIR/ollama $BINDIR/ollama
$SUDO install -o0 -g0 -m755 ./ollama-linux-amd64 $BINDIR/ollama

install_success() {
    status 'The Ollama API is now available at 127.0.0.1:11434.'
    status 'Install complete. Run "ollama" from the command line.'
}
trap install_success EXIT

# Everything from this point onwards is optional.

configure_systemd() {
    if ! id ollama >/dev/null 2>&1; then
        status "Creating ollama user..."
        $SUDO useradd -r -s /bin/false -U -m -d /usr/share/ollama ollama
    fi
    if getent group render >/dev/null 2>&1; then
        status "Adding ollama user to render group..."
        $SUDO usermod -a -G render ollama
    fi
    if getent group video >/dev/null 2>&1; then
        status "Adding ollama user to video group..."
        $SUDO usermod -a -G video ollama
    fi

    status "Adding current user to ollama group..."
    $SUDO usermod -a -G ollama $(whoami)

    status "Creating ollama systemd service..."
    cat <<EOF | $SUDO tee /etc/systemd/system/ollama.service >/dev/null
[Unit]
Description=Ollama Service
After=network-online.target

[Service]
ExecStart=$BINDIR/ollama serve
User=ollama
Group=ollama
Restart=always
RestartSec=3
Environment="PATH=$PATH"

[Install]
WantedBy=default.target
EOF
    SYSTEMCTL_RUNNING="$(systemctl is-system-running || true)"
    case $SYSTEMCTL_RUNNING in
        running|degraded)
            status "Enabling and starting ollama service..."
            $SUDO systemctl daemon-reload
            $SUDO systemctl enable ollama

            start_service() { $SUDO systemctl restart ollama; }
            trap start_service EXIT
            ;;
    esac
}

if available systemctl; then
    configure_systemd
fi

# WSL2 only supports GPUs via nvidia passthrough
# so check for nvidia-smi to determine if GPU is available
if [ "$IS_WSL2" = true ]; then
    if available nvidia-smi && [ -n "$(nvidia-smi | grep -o "CUDA Version: [0-9]*\.[0-9]*")" ]; then
        status "Nvidia GPU detected."
    fi
    install_success
    exit 0
fi

# Install GPU dependencies on Linux
if ! available lspci && ! available lshw; then
    warning "Unable to detect NVIDIA/AMD GPU. Install lspci or lshw to automatically detect and install GPU dependencies."
    exit 0
fi

check_gpu() {
    # Look for devices based on vendor ID for NVIDIA and AMD
    case $1 in
        lspci)
            case $2 in
                nvidia) available lspci && lspci -d '10de:' | grep -q 'NVIDIA' || return 1 ;;
                amdgpu) available lspci && lspci -d '1002:' | grep -q 'AMD' || return 1 ;;
            esac ;;
        lshw)
            case $2 in
                nvidia) available lshw && $SUDO lshw -c display -numeric | grep -q 'vendor: .* \[10DE\]' || return 1 ;;
                amdgpu) available lshw && $SUDO lshw -c display -numeric | grep -q 'vendor: .* \[1002\]' || return 1 ;;
            esac ;;
        nvidia-smi) available nvidia-smi || return 1 ;;
    esac
}

if check_gpu nvidia-smi; then
    status "NVIDIA GPU installed."
    exit 0
fi

if ! check_gpu lspci nvidia && ! check_gpu lshw nvidia && ! check_gpu lspci amdgpu && ! check_gpu lshw amdgpu; then
    install_success
    warning "No NVIDIA/AMD GPU detected. Ollama will run in CPU-only mode."
    exit 0
fi

if check_gpu lspci amdgpu || check_gpu lshw amdgpu; then
    # Look for pre-existing ROCm v6 before downloading the dependencies
    for search in "${HIP_PATH:-''}" "${ROCM_PATH:-''}" "/opt/rocm" "/usr/lib64"; do
        if [ -n "${search}" ] && [ -e "${search}/libhipblas.so.2" -o -e "${search}/lib/libhipblas.so.2" ]; then
            status "Compatible AMD GPU ROCm library detected at ${search}"
            install_success
            exit 0
        fi
    done

    status "Downloading AMD GPU dependencies..."
    $SUDO rm -rf /usr/share/ollama/lib
    $SUDO chmod o+x /usr/share/ollama
    $SUDO install -o ollama -g ollama -m 755 -d /usr/share/ollama/lib/rocm
    curl --fail --show-error --location --progress-bar "https://ollama.com/download/ollama-linux-amd64-rocm.tgz${VER_PARAM}" \
        | $SUDO tar zx --owner ollama --group ollama -C /usr/share/ollama/lib/rocm .
    install_success
    status "AMD GPU ready."
    exit 0
fi

# ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#rhel-7-centos-7
# ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#rhel-8-rocky-8
# ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#rhel-9-rocky-9
# ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#fedora
install_cuda_driver_yum() {
    status 'Installing NVIDIA repository...'
    case $PACKAGE_MANAGER in
        yum)
            $SUDO $PACKAGE_MANAGER -y install yum-utils
            $SUDO $PACKAGE_MANAGER-config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m)/cuda-$1$2.repo
            ;;
        dnf)
            $SUDO $PACKAGE_MANAGER config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m)/cuda-$1$2.repo
            ;;
    esac

    case $1 in
        rhel)
            status 'Installing EPEL repository...'
            # EPEL is required for third-party dependencies such as dkms and libvdpau
            $SUDO $PACKAGE_MANAGER -y install https://dl.fedoraproject.org/pub/epel/epel-release-latest-$2.noarch.rpm || true
            ;;
    esac

    status 'Installing CUDA driver...'

    if [ "$1" = 'centos' ] || [ "$1$2" = 'rhel7' ]; then
        $SUDO $PACKAGE_MANAGER -y install nvidia-driver-latest-dkms
    fi

    $SUDO $PACKAGE_MANAGER -y install cuda-drivers
}

# ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#ubuntu
# ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#debian
install_cuda_driver_apt() {
    status 'Installing NVIDIA repository...'
    curl -fsSL -o $TEMP_DIR/cuda-keyring.deb https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m)/cuda-keyring_1.1-1_all.deb

    case $1 in
        debian)
            status 'Enabling contrib sources...'
            $SUDO sed 's/main/contrib/' < /etc/apt/sources.list | $SUDO tee /etc/apt/sources.list.d/contrib.list > /dev/null
            if [ -f "/etc/apt/sources.list.d/debian.sources" ]; then
                $SUDO sed 's/main/contrib/' < /etc/apt/sources.list.d/debian.sources | $SUDO tee /etc/apt/sources.list.d/contrib.sources > /dev/null
            fi
            ;;
    esac

    status 'Installing CUDA driver...'
    $SUDO dpkg -i $TEMP_DIR/cuda-keyring.deb
    $SUDO apt-get update

    [ -n "$SUDO" ] && SUDO_E="$SUDO -E" || SUDO_E=
    DEBIAN_FRONTEND=noninteractive $SUDO_E apt-get -y install cuda-drivers -q
}

if [ ! -f "/etc/os-release" ]; then
    error "Unknown distribution. Skipping CUDA installation."
fi

. /etc/os-release

OS_NAME=$ID
OS_VERSION=$VERSION_ID

PACKAGE_MANAGER=
for PACKAGE_MANAGER in dnf yum apt-get; do
    if available $PACKAGE_MANAGER; then
        break
    fi
done

if [ -z "$PACKAGE_MANAGER" ]; then
    error "Unknown package manager. Skipping CUDA installation."
fi

if ! check_gpu nvidia-smi || [ -z "$(nvidia-smi | grep -o "CUDA Version: [0-9]*\.[0-9]*")" ]; then
    case $OS_NAME in
        centos|rhel) install_cuda_driver_yum 'rhel' $(echo $OS_VERSION | cut -d '.' -f 1) ;;
        rocky) install_cuda_driver_yum 'rhel' $(echo $OS_VERSION | cut -c1) ;;
        fedora) [ $OS_VERSION -lt '37' ] && install_cuda_driver_yum $OS_NAME $OS_VERSION || install_cuda_driver_yum $OS_NAME '37';;
        amzn) install_cuda_driver_yum 'fedora' '37' ;;
        debian) install_cuda_driver_apt $OS_NAME $OS_VERSION ;;
        ubuntu) install_cuda_driver_apt $OS_NAME $(echo $OS_VERSION | sed 's/\.//') ;;
        *) exit ;;
    esac
fi

if ! lsmod | grep -q nvidia || ! lsmod | grep -q nvidia_uvm; then
    KERNEL_RELEASE="$(uname -r)"
    case $OS_NAME in
        rocky) $SUDO $PACKAGE_MANAGER -y install kernel-devel kernel-headers ;;
        centos|rhel|amzn) $SUDO $PACKAGE_MANAGER -y install kernel-devel-$KERNEL_RELEASE kernel-headers-$KERNEL_RELEASE ;;
        fedora) $SUDO $PACKAGE_MANAGER -y install kernel-devel-$KERNEL_RELEASE ;;
        debian|ubuntu) $SUDO apt-get -y install linux-headers-$KERNEL_RELEASE ;;
        *) exit ;;
    esac

    NVIDIA_CUDA_VERSION=$($SUDO dkms status | awk -F: '/added/ { print $1 }')
    if [ -n "$NVIDIA_CUDA_VERSION" ]; then
        $SUDO dkms install $NVIDIA_CUDA_VERSION
    fi

    if lsmod | grep -q nouveau; then
        status 'Reboot to complete NVIDIA CUDA driver install.'
        exit 0
    fi

    $SUDO modprobe nvidia
    $SUDO modprobe nvidia_uvm
fi

# make sure the NVIDIA modules are loaded on boot with nvidia-persistenced
if command -v nvidia-persistenced > /dev/null 2>&1; then
    $SUDO touch /etc/modules-load.d/nvidia.conf
    MODULES="nvidia nvidia-uvm"
    for MODULE in $MODULES; do
        if ! grep -qxF "$MODULE" /etc/modules-load.d/nvidia.conf; then
            echo "$MODULE" | sudo tee -a /etc/modules-load.d/nvidia.conf > /dev/null
        fi
    done
fi

status "NVIDIA GPU ready."
install_success

出现该内容说明Ollama已经安装完成

二、启动Nginx并部署Vue

启动nginx命令:systemctl start nginx.service
查看nginx状态:systemctl status nginx.service
关闭nginx命令:systemctl stop nginx.service

修改子配置文件,因为子配置文件内是写http的内容。
nginx服务所在地址为:/etc/nginx/sites-available
进入该目录编辑default文件:vim default

index index.html index.htm index.nginx-debian.html;

  # First attempt to serve request as file, then
        # as directory, then fall back to displaying a 404.
        try_files $uri $uri/ @router;
}

location @router {
        rewrite ^.*$ /index.html last;
}

如果你前端使用的是vue并且用了vue-router,那么就需要配置该代码,否则你进行router跳转的时候,就会出现404的问题。

三、启动Python脚本

进入存放python脚本的目录,运行命令:python xxx.py。运行脚本后,系统可能会提示有一些模块没有安装,按照提示安装即可。
命令:pip install module_name
其中可能有些脚本提示不对,比如:
ModuleNotFoundError: No module named 'docx'
如果出现这个问题,不能直接安装docx模块,而是应该安装python-docx。
将该安装的库全部安装后,进入放置python脚本的目录启动入口文件,短暂启动命令:python ai_analysis.py

持久后台运行命令:
nohup python ai_analysis.py /opt/app/llm_python/ai_analysis_project/log 2>&1

四、目前项目需要的库

使用MimiCPM需要的库,官方测试所用的环境:
Pillow10.1.0
torch
2.1.2 / 1.13.0(原本的库版本)
torchvision0.16.2 / 0.17.1(原本的库版本)
transformers
4.40.0
sentencepiece0.1.99
accelerate
0.30.1
bitsandbytes==0.43.1

AI分析所需要的库
langchain
langchain_community

分析文档所需要的库
pandasai
python-docx
fitz
faiss-gpu (conda install faiss-gpu -c pytorch)

  • 17
    点赞
  • 19
    收藏
    觉得还不错? 一键收藏
  • 6
    评论
大语言模型部署可以通过使用开源的大语言模型部署平台来实现。一个例子是OpenLLM,它是一个用于在生产环境中操作大型语言模型的开放平台。OpenLLM提供了一个标准的解决方案,可以将大语言模型部署到云端或本地,并且可以放心地用于生产环境中。它还提供了进一步的能力,让用户更加方便地基于大语言模型构建更强大的AI应用。通过使用OpenLLM,您可以轻松地微调、服务、部署和监控任何大语言模型。\[2\] 另外,为了开发公司自己的大语言模型,一种常见的方式是结合专业领域的训练数据和网上的开源大语言模型进行微调。这种方式相对于从零开始自研大语言模型来说,更加节省资源和金钱。因此,如果您的公司是一个小公司或者资源有限,这种方式可能更适合您。\[3\]希望这些信息能够给您提供一些关于大语言模型部署的思路。 #### 引用[.reference_title] - *1* *3* [如何部署属于自己的大语言模型](https://blog.csdn.net/weixin_39759781/article/details/130063164)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v91^insertT0,239^v3^insert_chatgpt"}} ] [.reference_item] - *2* [AIGC:大语言模型开放平台OpenLLM简介(提供简易的模型部署体验)](https://blog.csdn.net/zhanggqianglovec/article/details/131556821)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v91^insertT0,239^v3^insert_chatgpt"}} ] [.reference_item] [ .reference_list ]
评论 6
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值