Linux Centos 使用Ollama 部署DeepSeek 无GPU CPU也可部署

太阳和我肩并肩

1150人浏览 · 2025-02-26 16:43:00

太阳和我肩并肩 · 2025-02-26 16:43:00 发布

1、安装Ollama

Ollama是命令行界面（CLI），可以从命令行安装、运行和管理AI模型。

官网：Ollama

官网很慢，选择其他下载源：互链高科

1.1、手动安装

（下载Ollama(大约1.6G) 不知道为什么没成功，手动下载上传到服务器上的）

#下载Ollama(大约1.6G) 不知道为什么没成功，手动下载上传到服务器上的
wget http://61.133.217.142:20800/download/ollama/ollama-linux-amd64.tgz -o /usr/local/my/ollama/ollama-linux-amd64.tgz

下载地址：

ollama-linux-amd64.tgz

http://61.133.217.142:20800/download/ollama/ollama-linux-amd64.tgz?token=

install.sh(这个地址是原版install.sh，此处搭建使用改过的脚本，如下附件)

http://61.133.217.142:20800/download/ollama/install.sh?token=

install.sh脚本需要更改内容如下，可直接复制

#!/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 use 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

for BINDIR in /usr/local/bin /usr/bin /bin; do
    echo $PATH | grep -q $BINDIR && break || continue
done
OLLAMA_INSTALL_DIR=$(dirname ${BINDIR})

status "Installing ollama to $OLLAMA_INSTALL_DIR"
$SUDO install -o0 -g0 -m755 -d $BINDIR
$SUDO install -o0 -g0 -m755 -d "$OLLAMA_INSTALL_DIR"
status "Downloading Linux ${ARCH} bundle"
#    curl --fail --show-error --location --progress-bar \
#        "https://ollama.com/download/ollama-linux-${ARCH}.tgz${VER_PARAM}" | \
$SUDO tar -xzf ./ollama-linux-amd64.tgz -C "$OLLAMA_INSTALL_DIR"
BUNDLE=1
if [ "$OLLAMA_INSTALL_DIR/bin/ollama" != "$BINDIR/ollama" ] ; then
    status "Making ollama accessible in the PATH in $BINDIR"
    $SUDO ln -sf "$OLLAMA_INSTALL_DIR/ollama" "$BINDIR/ollama"
fi


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 -disable network | grep -q 'vendor: .* ' || return 1 ;;
                amdgpu) available lshw && $SUDO lshw -c display -numeric -disable network | grep -q 'vendor: .* ' || 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
    if [ $BUNDLE -ne 0 ]; then
        status "Downloading Linux ROCm ${ARCH} bundle"
        curl --fail --show-error --location --progress-bar \
            "https://ollama.com/download/ollama-linux-${ARCH}-rocm.tgz${VER_PARAM}" | \
            $SUDO tar -xzf - -C "$OLLAMA_INSTALL_DIR"

        install_success
        status "AMD GPU ready."
        exit 0
    fi
    # 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

CUDA_REPO_ERR_MSG="NVIDIA GPU detected, but your OS and Architecture are not supported by NVIDIA.  Please install the CUDA driver manually https://docs.nvidia.com/cuda/cuda-installation-guide-linux/"
# 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
            if curl -I --silent --fail --location "https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m | sed -e 's/aarch64/sbsa/')/cuda-$1$2.repo" >/dev/null ; then
                $SUDO $PACKAGE_MANAGER-config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m | sed -e 's/aarch64/sbsa/')/cuda-$1$2.repo
            else
                error $CUDA_REPO_ERR_MSG
            fi
            ;;
        dnf)
            if curl -I --silent --fail --location "https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m | sed -e 's/aarch64/sbsa/')/cuda-$1$2.repo" >/dev/null ; then
                $SUDO $PACKAGE_MANAGER config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m | sed -e 's/aarch64/sbsa/')/cuda-$1$2.repo
            else
                error $CUDA_REPO_ERR_MSG
            fi
            ;;
    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...'
    if curl -I --silent --fail --location "https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m | sed -e 's/aarch64/sbsa/')/cuda-keyring_1.1-1_all.deb" >/dev/null ; then
        curl -fsSL -o $TEMP_DIR/cuda-keyring.deb https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m | sed -e 's/aarch64/sbsa/')/cuda-keyring_1.1-1_all.deb
    else
        error $CUDA_REPO_ERR_MSG
    fi

    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 '39' ] && install_cuda_driver_yum $OS_NAME $OS_VERSION || install_cuda_driver_yum $OS_NAME '39';;
        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 available nvidia-persistenced; 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

1.2、将安装包和脚本放在同一目录

此处使用地址　/usr/local/my/ollama

为脚本增加执行权限

# 进入存放ollama目录
cd /usr/local/my/ollama

# 给脚本增加执行权限
chmod +x install.sh

1.3、安装ollama

# 安装ollama
./install.sh

# 此时如果提示【-bash: ./install.sh: /bin/sh^M: 坏的解释器: 没有那个文件或目录】，是因为：windows系统下换行符为 \r\n，linux下换行符为 \n

可以使用sed替换文件内容中多余的\r

# 替换文件种多余的\r
sed 's/\r//' -i xxx.sh

再重新执行安装命令./install.sh

最后的警告暂时不管

1.4、启动ollama

启动后什么都没有即代表启动成功

# 启动ollama
systemctl start ollama

亲测

改完模型存储路径 ollama list，模型都不见了！！！！！！！！！！！！！！！！！！！！！

所以先改存储路径，再下载模型吧！！！！！！

毕竟下载一次好慢好慢！！！！！！！

1.5、模型存储路径修改

默认的模型存储路径是 /usr/share/ollama/.ollama/models

此处修改为 /usr/local/my/ollama/models

# 1.停止Ollama服务
sudo systemctl stop ollama

# 2.给新目录赋权 读写
sudo chown -R root:root /usr/local/my/ollama/models
sudo chmod -R 775 /usr/local/my/ollama/models

# 3.修改Ollama服务配置文件
# 3.1编辑服务配置文件
vim /etc/systemd/system/ollama.service

# 3.2在[Service]部分的Environment字段后，添加新的Environment字段，指定新的模型路径
# Environment="OLLAMA_MODELS=/usr/local/my/ollama/models"
# 完整的示例如下：
# 添加完Esc -> :wq 保存退出
[Unit]
Description=Ollama Service
After=network-online.target


[Service]
ExecStart=/usr/local/bin/ollama serve
User=root
Group=root
Restart=always
RestartSec=3
Environment="PATH=/usr/local/another/java/jdk1.8.0_391/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/root/bin"
# 模型存储地址
Environment="OLLAMA_MODELS=/usr/local/my/ollama/models"
# 0.0.0.0的设置将允许远程访问
Environment="OLLAMA_HOST=0.0.0.0:11434"
# 允许所有来源的请求
Environment="OLLAMA_ORIGINS=*"


[Install]
WantedBy=default.targe

# 4.重新加载Ollama配置
# 4.1重新加载配置
sudo systemctl daemon-reload

# 4.2重启Ollama服务
sudo systemctl restart ollama.service

# 4.3查看服务状态
sudo systemctl status ollama

# 5.验证
# 5.1检查默认路径：
    进入默认的模型路径/usr/share/ollama/.ollama/models，会发现models文件夹已经消失。
# 5.2检查新路径：
    在新的路径/data/ollama/models下，会看到生成了blobs和manifests文件夹，这表明模型路径已经成功更改。

1.6、下载DeepSeek

下载过程有些漫长大约需要1-1.5个小时，下载大小4.7G左右

# 下载deepseek 此处下载7b版本
ollama run deepseek-r1:7b

显示success即为安装完成，安装完成默认启动

测试输入who are you

常用命令：

# 重新加载配置
sudo systemctl daemon-reload
# 重启ollama
sudo systemctl restart ollama   
# 查看日志
journalctl -u ollama -f
# 查看ollama环境变量
sudo systemctl show --property=Environment ollama.service

一直不能使用公网IP访问，防火墙开启11434端口放行

# 检查防火墙规则
firewall-cmd --list-ports

# 防火墙开放端口
firewall-cmd --zone=public --add-port=11434/tcp --permanent
# 加载防火墙配置
firewall-cmd --reload


# 防火墙关闭端口
firewall-cmd --zone=public --remove-port=11434/tcp --permanent
# 加载防火墙配置
firewall-cmd --reload

展示一下本地浏览器使用Page Assist访问远程服务器的Ollama，一定要配置自定义来源URL，并且最后不能带/，否则会403访问失败

也可以使用APiPost访问

API调用参考地址：https://github.com/ollama/ollama/blob/main/docs/api.md

2、卸载Ollama

（没试过，暂时先这样）

sudo systemctl stop ollama
sudo systemctl disable ollama
sudo rm /etc/systemd/system/ollama.service
sudo rm $(which ollama)
sudo rm -r /usr/share/ollama
sudo userdel ollama
sudo groupdel ollama