这篇文章主要分享两方面内容:
1)在纯内网环境下如何部署ollama
2)在纯内网环境下如何配置大模型
话不多说直接开始。
①离线部署ollama
一、通过浏览器访问ollama官方安装脚本,获取脚本内容。复制里面的内容。
在Linux中执行vi install.sh,将复制的内容粘贴进去。
https://ollama.com/install.shhttps://ollama.com/install.sh
二、修改install.sh安装脚本,下面是完整的脚本,也可以忽略第一步直接复制这里的内容写入install.sh。这里主要改动的地方是联网获取ollama的部分为从本地获取。
#!/bin/sh
# This script installs Ollama on Linux.
# It detects the current operating system architecture and installs the appropriate version of Ollama.set -eustatus() { echo ">>> $*" >&2; }
error() { echo "ERROR $*"; exit 1; }
warning() { echo "WARNING: $*"; }TEMP_DIR=$(mktemp -d)
cleanup() { rm -rf $TEMP_DIR; }
trap cleanup EXITavailable() { command -v $1 >/dev/null; }
require() {local MISSING=''for TOOL in $*; doif ! available $TOOL; thenMISSING="$MISSING $TOOL"fidoneecho $MISSING
}[ "$(uname -s)" = "Linux" ] || error 'This script is intended to run on Linux only.'ARCH=$(uname -m)
case "$ARCH" inx86_64) ARCH="amd64" ;;aarch64|arm64) ARCH="arm64" ;;*) error "Unsupported architecture: $ARCH" ;;
esacIS_WSL2=falseKERN=$(uname -r)
case "$KERN" in*icrosoft*WSL2 | *icrosoft*wsl2) IS_WSL2=true;;*icrosoft) error "Microsoft WSL1 is not currently supported. Please use WSL2 with 'wsl --set-version <distro> 2'" ;;*) ;;
esacVER_PARAM="${OLLAMA_VERSION:+?version=$OLLAMA_VERSION}"SUDO=
if [ "$(id -u)" -ne 0 ]; then# Running as root, no need for sudoif ! available sudo; thenerror "This script requires superuser permissions. Please re-run as root."fiSUDO="sudo"
fiNEEDS=$(require curl awk grep sed tee xargs)
if [ -n "$NEEDS" ]; thenstatus "ERROR: The following tools are required but missing:"for NEED in $NEEDS; doecho " - $NEED"doneexit 1
fifor BINDIR in /usr/local/bin /usr/bin /bin; doecho $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"
#if curl -I --silent --fail --location "https://ollama.com/download/ollama-linux-${ARCH}.tgz${VER_PARAM}" >/dev/null ; then
#注释掉以下代码
# status "Downloading Linux ${ARCH} bundle"
# curl --fail --show-error --location --progress-bar \
# "https://ollama.com/download/ollama-linux-${ARCH}.tgz${VER_PARAM}" | \
# $SUDO tar -xzf - -C "$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
#else
# status "Downloading Linux ${ARCH} CLI"
# curl --fail --show-error --location --progress-bar -o "$TEMP_DIR/ollama"\
# "https://ollama.com/download/ollama-linux-${ARCH}${VER_PARAM}"
# $SUDO install -o0 -g0 -m755 $TEMP_DIR/ollama $OLLAMA_INSTALL_DIR/ollama
# BUNDLE=0
# if [ "$OLLAMA_INSTALL_DIR/ollama" != "$BINDIR/ollama" ] ; then
# status "Making ollama accessible in the PATH in $BINDIR"
# $SUDO ln -sf "$OLLAMA_INSTALL_DIR/ollama" "$BINDIR/ollama"
# fi
#fi
#新增以下代码
LOCAL_OLLAMA_TGZ="./ollama-linux-${ARCH}.tgz${VER_PARAM}"
if [ -f "$LOCAL_OLLAMA_TGZ" ]; thenstatus "Installing from local file $LOCAL_OLLAMA_TGZ"$SUDO tar -xzf "$LOCAL_OLLAMA_TGZ" -C "$OLLAMA_INSTALL_DIR"BUNDLE=1if [ ! -e "$BINDIR/ollama" ]; thenstatus "Making ollama accessible in the PATH in $BINDIR"$SUDO ln -sf "$OLLAMA_INSTALL_DIR/ollama" "$BINDIR/ollama"fi
elseecho "Error: The local file $LOCAL_OLLAMA_TGZ does not exist."exit 1
fiinstall_success() {status 'The Ollama API is now available at 127.0.0.1:11434.'status 'Install complete. Run "ollama" from the command line.'
}
trap install_success EXIT# Everything from this point onwards is optional.configure_systemd() {if ! id ollama >/dev/null 2>&1; thenstatus "Creating ollama user..."$SUDO useradd -r -s /bin/false -U -m -d /usr/share/ollama ollamafiif getent group render >/dev/null 2>&1; thenstatus "Adding ollama user to render group..."$SUDO usermod -a -G render ollamafiif getent group video >/dev/null 2>&1; thenstatus "Adding ollama user to video group..."$SUDO usermod -a -G video ollamafistatus "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=$PATH"[Install]
WantedBy=default.target
EOFSYSTEMCTL_RUNNING="$(systemctl is-system-running || true)"case $SYSTEMCTL_RUNNING inrunning|degraded)status "Enabling and starting ollama service..."$SUDO systemctl daemon-reload$SUDO systemctl enable ollamastart_service() { $SUDO systemctl restart ollama; }trap start_service EXIT;;esac
}if available systemctl; thenconfigure_systemd
fi# WSL2 only supports GPUs via nvidia passthrough
# so check for nvidia-smi to determine if GPU is available
if [ "$IS_WSL2" = true ]; thenif available nvidia-smi && [ -n "$(nvidia-smi | grep -o "CUDA Version: [0-9]*\.[0-9]*")" ]; thenstatus "Nvidia GPU detected."fiinstall_successexit 0
fi# Install GPU dependencies on Linux
if ! available lspci && ! available lshw; thenwarning "Unable to detect NVIDIA/AMD GPU. Install lspci or lshw to automatically detect and install GPU dependencies."exit 0
ficheck_gpu() {# Look for devices based on vendor ID for NVIDIA and AMDcase $1 inlspci)case $2 innvidia) 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 innvidia) available lshw && $SUDO lshw -c display -numeric -disable network | grep -q 'vendor: .* \[10DE\]' || return 1 ;;amdgpu) available lshw && $SUDO lshw -c display -numeric -disable network | grep -q 'vendor: .* \[1002\]' || return 1 ;;esac ;;nvidia-smi) available nvidia-smi || return 1 ;;esac
}if check_gpu nvidia-smi; thenstatus "NVIDIA GPU installed."exit 0
fiif ! check_gpu lspci nvidia && ! check_gpu lshw nvidia && ! check_gpu lspci amdgpu && ! check_gpu lshw amdgpu; theninstall_successwarning "No NVIDIA/AMD GPU detected. Ollama will run in CPU-only mode."exit 0
fiif check_gpu lspci amdgpu || check_gpu lshw amdgpu; thenif [ $BUNDLE -ne 0 ]; thenstatus "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_successstatus "AMD GPU ready."exit 0fi# Look for pre-existing ROCm v6 before downloading the dependenciesfor search in "${HIP_PATH:-''}" "${ROCM_PATH:-''}" "/opt/rocm" "/usr/lib64"; doif [ -n "${search}" ] && [ -e "${search}/libhipblas.so.2" -o -e "${search}/lib/libhipblas.so.2" ]; thenstatus "Compatible AMD GPU ROCm library detected at ${search}"install_successexit 0fidonestatus "Downloading AMD GPU dependencies..."$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/rocmcurl --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_successstatus "AMD GPU ready."exit 0
fiCUDA_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 $PACKAGE_MANAGER inyum)$SUDO $PACKAGE_MANAGER -y install yum-utilsif 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.repoelseerror $CUDA_REPO_ERR_MSGfi;;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.repoelseerror $CUDA_REPO_ERR_MSGfi;;esaccase $1 inrhel)status 'Installing EPEL repository...'# EPEL is required for third-party dependencies such as dkms and libvdpau$SUDO $PACKAGE_MANAGER -y install https://dl.fedoraproject.org/pub/epel/epel-release-latest-$2.noarch.rpm || true;;esacstatus 'Installing CUDA driver...'if [ "$1" = 'centos' ] || [ "$1$2" = 'rhel7' ]; then$SUDO $PACKAGE_MANAGER -y install nvidia-driver-latest-dkmsfi$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 ; thencurl -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.debelseerror $CUDA_REPO_ERR_MSGficase $1 indebian)status 'Enabling contrib sources...'$SUDO sed 's/main/contrib/' < /etc/apt/sources.list | $SUDO tee /etc/apt/sources.list.d/contrib.list > /dev/nullif [ -f "/etc/apt/sources.list.d/debian.sources" ]; then$SUDO sed 's/main/contrib/' < /etc/apt/sources.list.d/debian.sources | $SUDO tee /etc/apt/sources.list.d/contrib.sources > /dev/nullfi;;esacstatus 'Installing CUDA driver...'$SUDO dpkg -i $TEMP_DIR/cuda-keyring.deb$SUDO apt-get update[ -n "$SUDO" ] && SUDO_E="$SUDO -E" || SUDO_E=DEBIAN_FRONTEND=noninteractive $SUDO_E apt-get -y install cuda-drivers -q
}if [ ! -f "/etc/os-release" ]; thenerror "Unknown distribution. Skipping CUDA installation."
fi. /etc/os-releaseOS_NAME=$ID
OS_VERSION=$VERSION_IDPACKAGE_MANAGER=
for PACKAGE_MANAGER in dnf yum apt-get; doif available $PACKAGE_MANAGER; thenbreakfi
doneif [ -z "$PACKAGE_MANAGER" ]; thenerror "Unknown package manager. Skipping CUDA installation."
fiif ! check_gpu nvidia-smi || [ -z "$(nvidia-smi | grep -o "CUDA Version: [0-9]*\.[0-9]*")" ]; thencase $OS_NAME incentos|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 $OS_VERSION | sed 's/\.//') ;;*) exit ;;esac
fiif ! lsmod | grep -q nvidia || ! lsmod | grep -q nvidia_uvm; thenKERNEL_RELEASE="$(uname -r)"case $OS_NAME inrocky) $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 ;;esacNVIDIA_CUDA_VERSION=$($SUDO dkms status | awk -F: '/added/ { print $1 }')if [ -n "$NVIDIA_CUDA_VERSION" ]; then$SUDO dkms install $NVIDIA_CUDA_VERSIONfiif lsmod | grep -q nouveau; thenstatus 'Reboot to complete NVIDIA CUDA driver install.'exit 0fi$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.confMODULES="nvidia nvidia-uvm"for MODULE in $MODULES; doif ! grep -qxF "$MODULE" /etc/modules-load.d/nvidia.conf; thenecho "$MODULE" | $SUDO tee -a /etc/modules-load.d/nvidia.conf > /dev/nullfidone
fistatus "NVIDIA GPU ready."
install_success
三、下载ollama安装包
下载地址:https://github.com/ollama/ollama/releases/下载对应的包
具体需要什么型号的可通过 lscpu 命令 查看自己的cpu架构
x86_64 CPU 选择下载 ollama-linux-amd64.tgz aarch64
arm64 CPU 选择下载 ollama-linux-arm64.tgz
四、运行install.sh脚本进行安装
进入install.sh所在目录
chmod +x install.sh #给脚本赋予执行权限
./install.sh
# 如果报错误: bash: ./build_android.sh:/bin/sh^M:解释器错误: 没有那个文件或目录,执行
sed -i 's/\r$//' install.sh
②离线安装大模型
因为我们的服务器是完全内网环境,所以即便安装ollama后也无法下载大模型,因此需要我们手动将模型放到ollama可以识别的地方。
默认情况下ollama模型的所在路径为:
macOS: ~/.ollama/models
Linux: **/usr/share/ollama/.ollama/models**
Windows: C:Users<username>.ollamamodels
自己在服务器上创建一个路径,打开ollama配置文件/etc/systemd/system/ollama.service
在里面加入你新创建的路径
接下来,找一个可以上网的主机,执行ollama run ***,当大模型下载完成后,找到models目录,将整个目录拷贝到服务器你新创建的路径下。
重启ollama,之后再执行ollama list命令,如果看到有模型了,证明搞定。