使用BitaHub部署DeepSeek-R1
2025 年 1 月 20 日,DeepSeek 发布并开源了最新的推理模型–DeepSeek-R1,性能比肩OpenAI-o1,同时还开源了 6 个R1小模型,使用从 DeepSeek-R1 蒸馏出来的知识去微调 Qwen、Llama,参数包含了1.5B、7B、 8B、14B、32B、70B,能够满足各种场景。
本次将使用BitaHub部署DeepSeek-R1-Distill,BitaHub是一个开放的Al和深度学习社区,GPU算力资源有4090、A100 等高性能显卡,提供了全流程的 AI 开发、训练、部署的专业环境。
接下来将手把手教你使用 bitahub 部署DeepSeek-R1-Distill。
注册 bitahub
bitahub 官网为https://www.bitahub.com/,点击右上角的登录按钮
点击注册
填写相关信息,然后点击立刻注册即可
对于新用户,可以免费获得 20 元的算力!
并且在活动期间(2025年1月22日到 2月14日),4090 价格超低,只需 1.2 元/小时,大概是全网性价比最高的平台了。
DeepSeek-R1-Distill 下载
注册并登录 bitahub 后,进入控制台
点击文件存储,这里用来创建文件系统,存放DeepSeek-R1-Distill 的模型文件
进入新创建的文件系统
现在该文件系统是空的,需要我们上传 deepseek 的模型文件
DeepSeek-R1-Distill-Qwen-1.5B 的下载地址为https://modelscope.cn/models/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B/files
在自己的电脑中ModelScope
pip install modelscope
然后通过下面的命令把模型文件下载到我们的电脑,然后再上传至 bitahub 的存储桶中
cd 模型存放的位置
modelscope download --model deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B --local_dir ./DeepSeek-R1-Distill-Qwen-1.5B
下载完毕
然后将文件夹DeepSeek-R1-Distill-Qwen-1.5B 上传到 bitahub
上传完成后,把DeepSeek-R1-Distill-Qwen-1.5B 添加到模型,点击菜单的模型
点击创建模型
然后输出模型的名称,文件来源选择刚才上传的文件夹
这样模型就创建好了,但是这里只是给模型文件创建一个映射,方便后续调用,并不是运行了这个模型
部署DeepSeek-R1-Distill
在 JupyterLab 中使用
点击菜单中的开发环境,然后点击创建
填写任务名称
然后挂载模型文件
这样进入容器的时候就能访问到模型文件了
然后选择镜像,点击使用平台镜像
选择镜像pytorch:2.3.1-cuda12.1-cudnn8-py310-ubuntu22.04
使用单卡 4090 就可以运行DeepSeek-R1-Distill-Qwen-1.5B 了,
访问方式使用 jupyterlab,也可以使用 ssh 搭配 vscode,参考教程地址https://www.bitahub.com/help/user-guide/training/develop/ssh。
运行时长根据自己的需求设置,时间到了会强制被关闭。
最后点击确认即可。
当任务状态为“运行中”,点击 jupyter 进入环境。如果任务状态为“ 等待“,则此时的资源正在调度中。
使用 ollama 部署
进入终端
以下命令为 ollama 官方提供的命令,会从 github 下载文件,但是由于众所周知的原因,下载速度非常慢
curl -fsSL https://ollama.com/install.sh | sh
所以使用下面的下载脚本
#!/bin/sh
# This script installs Ollama on Linux.
# It detects the current operating system architecture and installs the appropriate version of Ollama.
set -eu
red="$( (/usr/bin/tput bold || :; /usr/bin/tput setaf 1 || :) 2>&-)"
plain="$( (/usr/bin/tput sgr0 || :) 2>&-)"
status() { echo ">>> $*" >&2; }
error() { echo "${red}ERROR:${plain} $*"; exit 1; }
warning() { echo "${red}WARNING:${plain} $*"; }
TEMP_DIR=$(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 ${BINDIR})
if [ -d "$OLLAMA_INSTALL_DIR/lib/ollama" ] ; then
status "Cleaning up old version at $OLLAMA_INSTALL_DIR/lib/ollama"
$SUDO rm -rf "$OLLAMA_INSTALL_DIR/lib/ollama"
fi
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://gh-proxy.com/github.com/ollama/ollama/releases/download/v0.5.7/ollama-linux-arm64.tgz" | \
$SUDO tar -xzf - -C "$OLLAMA_INSTALL_DIR"
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
# Check for NVIDIA JetPack systems with additional downloads
if [ -f /etc/nv_tegra_release ] ; then
if grep R36 /etc/nv_tegra_release > /dev/null ; then
status "Downloading JetPack 6 components"
curl --fail --show-error --location --progress-bar \
"https://gh-proxy.com/github.com/ollama/ollama/releases/download/v0.5.7/ollama-linux-arm64-jetpack6.tgz" | \
$SUDO tar -xzf - -C "$OLLAMA_INSTALL_DIR"
elif grep R35 /etc/nv_tegra_release > /dev/null ; then
status "Downloading JetPack 5 components"
curl --fail --show-error --location --progress-bar \
"https://gh-proxy.com/github.com/ollama/ollama/releases/download/v0.5.7/ollama-linux-arm64-jetpack5.tgz" | \
$SUDO tar -xzf - -C "$OLLAMA_INSTALL_DIR"
else
warning "Unsupported JetPack version detected. GPU may not be supported"
fi
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() { $SUDO systemctl restart ollama; }
trap start_service EXIT
;;
*)
warning "systemd is not running"
if [ "$IS_WSL2" = true ]; then
warning "see https://learn.microsoft.com/en-us/windows/wsl/systemd#how-to-enable-systemd to enable it"
fi
;;
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
# Don't attempt to install drivers on Jetson systems
if [ -f /etc/nv_tegra_release ] ; then
status "NVIDIA JetPack ready."
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: .* \[10DE\]' || 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; 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
status "Downloading Linux ROCm ${ARCH} bundle"
curl --fail --show-error --location --progress-bar \
"https://gh-proxy.com/github.com/ollama/ollama/releases/download/v0.5.7/ollama-linux-amd64-rocm.tgz" | \
$SUDO tar -xzf - -C "$OLLAMA_INSTALL_DIR"
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
在/workspace 下新建文件 install.sh
把下载脚本粘贴进去
执行命令
chmod +x install.sh
./install.sh
启动 ollama
ollama serve
运行 DeepSeek-R1-Distill-Qwen-1.5B(ollama run 的时候会先把模型文件下载)
ollama run deepseek-r1:1.5b
使用 vllm 部署
终端中运行命令
pip install vllm
安装完毕后验证是否安装成功,运行命令
vllm -v
显示这个就按照成功了
运行以下命令,部署 deepseek
vllm serve /model/DeepSeek-R1-Distill-Qwen-1.5B
出现这个就是运行成功了
测试模型返回,运行以下命令
curl http://localhost:8000/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "/model/DeepSeek-R1-Distill-Qwen-1.5B",
"messages": [
{"role": "system", "content": "你是一名数学家"},
{"role": "user", "content": "请计算1+1=?"}
]
}'
模型返回的输出
但是现在这个接口只能在本地使用,如果要公网使用,还需要进行内网穿透。
所以 bitahub 提供了专门的模型部署服务,可以在公网访问,参考链接https://www.bitahub.com/help/user-guide/inferenceService/onlineReasoning/createSingleServiceOnlineReasoning
bitahub 的模型部署服务是Serverless,即只有使用的时候扣费,极大降低了成本。举个例子,部署了一个图像分类模型,一种方案是专门开一台服务器,假设最小收费单位是小时,如果运行一天,那么就需要花费 24 小时对应的价格,但并不是 24 小时的每时每刻都有用户在使用这个接口,这些无人使用时的服务器成本需要我们自己承担。但使用 bitahub 的模型部署服务就不一样了,当后台监测到没有服务请求时,自动释放资源,释放后不扣钱,当有请求发起时,后台自动启动模型,用户可以正常使用接口,在没有使用的这个空档期,无需我们支付费用。
让 deepseek 总结一下 bitahub 的优势
点击存为镜像方便后续使用
使用 bitahub 的模型部署服务
单击 模型部署中的应用管理,然后点击创建应用
按要求填写应用基础信息
应用信息中的输入类型选择模型
选择模型
部署信息,端口填 8000(vllm 的默认端口),部署镜像选择私有镜像(前面保存的 vllm 镜像)
启动命令填写
vllm serve /model/DeepSeek-R1-Distill-Qwen-1.5B
最后点击确认。
然后点击在线推理中的部署
按照下面的内容填写,服务名称、服务地址可以随便写
API 认证(按自己需求选择,如果关就所有人可以访问),支持副本数为 0(没有服务请求时进入休眠,该时间不收费)
最后点击确定。
当出现这些内容的时候就表示部署成功了
部署的服务的访问接口
测试服务访问
curl https://www.bitahub.com/inf-app/xxxxxxx/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "/model/DeepSeek-R1-Distill-Qwen-1.5B",
"messages": [
{"role": "system", "content": "你是一名数学家"},
{"role": "user", "content": "请计算1+1=?"}
]
}'
测试通过