添加 vllm.sh

vllm.sh

@@ -0,0 +1,95 @@
+#!/bin/bash
+
+# vLLM Docker一键安装脚本
+# 功能：自动安装Docker, NVIDIA驱动和容器工具包，并部署vLLM服务
+
+set -e
+
+# 检查是否为root用户
+if [ "$(id -u)" -ne 0 ]; then
+    echo "请使用root用户或通过sudo运行此脚本"
+    exit 1
+fi
+
+# 获取GPU数量
+read -p "请输入要使用的GPU数量 (例如: 1): " GPU_COUNT
+if ! [[ "$GPU_COUNT" =~ ^[1-9][0-9]*$ ]]; then
+    echo "错误: 请输入有效的数字"
+    exit 1
+fi
+
+# 获取模型名称
+read -p "请输入要下载的模型名称 (例如: meta-llama/Llama-2-7b-chat-hf): " MODEL_NAME
+if [ -z "$MODEL_NAME" ]; then
+    echo "错误: 模型名称不能为空"
+    exit 1
+fi
+
+# 检查NVIDIA显卡
+echo "检查NVIDIA显卡..."
+if ! lspci | grep -i nvidia > /dev/null; then
+    echo "未检测到NVIDIA显卡!"
+    exit 1
+fi
+
+# 安装基础依赖
+echo "安装基础依赖..."
+apt-get update
+apt-get install -y curl apt-transport-https ca-certificates software-properties-common
+
+# 安装NVIDIA驱动
+echo "检查NVIDIA驱动..."
+if ! nvidia-smi &> /dev/null; then
+    echo "安装NVIDIA驱动..."
+    add-apt-repository -y ppa:graphics-drivers/ppa
+    apt-get update
+    apt-get install -y ubuntu-drivers-common
+    ubuntu-drivers autoinstall
+    echo "NVIDIA驱动安装完成，需要重启。"
+    echo "请重启后再次运行此脚本继续安装。"
+    exit 0
+fi
+
+# 安装Docker
+echo "检查Docker..."
+if ! command -v docker &> /dev/null; then
+    echo "安装Docker..."
+    curl -fsSL https://download.docker.com/linux/ubuntu/gpg | apt-key add -
+    add-apt-repository -y "deb [arch=amd64] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable"
+    apt-get update
+    apt-get install -y docker-ce docker-ce-cli containerd.io
+    systemctl enable --now docker
+fi
+
+# 安装NVIDIA Container Toolkit
+echo "检查NVIDIA Container Toolkit..."
+if ! dpkg -s nvidia-container-toolkit &> /dev/null; then
+    echo "安装NVIDIA Container Toolkit..."
+    distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
+    curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | apt-key add -
+    curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | tee /etc/apt/sources.list.d/nvidia-docker.list
+    apt-get update
+    apt-get install -y nvidia-container-toolkit
+    systemctl restart docker
+fi
+
+# 创建vLLM服务
+echo "部署vLLM容器..."
+docker run -d --gpus all \
+       --shm-size=1g \
+       --ulimit memlock=-1 \
+       --ulimit stack=67108864 \
+       -e NCCL_IGNORE_DISABLED_P2P=1 \
+       -p 8000:8000 \
+       --name vllm_service \
+       --restart always \
+       -v $HOME/.cache/huggingface:/root/.cache/huggingface \
+       ghcr.io/vllm/vllm:latest \
+       --model $MODEL_NAME \
+       --tensor-parallel-size $GPU_COUNT \
+       --host 0.0.0.0 \
+       --port 8000
+
+echo "vLLM服务已成功部署!"
+echo "访问地址: http://localhost:8000"
+echo "您可以使用以下命令查看日志: docker logs -f vllm_service"