本地shadowsocks修改为国内镜像方案

This commit is contained in:
2026-06-03 16:33:45 +08:00
parent e95ccb6d05
commit 093da7722a
2 changed files with 25 additions and 31 deletions
+21 -19
View File
@@ -2,6 +2,7 @@
# MinerU on ROCm 7.2.1 Docker Image # MinerU on ROCm 7.2.1 Docker Image
# 原生 Linux + Ubuntu 24.04 + ROCm 7.2.1 + PyTorch 2.11.0 + vllm + MinerU 3.2.0 # 原生 Linux + Ubuntu 24.04 + ROCm 7.2.1 + PyTorch 2.11.0 + vllm + MinerU 3.2.0
# #
# 国内网络优化版:Ubuntu/PyPI/GitHub 全部使用国内镜像
# 构建前请根据你的 GPU 修改 ARCH 参数(默认 gfx1201 = RX 9070) # 构建前请根据你的 GPU 修改 ARCH 参数(默认 gfx1201 = RX 9070)
# ============================================================================= # =============================================================================
@@ -14,10 +15,11 @@ ARG PYTHON_VER=3.12
ARG VENV=/opt/mineru_venv ARG VENV=/opt/mineru_venv
ARG TORCH_INDEX=https://download.pytorch.org/whl/rocm7.2 ARG TORCH_INDEX=https://download.pytorch.org/whl/rocm7.2
# -- 代理设置(国内构建必需)------------------------------------------------ # -- 国内镜像配置 -----------------------------------------------------------
ARG HTTP_PROXY # GitHub 加速(ghproxy.com)
ARG HTTPS_PROXY ARG GH_PROXY=https://ghproxy.com/
ARG NO_PROXY=localhost,127.0.0.1 # PyPI 镜像
ARG PIP_INDEX=https://pypi.tuna.tsinghua.edu.cn/simple
# -- 环境变量 --------------------------------------------------------------- # -- 环境变量 ---------------------------------------------------------------
ENV DEBIAN_FRONTEND=noninteractive \ ENV DEBIAN_FRONTEND=noninteractive \
@@ -27,13 +29,7 @@ ENV DEBIAN_FRONTEND=noninteractive \
MINERU_MODEL_SOURCE=huggingface \ MINERU_MODEL_SOURCE=huggingface \
TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1 \ TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1 \
HSA_ENABLE_SDMA=1 \ HSA_ENABLE_SDMA=1 \
VLLM_TARGET_DEVICE=rocm \ VLLM_TARGET_DEVICE=rocm
HTTP_PROXY=${HTTP_PROXY} \
HTTPS_PROXY=${HTTPS_PROXY} \
NO_PROXY=${NO_PROXY} \
http_proxy=${HTTP_PROXY} \
https_proxy=${HTTPS_PROXY} \
no_proxy=${NO_PROXY}
WORKDIR /opt WORKDIR /opt
@@ -43,12 +39,9 @@ WORKDIR /opt
# Ubuntu 24.04 使用 deb822 格式,默认源文件是 /etc/apt/sources.list.d/ubuntu.sources # Ubuntu 24.04 使用 deb822 格式,默认源文件是 /etc/apt/sources.list.d/ubuntu.sources
RUN sed -i 's|http://.*archive.ubuntu.com|http://mirrors.tuna.tsinghua.edu.cn|g' /etc/apt/sources.list.d/ubuntu.sources && \ RUN sed -i 's|http://.*archive.ubuntu.com|http://mirrors.tuna.tsinghua.edu.cn|g' /etc/apt/sources.list.d/ubuntu.sources && \
sed -i 's|http://.*security.ubuntu.com|http://mirrors.tuna.tsinghua.edu.cn|g' /etc/apt/sources.list.d/ubuntu.sources && \ sed -i 's|http://.*security.ubuntu.com|http://mirrors.tuna.tsinghua.edu.cn|g' /etc/apt/sources.list.d/ubuntu.sources && \
# 如果设置了代理,配置 apt 走代理
([ -n "$HTTP_PROXY" ] && echo "Acquire::http::Proxy \"$HTTP_PROXY\";" > /etc/apt/apt.conf.d/99proxy) || true && \
([ -n "$HTTPS_PROXY" ] && echo "Acquire::https::Proxy \"$HTTPS_PROXY\";" >> /etc/apt/apt.conf.d/99proxy) || true && \
apt-get update && apt-get install -y --no-install-recommends \ apt-get update && apt-get install -y --no-install-recommends \
wget curl ca-certificates gnupg software-properties-common && \ wget curl ca-certificates gnupg software-properties-common && \
# 添加 AMD ROCm 仓库 # 添加 AMD ROCm 仓库(repo.radeon.com 通常国内可直连)
wget -q https://repo.radeon.com/rocm/rocm.gpg.key -O - | \ wget -q https://repo.radeon.com/rocm/rocm.gpg.key -O - | \
gpg --dearmor | tee /etc/apt/trusted.gpg.d/rocm.gpg > /dev/null && \ gpg --dearmor | tee /etc/apt/trusted.gpg.d/rocm.gpg > /dev/null && \
echo 'deb [arch=amd64] https://repo.radeon.com/rocm/apt/7.2.1 noble main' \ echo 'deb [arch=amd64] https://repo.radeon.com/rocm/apt/7.2.1 noble main' \
@@ -101,7 +94,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
# 阶段 4:CMake 4.0(vllm 要求 ≥ 4.0,Ubuntu 24.04 自带 3.28 不够) # 阶段 4:CMake 4.0(vllm 要求 ≥ 4.0,Ubuntu 24.04 自带 3.28 不够)
# =========================================================================== # ===========================================================================
RUN cd /tmp && \ RUN cd /tmp && \
wget -q https://github.com/Kitware/CMake/releases/download/v4.0.0/cmake-4.0.0-linux-x86_64.tar.gz && \ wget -q ${GH_PROXY}https://github.com/Kitware/CMake/releases/download/v4.0.0/cmake-4.0.0-linux-x86_64.tar.gz && \
tar -xzf cmake-4.0.0-linux-x86_64.tar.gz && \ tar -xzf cmake-4.0.0-linux-x86_64.tar.gz && \
cp -r cmake-4.0.0-linux-x86_64/bin/* /usr/local/bin/ && \ cp -r cmake-4.0.0-linux-x86_64/bin/* /usr/local/bin/ && \
cp -r cmake-4.0.0-linux-x86_64/share/* /usr/local/share/ && \ cp -r cmake-4.0.0-linux-x86_64/share/* /usr/local/share/ && \
@@ -112,8 +105,12 @@ RUN cd /tmp && \
# 阶段 5:Python 虚拟环境 + PyTorch ROCm # 阶段 5:Python 虚拟环境 + PyTorch ROCm
# =========================================================================== # ===========================================================================
RUN python${PYTHON_VER} -m venv ${VENV} && \ RUN python${PYTHON_VER} -m venv ${VENV} && \
# 配置 pip 国内镜像
mkdir -p /root/.pip && \
echo "[global]" > /root/.pip/pip.conf && \
echo "index-url = ${PIP_INDEX}" >> /root/.pip/pip.conf && \
${VENV}/bin/pip install --no-cache-dir -U pip setuptools wheel && \ ${VENV}/bin/pip install --no-cache-dir -U pip setuptools wheel && \
# 安装 PyTorch ROCm 版(锁定 2.11,≥ 2.12 在部分环境下有 rocprofiler 问题) # 安装 PyTorch ROCm 版(指定 index-url 覆盖全局镜像)
${VENV}/bin/pip install --no-cache-dir --pre \ ${VENV}/bin/pip install --no-cache-dir --pre \
torch==2.11.0+rocm7.2 \ torch==2.11.0+rocm7.2 \
torchvision \ torchvision \
@@ -132,9 +129,11 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
apt-get clean && rm -rf /var/lib/apt/lists/* apt-get clean && rm -rf /var/lib/apt/lists/*
# =========================================================================== # ===========================================================================
# 阶段 7:amd-aiter + flash_attn # 阶段 7:amd-aiter + flash_attn(GitHub 通过 ghproxy 加速)
# =========================================================================== # ===========================================================================
RUN set -ex && \ RUN set -ex && \
# 配置 git 走 ghproxy
git config --global url."${GH_PROXY}https://github.com/".insteadOf "https://github.com/" && \
# aiter(AMD 优化的 attention 算子) # aiter(AMD 优化的 attention 算子)
cd /opt && git clone --recursive --depth 1 https://github.com/ROCm/aiter.git && \ cd /opt && git clone --recursive --depth 1 https://github.com/ROCm/aiter.git && \
${VENV}/bin/pip install --no-cache-dir -e /opt/aiter && \ ${VENV}/bin/pip install --no-cache-dir -e /opt/aiter && \
@@ -149,6 +148,8 @@ RUN set -ex && \
# 阶段 8:编译 vllm # 阶段 8:编译 vllm
# =========================================================================== # ===========================================================================
RUN set -ex && \ RUN set -ex && \
# 配置 git 走 ghproxy(新 RUN 层需重新配置)
git config --global url."${GH_PROXY}https://github.com/".insteadOf "https://github.com/" && \
# setuptools 升级(PEP 639 兼容) # setuptools 升级(PEP 639 兼容)
${VENV}/bin/pip install --no-cache-dir -U \ ${VENV}/bin/pip install --no-cache-dir -U \
"setuptools>=77.0.3" setuptools_scm setuptools_rust wheel && \ "setuptools>=77.0.3" setuptools_scm setuptools_rust wheel && \
@@ -172,7 +173,7 @@ RUN set -ex && \
cd /opt/vllm_build && ninja -j8 && \ cd /opt/vllm_build && ninja -j8 && \
# 安装 .so 到 vllm 源码目录 # 安装 .so 到 vllm 源码目录
cp /opt/vllm_build/*.abi3.so /opt/vllm/vllm/ && \ cp /opt/vllm_build/*.abi3.so /opt/vllm/vllm/ && \
# pip install vllm(让 pip 解析运行时依赖:xgrammar, compressed_tensors 等) # pip install vllm(让 pip 解析运行时依赖)
cd /opt/vllm && ${VENV}/bin/pip install --no-cache-dir -e . --no-build-isolation && \ cd /opt/vllm && ${VENV}/bin/pip install --no-cache-dir -e . --no-build-isolation && \
# 验证 PyTorch 没被 vllm 依赖覆盖 # 验证 PyTorch 没被 vllm 依赖覆盖
${VENV}/bin/python -c "import torch; v=torch.__version__; assert 'rocm' in v, f'PyTorch overwritten by vllm deps: {v}'; print('PyTorch OK:', v)" && \ ${VENV}/bin/python -c "import torch; v=torch.__version__; assert 'rocm' in v, f'PyTorch overwritten by vllm deps: {v}'; print('PyTorch OK:', v)" && \
@@ -196,6 +197,7 @@ COPY scripts/cache_warmer.py /opt/cache_warmer.py
# 阶段 9:安装 MinerU + RDNA 适配补丁 # 阶段 9:安装 MinerU + RDNA 适配补丁
# =========================================================================== # ===========================================================================
RUN set -ex && \ RUN set -ex && \
# pip 国内镜像已在阶段 5 全局配置
${VENV}/bin/pip install --no-cache-dir 'mineru[core]' && \ ${VENV}/bin/pip install --no-cache-dir 'mineru[core]' && \
# 验证 PyTorch 没被覆盖 # 验证 PyTorch 没被覆盖
${VENV}/bin/python -c "import torch; v=torch.__version__; assert 'rocm' in v, f'PyTorch overwritten: {v}'; print('PyTorch OK:', v)" && \ ${VENV}/bin/python -c "import torch; v=torch.__version__; assert 'rocm' in v, f'PyTorch overwritten: {v}'; print('PyTorch OK:', v)" && \
+4 -12
View File
@@ -9,7 +9,6 @@ services:
build: build:
context: . context: .
dockerfile: Dockerfile dockerfile: Dockerfile
network: host # 构建时走宿主机网络(国内访问 ROCm 源需要)
args: args:
# ---- 按你的 GPU 修改 ---- # ---- 按你的 GPU 修改 ----
# gfx1201 = RX 9070 / 9070 XT / 9070 GRE # gfx1201 = RX 9070 / 9070 XT / 9070 GRE
@@ -18,9 +17,10 @@ services:
# gfx1101 = RX 7800 XT / 7700 XT # gfx1101 = RX 7800 XT / 7700 XT
# gfx1030 = RX 6950 / 6900 / 6800 系列 # gfx1030 = RX 6950 / 6900 / 6800 系列
ARCH: gfx1201 ARCH: gfx1201
# ---- 代理(国内必需)---- # ---- GitHub 加速代理(国内构建用,若 ghproxy 不可用请更换)----
HTTP_PROXY: http://127.0.0.1:8118 # GH_PROXY: https://ghproxy.com/
HTTPS_PROXY: http://127.0.0.1:8118 # ---- PyPI 镜像(国内构建用)----
# PIP_INDEX: https://pypi.tuna.tsinghua.edu.cn/simple
container_name: mineru-rocm container_name: mineru-rocm
stdin_open: true stdin_open: true
tty: true tty: true
@@ -39,8 +39,6 @@ services:
group_add: group_add:
- video # /dev/dri/render* 权限 - video # /dev/dri/render* 权限
- render # /dev/kfd 权限 - render # /dev/kfd 权限
# 如果要与宿主机用户对齐,取消下面注释并改为你的 UID/GID
# user: "${UID:-1000}:${GID:-1000}"
# ---- 环境变量 ---- # ---- 环境变量 ----
environment: environment:
@@ -59,12 +57,6 @@ services:
- ${MIOPEN_CACHE:-./data/miopen}:/root/.cache/miopen - ${MIOPEN_CACHE:-./data/miopen}:/root/.cache/miopen
# ---- 启动命令(默认 bash,可改)---- # ---- 启动命令(默认 bash,可改)----
# 例如直接处理 PDF:
# command: mineru -p /data/input/example.pdf -o /data/output -b hybrid-auto-engine
# 启动 WebUI:
# command: mineru-gradio --server-name 0.0.0.0 --server-port 7860
# 启动 API:
# command: mineru-api --host 0.0.0.0 --port 8000
command: bash command: bash
# ---- 端口(WebUI / API 模式时启用)---- # ---- 端口(WebUI / API 模式时启用)----