diff --git a/docker/Dockerfile b/docker/Dockerfile index f0fca07..5ab2025 100644 --- a/docker/Dockerfile +++ b/docker/Dockerfile @@ -2,6 +2,7 @@ # 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 # +# 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) # ============================================================================= @@ -14,10 +15,11 @@ ARG PYTHON_VER=3.12 ARG VENV=/opt/mineru_venv ARG TORCH_INDEX=https://download.pytorch.org/whl/rocm7.2 -# -- 代理设置(国内构建必需)------------------------------------------------ -ARG HTTP_PROXY -ARG HTTPS_PROXY -ARG NO_PROXY=localhost,127.0.0.1 +# -- 国内镜像配置 ----------------------------------------------------------- +# GitHub 加速(ghproxy.com) +ARG GH_PROXY=https://ghproxy.com/ +# PyPI 镜像 +ARG PIP_INDEX=https://pypi.tuna.tsinghua.edu.cn/simple # -- 环境变量 --------------------------------------------------------------- ENV DEBIAN_FRONTEND=noninteractive \ @@ -27,13 +29,7 @@ ENV DEBIAN_FRONTEND=noninteractive \ MINERU_MODEL_SOURCE=huggingface \ TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL=1 \ HSA_ENABLE_SDMA=1 \ - 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} + VLLM_TARGET_DEVICE=rocm 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 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 && \ - # 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 \ 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 - | \ 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' \ @@ -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) # =========================================================================== 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 ${GH_PROXY}https://github.com/Kitware/CMake/releases/download/v4.0.0/cmake-4.0.0-linux-x86_64.tar.gz && \ tar -xzf cmake-4.0.0-linux-x86_64.tar.gz && \ cp -r cmake-4.0.0-linux-x86_64/bin/* /usr/local/bin/ && \ cp -r cmake-4.0.0-linux-x86_64/share/* /usr/local/share/ && \ @@ -112,8 +105,12 @@ RUN cd /tmp && \ # 阶段 5:Python 虚拟环境 + PyTorch ROCm # =========================================================================== RUN python${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 && \ - # 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) ${VENV}/bin/pip install --no-cache-dir --pre \ torch==2.11.0+rocm7.2 \ torchvision \ @@ -132,9 +129,11 @@ RUN apt-get update && apt-get install -y --no-install-recommends \ apt-get clean && rm -rf /var/lib/apt/lists/* # =========================================================================== -# 阶段 7:amd-aiter + flash_attn +# 阶段 7:amd-aiter + flash_attn(GitHub 通过 ghproxy 加速) # =========================================================================== RUN set -ex && \ + # 配置 git 走 ghproxy + git config --global url."${GH_PROXY}https://github.com/".insteadOf "https://github.com/" && \ # aiter(AMD 优化的 attention 算子) cd /opt && git clone --recursive --depth 1 https://github.com/ROCm/aiter.git && \ ${VENV}/bin/pip install --no-cache-dir -e /opt/aiter && \ @@ -149,6 +148,8 @@ RUN set -ex && \ # 阶段 8:编译 vllm # =========================================================================== RUN set -ex && \ + # 配置 git 走 ghproxy(新 RUN 层需重新配置) + git config --global url."${GH_PROXY}https://github.com/".insteadOf "https://github.com/" && \ # setuptools 升级(PEP 639 兼容) ${VENV}/bin/pip install --no-cache-dir -U \ "setuptools>=77.0.3" setuptools_scm setuptools_rust wheel && \ @@ -172,7 +173,7 @@ RUN set -ex && \ cd /opt/vllm_build && ninja -j8 && \ # 安装 .so 到 vllm 源码目录 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 && \ # 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)" && \ @@ -196,6 +197,7 @@ COPY scripts/cache_warmer.py /opt/cache_warmer.py # 阶段 9:安装 MinerU + RDNA 适配补丁 # =========================================================================== 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]' && \ # 验证 PyTorch 没被覆盖 ${VENV}/bin/python -c "import torch; v=torch.__version__; assert 'rocm' in v, f'PyTorch overwritten: {v}'; print('PyTorch OK:', v)" && \ diff --git a/docker/docker-compose.yml b/docker/docker-compose.yml index 716bf41..14aea0d 100644 --- a/docker/docker-compose.yml +++ b/docker/docker-compose.yml @@ -9,7 +9,6 @@ services: build: context: . dockerfile: Dockerfile - network: host # 构建时走宿主机网络(国内访问 ROCm 源需要) args: # ---- 按你的 GPU 修改 ---- # gfx1201 = RX 9070 / 9070 XT / 9070 GRE @@ -18,9 +17,10 @@ services: # gfx1101 = RX 7800 XT / 7700 XT # gfx1030 = RX 6950 / 6900 / 6800 系列 ARCH: gfx1201 - # ---- 代理(国内必需)---- - HTTP_PROXY: http://127.0.0.1:8118 - HTTPS_PROXY: http://127.0.0.1:8118 + # ---- GitHub 加速代理(国内构建用,若 ghproxy 不可用请更换)---- + # GH_PROXY: https://ghproxy.com/ + # ---- PyPI 镜像(国内构建用)---- + # PIP_INDEX: https://pypi.tuna.tsinghua.edu.cn/simple container_name: mineru-rocm stdin_open: true tty: true @@ -39,8 +39,6 @@ services: group_add: - video # /dev/dri/render* 权限 - render # /dev/kfd 权限 - # 如果要与宿主机用户对齐,取消下面注释并改为你的 UID/GID - # user: "${UID:-1000}:${GID:-1000}" # ---- 环境变量 ---- environment: @@ -59,12 +57,6 @@ services: - ${MIOPEN_CACHE:-./data/miopen}:/root/.cache/miopen # ---- 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 # ---- 端口(WebUI / API 模式时启用)----