diff --git a/docker/china/mlu.Dockerfile b/docker/china/mlu.Dockerfile new file mode 100644 index 00000000..98615bc6 --- /dev/null +++ b/docker/china/mlu.Dockerfile @@ -0,0 +1,28 @@ +# Base image containing the vLLM inference environment, requiring amd64(x86-64) CPU + Cambricon MLU. +FROM + + +# Install Noto fonts for Chinese characters +RUN apt-get update && \ + apt-get install -y \ + fonts-noto-core \ + fonts-noto-cjk \ + fontconfig && \ + fc-cache -fv && \ + apt-get clean && \ + rm -rf /var/lib/apt/lists/* + +# Install mineru latest +RUN python3 -m pip install -U pip -i https://mirrors.aliyun.com/pypi/simple && \ + python3 -m pip install 'mineru[core]>=2.7.3' \ + numpy==1.26.4 \ + opencv-python==4.11.0.86 \ + accelerate==1.2.0 \ + -i https://mirrors.aliyun.com/pypi/simple && \ + python3 -m pip cache purge + +# Download models and update the configuration file +RUN /bin/bash -c "mineru-models-download -s modelscope -m all" + +# Set the entry point to activate the virtual environment and run the command line tool +ENTRYPOINT ["/bin/bash", "-c", "export MINERU_MODEL_SOURCE=local && exec \"$@\"", "--"] \ No newline at end of file diff --git a/docs/zh/usage/acceleration_cards/Cambricon.md b/docs/zh/usage/acceleration_cards/Cambricon.md index 1918c41c..31f6b027 100644 --- a/docs/zh/usage/acceleration_cards/Cambricon.md +++ b/docs/zh/usage/acceleration_cards/Cambricon.md @@ -1,253 +1,127 @@ -# MinerU -## 1. 环境准备 -容器启动方式见第3节 -### 1.1 获取代码 +## 1. 测试平台 +以下为本指南测试使用的平台信息，供参考： ``` -git clone https://github.com/opendatalab/MinerU.git -git checkout fa1149cd4abf9db5e0f13e4e074cdb568be189f4 -``` -### 1.2 安装依赖 -``` -source /torch/venv3/pytorch_infer/bin/activate -pip install accelerate==1.11.0 doclayout_yolo==0.0.4 thop==0.1.1.post2209072238 ultralytics-thop==2.0.18 ultralytics==8.3.228 -# requirements_check.txt具体内容在下面 -pip install -r requirements_check.txt -cd MinerU -pip install -e .[core] --no-deps -``` -requirements_check.txt -``` -# triton==3.0.0+mlu1.3.1 -# torch==2.5.0+cpu -# torchvision==0.20.0+cpu - - -# === 1. 已安装且版本相同 === -# (这些包已满足要求, 无需操作) - - -# === 2. 已安装但版本不同 === -# (运行 pip install -r 将强制更新到左侧的目标版本) -# accelerate==1.11.0 # 0.33.0 -beautifulsoup4==4.14.2 # 4.12.3 -cffi==2.0.0 # 1.17.1 -huggingface-hub==0.36.0 # 0.25.2 -jiter==0.12.0 # 0.8.2 -openai==2.8.0 # 1.59.7 -pillow==11.3.0 # 10.4.0 -sympy==1.14.0 # 1.13.1 -tokenizers==0.22.1 # 0.21.0 -# torch==2.9.1 # 2.5.0+cpu -# torchvision==0.24.1 # 0.20.0+cpu -transformers==4.57.1 # 4.48.0 -# triton==3.5.1 # 3.0.0+mlu1.3.1 -typing-extensions==4.15.0 # 4.12.2 - -# === 3. 未安装 === -# (运行 pip install -r 将安装这些包) -aiofiles==24.1.0 -albucore==0.0.24 -albumentations==2.0.8 -antlr4-python3-runtime==4.9.3 -brotli==1.2.0 -coloredlogs==15.0.1 -colorlog==6.10.1 -cryptography==46.0.3 -# doclayout_yolo==0.0.4 -fast-langdetect==0.2.5 -fasttext-predict==0.9.2.4 -ffmpy==1.0.0 -flatbuffers==25.9.23 -ftfy==6.3.1 -gradio-client==1.13.3 -gradio-pdf==0.0.22 -gradio==5.49.1 -groovy==0.1.2 -hf-xet==1.2.0 -httpx-retries==0.4.5 -humanfriendly==10.0 -imageio==2.37.2 -json-repair==0.53.0 -magika==0.6.3 -markdown-it-py==4.0.0 -mdurl==0.1.2 -mineru-vl-utils==0.1.15 -mineru==2.6.4 -modelscope==1.31.0 -# nvidia-cublas-cu12==12.8.4.1 -# nvidia-cuda-cupti-cu12==12.8.90 -# nvidia-cuda-nvrtc-cu12==12.8.93 -# nvidia-cuda-runtime-cu12==12.8.90 -# nvidia-cudnn-cu12==9.10.2.21 -# nvidia-cufft-cu12==11.3.3.83 -# nvidia-cufile-cu12==1.13.1.3 -# nvidia-curand-cu12==10.3.9.90 -# nvidia-cusolver-cu12==11.7.3.90 -# nvidia-cusparse-cu12==12.5.8.93 -# nvidia-cusparselt-cu12==0.7.1 -# nvidia-nccl-cu12==2.27.5 -# nvidia-nvjitlink-cu12==12.8.93 -# nvidia-nvshmem-cu12==3.3.20 -# nvidia-nvtx-cu12==12.8.90 -omegaconf==2.3.0 -onnxruntime==1.23.2 -orjson==3.11.4 -pdfminer.six==20250506 -pdftext==0.6.3 -polars-runtime-32==1.35.2 -polars==1.35.2 -pyclipper==1.3.0.post6 -pydantic-settings==2.12.0 -pydub==0.25.1 -pypdf==6.2.0 -pypdfium2==4.30.0 -python-multipart==0.0.20 -reportlab==4.4.4 -rich==14.2.0 -robust-downloader==0.0.2 -ruff==0.14.5 -safehttpx==0.1.7 -scikit-image==0.25.2 -seaborn==0.13.2 -semantic-version==2.10.0 -shapely==2.1.2 -shellingham==1.5.4 -simsimd==6.5.3 -stringzilla==4.2.3 -# thop==0.1.1.post2209072238 -tifffile==2025.5.10 -typer==0.20.0 -typing-inspection==0.4.2 -# ultralytics-thop==2.0.18 -# ultralytics==8.3.228 -``` -### 1.3 修改代码 -/raid_data/home/yqk/mineru-251114/MinerU/mineru/backend/pipeline/pipeline_analyze.py, line 1 -添加代码 -``` -# 添加MLU支持 -import torch_mlu.utils.gpu_migration -# 高版本镜像为 -# import torch.mlu.utils.gpu_migration +os: Ubuntu 22.04.5 LTS +cpu: Hygon Hygon C86 7490 +gcu: MLU590-M9D +driver: v6.2.11 +docker: 28.3.0 ``` -## 2. 使用方法 -``` -export HF_ENDPOINT=https://hf-mirror.com -mineru-api --host 0.0.0.0 --port 8009 -``` +## 2. 环境准备 -## 3. 其他 +### 2.1 使用 Dockerfile 构建镜像 -### 3.1 Dify插件配置问题 -给Dify的MinerU插件使用时，需将Dify的.env文件中FILES_URL设置为http://{ip}:{dify的网页访问端口}。 -根据网上找到的很多回答可能是要暴露5001，并将FILES_URL设置为http://{ip}:5001，并暴露5001端口，但其实设置为dify的网页访问端口即可。 - -### 3.2 容器启动方式 - -``` -export MY_CONTAINER="[容器名称]" -num=`docker ps -a|grep "$MY_CONTAINER" | wc -l` -echo $num -echo $MY_CONTAINER -if [ 0 -eq $num ];then -docker run -d \ - --privileged \ - --pid=host \ - --net=host \ - --shm-size 64g \ - --device /dev/cambricon_dev0 \ - --device /dev/cambricon_ipcm0 \ - --device /dev/cambricon_ctl \ - --name $MY_CONTAINER \ - -v [/path/to/your/data:/path/to/your/data] \ - -v /usr/bin/cnmon:/usr/bin/cnmon \ - [镜像名称] \ - sleep infinity -docker exec -ti $MY_CONTAINER /bin/bash -else - docker start $MY_CONTAINER - docker exec -ti $MY_CONTAINER /bin/bash -fi -``` - -### 3.3 将上面的过程进行打包 - -准备好前面的requirements_check.txt - -Dockerfile - -``` -# 1. 使用指定的基础镜像 -FROM cambricon-base/pytorch:v25.01-torch2.5.0-torchmlu1.24.1-ubuntu22.04-py310 - -# 2. 设置环境变量 -ENV HF_ENDPOINT=https://hf-mirror.com - -# 3. 定义 venv_pip 路径以便复用 -# 基础镜像中的虚拟环境路径 -ARG VENV_PIP=/torch/venv3/pytorch_infer/bin/pip - -# 4. 设置工作目录 -WORKDIR /app - -# 5. 安装 git (基础镜像可能不包含) -RUN apt-get update && apt-get install -y git && \ - rm -rf /var/lib/apt/lists/* - -# 6. 复制 requirements_check.txt 到镜像中 -# (这个文件需要您在宿主机上和 Dockerfile 放在同一目录下) -COPY requirements_check.txt . - -# 7. 步骤 1.1 & 1.2: 获取代码并安装所有依赖 -# 在一个 RUN 层中执行所有安装，以优化镜像大小 -RUN \ - # 1.1 获取代码 - echo "Cloning MinerU repository..." && \ - git clone https://gh-proxy.org/https://github.com/opendatalab/MinerU.git && \ - cd MinerU && \ - git checkout fa1149cd4abf9db5e0f13e4e074cdb568be189f4 && \ - cd .. && \ - \ - # 1.2 安装依赖 - # 第1个pip install (来自您的步骤) - echo "Installing initial dependencies..." && \ - ${VENV_PIP} install accelerate==1.11.0 doclayout_yolo==0.0.4 thop==0.1.1.post2209072238 ultralytics-thop==2.0.18 ultralytics==8.3.228 && \ - \ - # 第2个pip install (来自 requirements_check.txt) - echo "Installing dependencies from requirements_check.txt..." && \ - # 注意：基础镜像已包含 torch 和 triton，requirements_check.txt 中的注释行会被 pip 自动忽略 - ${VENV_PIP} install -r requirements_check.txt && \ - \ - # 第3个pip install (本地安装 MinerU) - echo "Installing MinerU in editable mode..." && \ - cd MinerU && \ - ${VENV_PIP} install -e .[core] --no-deps - -# 8. 步骤 1.3: 修改代码 -# 将 MLU 支持代码添加到指定文件的开头 -RUN echo "Applying MLU patch to pipeline_analyze.py..." && \ - sed -i '1i# 添加MLU支持\nimport torch_mlu.utils.gpu_migration\n# 高版本镜像为\n# import torch.mlu.utils.gpu_migration\n' \ - /app/MinerU/mineru/backend/pipeline/pipeline_analyze.py -``` - -该镜像的启动 - -``` -docker run -d --restart=always \ - --privileged \ - --pid=host \ - --net=host \ - --shm-size 64g \ - --device /dev/cambricon_dev0 \ - --device /dev/cambricon_ipcm0 \ - --device /dev/cambricon_ctl \ - --name mineru_service \ - mineru-mlu:latest \ - /torch/venv3/pytorch_infer/bin/python /app/MinerU/mineru/cli/fast_api.py --host 0.0.0.0 --port 8009 +```bash +wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/china/mlu.Dockerfile +docker build --network=host -t mineru:mlu-lmdeploy-latest -f mlu.Dockerfile . ``` +## 3. 启动 Docker 容器 + +```bash +docker run --name mineru_docker \ + --privileged \ + --ipc=host \ + --network=host \ + --cap-add SYS_PTRACE \ + --device=/dev/mem \ + --device=/dev/dri \ + --device=/dev/infiniband \ + --device=/dev/cambricon_ctl \ + --device=/dev/cambricon_dev0 \ + --device=/dev/cambricon_dev1 \ + --device=/dev/cambricon_dev2 \ + --device=/dev/cambricon_dev3 \ + --device=/dev/cambricon_dev4 \ + --device=/dev/cambricon_dev5 \ + --device=/dev/cambricon_dev6 \ + --device=/dev/cambricon_dev7 \ + --group-add video \ + --shm-size=400g \ + --ulimit memlock=-1 \ + --security-opt seccomp=unconfined \ + --security-opt apparmor=unconfined \ + -e MINERU_MODEL_SOURCE=local \ + -e MINERU_LMDEPLOY_DEVICE=camb \ + --entrypoint /bin/bash \ + -it mineru:mlu-lmdeploy-latest +``` + +执行该命令后，您将进入到Docker容器的交互式终端，您可以直接在容器内运行MinerU相关命令来使用MinerU的功能。 +您也可以直接通过替换`/bin/bash`为服务启动命令来启动MinerU服务，详细说明请参考[通过命令启动服务](https://opendatalab.github.io/MinerU/zh/usage/quick_usage/#apiwebuihttp-clientserver)。 +## 4. 注意事项 +不同环境下，MinerU对Cambricon加速卡的支持情况如下表所示： + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
使用场景容器环境
lmdeploy
命令行工具(mineru)pipeline🟢
<vlm/hybrid>-auto-engine🟢
<vlm/hybrid>-http-client🟢
fastapi服务(mineru-api)pipeline🟢
<vlm/hybrid>-auto-engine🟢
<vlm/hybrid>-http-client🟢
gradio界面(mineru-gradio)pipeline🟢
<vlm/hybrid>-auto-engine🟢
<vlm/hybrid>-http-client🟢
openai-server服务（mineru-openai-server）🟢
数据并行 (--data-parallel-size)🟢
+ +注： +🟢: 支持，运行较稳定，精度与Nvidia GPU基本一致 +🟡: 支持但较不稳定，在某些场景下可能出现异常，或精度存在一定差异 +🔴: 不支持，无法运行，或精度存在较大差异 + +>[!TIP] +>Cambricon加速卡指定可用加速卡的方式与NVIDIA GPU类似，请参考[使用指定GPU设备](https://opendatalab.github.io/MinerU/zh/usage/advanced_cli_parameters/#cuda_visible_devices)章节说明, \ No newline at end of file diff --git a/docs/zh/usage/acceleration_cards/Iluvatar.md b/docs/zh/usage/acceleration_cards/IluvatarCorex.md similarity index 100% rename from docs/zh/usage/acceleration_cards/Iluvatar.md rename to docs/zh/usage/acceleration_cards/IluvatarCorex.md diff --git a/docs/zh/usage/index.md b/docs/zh/usage/index.md index 20878af3..f97da1a3 100644 --- a/docs/zh/usage/index.md +++ b/docs/zh/usage/index.md @@ -15,9 +15,10 @@ * [海光 Hygon](acceleration_cards/Hygon.md) 🚀 * [燧原 Enflame](acceleration_cards/Enflame.md) 🚀 * [摩尔线程 MooreThreads](acceleration_cards/MooreThreads.md) 🚀 + * [天数智芯 IluvatarCorex](acceleration_cards/IluvatarCorex.md) 🚀 + * [寒武纪 Cambricon](acceleration_cards/Cambricon.md) 🚀 * [AMD](acceleration_cards/AMD.md) [#3662](https://github.com/opendatalab/MinerU/discussions/3662) ❤️ * [太初元碁 Tecorigin](acceleration_cards/Tecorigin.md) [#3767](https://github.com/opendatalab/MinerU/pull/3767) ❤️ - * [寒武纪 Cambricon](acceleration_cards/Cambricon.md) [#4004](https://github.com/opendatalab/MinerU/discussions/4004) ❤️ * [瀚博 VastAI](acceleration_cards/VastAI.md) [#4237](https://github.com/opendatalab/MinerU/discussions/4237)❤️ - 插件与生态 * [Cherry Studio](plugin/Cherry_Studio.md) diff --git a/mineru/utils/block_sort.py b/mineru/utils/block_sort.py index c00d2634..b8857fc0 100644 --- a/mineru/utils/block_sort.py +++ b/mineru/utils/block_sort.py @@ -198,6 +198,10 @@ def model_init(model_name: str): if hasattr(torch, 'npu') and torch.npu.is_available(): if torch.npu.is_bf16_supported(): bf_16_support = True + elif device_name.startswith("mlu"): + if hasattr(torch, 'mlu') and torch.mlu.is_available(): + if torch.mlu.is_bf16_supported(): + bf_16_support = True if model_name == 'layoutreader': # 检测modelscope的缓存目录是否存在 diff --git a/mineru/utils/config_reader.py b/mineru/utils/config_reader.py index 22f975db..213db62b 100644 --- a/mineru/utils/config_reader.py +++ b/mineru/utils/config_reader.py @@ -94,7 +94,11 @@ def get_device(): if torch.musa.is_available(): return "musa" except Exception as e: - pass + try: + if torch.mlu.is_available(): + return "mlu" + except Exception as e: + pass return "cpu" diff --git a/mineru/utils/model_utils.py b/mineru/utils/model_utils.py index 33b14fe6..ccc01ec9 100644 --- a/mineru/utils/model_utils.py +++ b/mineru/utils/model_utils.py @@ -429,6 +429,9 @@ def clean_memory(device='cuda'): elif str(device).startswith("musa"): if torch.musa.is_available(): torch.musa.empty_cache() + elif str(device).startswith("mlu"): + if torch.mlu.is_available(): + torch.mlu.empty_cache() gc.collect() @@ -470,5 +473,8 @@ def get_vram(device) -> int: elif str(device).startswith("musa"): if torch.musa.is_available(): total_memory = round(torch.musa.get_device_properties(device).total_memory / (1024 ** 3)) # 转为 GB + elif str(device).startswith("mlu"): + if torch.mlu.is_available(): + total_memory = round(torch.mlu.get_device_properties(device).total_memory / (1024 ** 3)) # 转为 GB return total_memory