feat: add Dockerfile for corex environment setup and update vllm server configurations

docker/china/corex.Dockerfile

@@ -0,0 +1,27 @@
+# Base image containing the vLLM inference environment, requiring amd64(x86-64) CPU + iluvatar GPU.
+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]>=2.7.4' \
+                            numpy==1.26.4 \
+                            opencv-python==4.11.0.86 \
+                            -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 \"$@\"", "--"]

docker/china/dcu.Dockerfile

@@ -2,7 +2,7 @@
 FROM harbor.sourcefind.cn:5443/dcu/admin/base/vllm:0.9.2-ubuntu22.04-dtk25.04.2-1226-das1.7-py3.10-20251226
 
 
-# Install libgl for opencv support & Noto fonts for Chinese characters
+# Install Noto fonts for Chinese characters
 RUN apt-get update && \
     apt-get install -y \
         fonts-noto-core \

docker/china/gcu.Dockerfile

@@ -2,7 +2,7 @@
 FROM crpi-vofi3w62lkohhxsp.cn-shanghai.personal.cr.aliyuncs.com/opendatalab-mineru/gcu:docker_images_topsrider_i3x_3.6.20260106_vllm0.11_pytorch2.8.0
 
 
-# Install libgl for opencv support & Noto fonts for Chinese characters
+# Install Noto fonts for Chinese characters
 RUN echo 'deb http://mirrors.aliyun.com/ubuntu/ noble main restricted universe multiverse\n\
 deb http://mirrors.aliyun.com/ubuntu/ noble-updates main restricted universe multiverse\n\
 deb http://mirrors.aliyun.com/ubuntu/ noble-backports main restricted universe multiverse\n\

docs/zh/usage/acceleration_cards/Iluvatar.md

@@ -0,0 +1,120 @@
+## 1. 测试平台
+以下为本指南测试使用的平台信息，供参考：
+```
+os: Ubuntu 22.04.5 LTS  
+cpu: Intel x86-64
+gcu: Iluvatar BI-V150
+driver: 4.4.0
+docker: 28.1.1
+```
+
+## 2. 环境准备
+
+### 2.1 使用 Dockerfile 构建镜像
+
+```bash
+wget https://gcore.jsdelivr.net/gh/opendatalab/MinerU@master/docker/china/corex.Dockerfile
+docker build --network=host -t mineru:corex-vllm-latest -f corex.Dockerfile .
+```
+
+
+## 3. 启动 Docker 容器
+
+```bash
+docker run --name mineru_docker \
+   -v /usr/src:/usr/src \
+   -v /lib/modules:/lib/modules \
+   -v /dev:/dev \
+   --privileged \
+   --cap-add=ALL \
+   --pid=host \
+   --group-add video \
+   --network=host \
+   --shm-size '400gb' \
+   --ulimit memlock=-1 \
+   --security-opt seccomp=unconfined \
+   --security-opt apparmor=unconfined \
+   -e VLLM_ENFORCE_CUDA_GRAPH=1 \
+   -e MINERU_MODEL_SOURCE=local \
+   -e MINERU_LMDEPLOY_DEVICE=corex \
+   -it mineru:corex-vllm-latest \
+   /bin/bash
+```
+
+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Enflame加速卡的支持情况如下表所示：
+
+<table border="1">
+  <thead>
+    <tr>
+      <th rowspan="2" colspan="2">使用场景</th>
+      <th colspan="2">容器环境</th>
+    </tr>
+    <tr>
+      <th>vllm</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td rowspan="3">命令行工具(mineru)</td>
+      <td>pipeline</td>
+      <td>🟢</td>
+    </tr>
+    <tr>
+      <td>&lt;vlm/hybrid&gt;-auto-engine</td>
+      <td>🟢</td>
+    </tr>
+    <tr>
+      <td>&lt;vlm/hybrid&gt;-http-client</td>
+      <td>🟢</td>
+    </tr>
+    <tr>
+      <td rowspan="3">fastapi服务(mineru-api)</td>
+      <td>pipeline</td>
+      <td>🟢</td>
+    </tr>
+    <tr>
+      <td>&lt;vlm/hybrid&gt;-auto-engine</td>
+      <td>🟢</td>
+    </tr>
+    <tr>
+      <td>&lt;vlm/hybrid&gt;-http-client</td>
+      <td>🟢</td>
+    </tr>
+    <tr>
+      <td rowspan="3">gradio界面(mineru-gradio)</td>
+      <td>pipeline</td>
+      <td>🟢</td>
+    </tr>
+    <tr>
+      <td>&lt;vlm/hybrid&gt;-auto-engine</td>
+      <td>🟢</td>
+    </tr>
+    <tr>
+      <td>&lt;vlm/hybrid&gt;-http-client</td>
+      <td>🟢</td>
+    </tr>
+    <tr>
+      <td colspan="2">openai-server服务（mineru-openai-server）</td>
+      <td>🟢</td>
+    </tr>
+    <tr>
+      <td colspan="2">数据并行 (--data-parallel-size)</td>
+      <td>🔴</td>
+    </tr>
+  </tbody>
+</table>
+
+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]
+>GCU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,
+>将环境变量`CUDA_VISIBLE_DEVICES`替换为`TOPS_VISIBLE_DEVICES`即可。 

mineru/backend/pipeline/model_init.py

@@ -297,7 +297,14 @@ def ocr_det_batch_setting(device):
     # 检测torch的版本号
     import torch
     from packaging import version
-    if version.parse(torch.__version__) >= version.parse("2.8.0") or str(device).startswith('mps'):
+
+    device_type = os.getenv("MINERU_LMDEPLOY_DEVICE", "")
+
+    if (
+            version.parse(torch.__version__) >= version.parse("2.8.0")
+            or str(device).startswith('mps')
+            or device_type.lower() in ["corex"]
+    ):
         enable_ocr_det_batch = False
     else:
         enable_ocr_det_batch = True

mineru/backend/pipeline/pipeline_analyze.py

@@ -193,7 +193,12 @@ def batch_image_analyze(
     # 检测torch的版本号
     import torch
     from packaging import version
-    if version.parse(torch.__version__) >= version.parse("2.8.0") or str(device).startswith('mps'):
+    device_type = os.getenv("MINERU_LMDEPLOY_DEVICE", "")
+    if (
+            version.parse(torch.__version__) >= version.parse("2.8.0")
+            or str(device).startswith('mps')
+            or device_type.lower() in ["corex"]
+    ):
         enable_ocr_det_batch = False
     else:
         enable_ocr_det_batch = True

mineru/backend/vlm/vlm_analyze.py

@@ -101,20 +101,27 @@ class ModelSingleton:
                     except ImportError:
                         raise ImportError("Please install vllm to use the vllm-engine backend.")
 
-                    """
                     # musa vllm v1 引擎特殊配置
-                    device = get_device()
+                    # device = get_device()
-                    if device.startswith("musa"):
+                    # if device_type.startswith("musa"):
-                        import torch
+                    #     import torch
-                        if torch.musa.is_available():
+                    #     if torch.musa.is_available():
-                            compilation_config = {
+                    #         compilation_config = {
-                                "cudagraph_capture_sizes": [1, 2, 3, 4, 5, 6, 7, 8, 10, 12, 14, 16, 18, 20, 24, 28, 30],
+                    #             "cudagraph_capture_sizes": [1, 2, 3, 4, 5, 6, 7, 8, 10, 12, 14, 16, 18, 20, 24, 28, 30],
-                                "simple_cuda_graph": True
+                    #             "simple_cuda_graph": True
-                            }
+                    #         }
-                            block_size = 32
+                    #         block_size = 32
-                            kwargs["compilation_config"] = compilation_config
+                    #         kwargs["compilation_config"] = compilation_config
-                            kwargs["block_size"] = block_size
+                    #         kwargs["block_size"] = block_size
-                    """
+
+                    # corex vllm v1 引擎特殊配置
+                    device_type = os.getenv("MINERU_LMDEPLOY_DEVICE", "")
+                    if device_type.lower() == "corex":
+                        compilation_config = {
+                            "cudagraph_mode": "FULL_DECODE_ONLY",
+                            "level": 0
+                        }
+                        kwargs["compilation_config"] = compilation_config
 
                     if "compilation_config" in kwargs:
                         if isinstance(kwargs["compilation_config"], str):

mineru/model/vlm/vllm_server.py

@@ -56,17 +56,22 @@ def main():
         model_path = auto_download_and_get_model_root_path("/", "vlm")
     if (not has_logits_processors_arg) and custom_logits_processors:
         args.extend(["--logits-processors", "mineru_vl_utils:MinerULogitsProcessor"])
-    """
+
     # musa vllm v1 引擎特殊配置 
-    device = get_device()
+    # device = get_device()
-    if device.startswith("musa"):
+    # if device.startswith("musa"):
-        import torch
+    #     import torch
-        if torch.musa.is_available():
+    #     if torch.musa.is_available():
-            if not has_block_size_arg:
+    #         if not has_block_size_arg:
-                args.extend(["--block-size", "32"])
+    #             args.extend(["--block-size", "32"])
-            if not has_compilation_config:
+    #         if not has_compilation_config:
-                args.extend(["--compilation-config", '{"cudagraph_capture_sizes": [1,2,3,4,5,6,7,8,10,12,14,16,18,20,24,28,30], "simple_cuda_graph": true}'])
+    #             args.extend(["--compilation-config", '{"cudagraph_capture_sizes": [1,2,3,4,5,6,7,8,10,12,14,16,18,20,24,28,30], "simple_cuda_graph": true}'])
-    """
+
+    # corex vllm v1 引擎特殊配置
+    device_type = os.getenv("MINERU_LMDEPLOY_DEVICE", "")
+    if device_type.lower() == "corex":
+        if not has_compilation_config:
+            args.extend(["--compilation-config", '{"cudagraph_mode": "FULL_DECODE_ONLY", "level": 0}'])
 
     # 重构参数，将模型路径作为位置参数
     sys.argv = [sys.argv[0]] + ["serve", model_path] + args