x

docker/Dockerfile

@@ -304,6 +304,7 @@ RUN set -ex && \
 RUN set -ex && \
     export http_proxy=${GIT_PROXY} https_proxy=${GIT_PROXY} && \
     ${VENV}/bin/pip install 'mineru[core]' click gradio && \
+    cd /opt/vllm && ${VENV}/bin/pip install -e . --no-build-isolation --no-deps && \
     ${VENV}/bin/python -c "import torch; import vllm; import mineru; import click; import gradio; import mineru.cli.gradio_app; print('MinerU + Gradio CLI imports OK')" && \
     ${VENV}/bin/mineru-gradio --help >/dev/null
 

docker/README.md

@@ -428,6 +428,19 @@ PY'
 
 当前入口脚本会在服务启动前执行同样的 vLLM 导入验证；如果验证失败，容器会直接退出并在 `docker compose logs gradio` 中显示真实 traceback，而不是等任务执行时才报泛化错误。
 
+如果日志明确显示 `ModuleNotFoundError: No module named 'vllm'`，说明 MinerU 依赖安装后 editable vLLM 没有注册到虚拟环境。当前 Dockerfile 已在安装 MinerU 后重新执行：
+
+```bash
+cd /opt/vllm && /opt/mineru_venv/bin/pip install -e . --no-build-isolation --no-deps
+```
+
+入口脚本也会在启动时自动尝试这个修复。你也可以在旧容器里手动验证/修复一次：
+
+```bash
+docker compose exec gradio bash -lc 'cd /opt/vllm && /opt/mineru_venv/bin/pip install -e . --no-build-isolation --no-deps && /opt/mineru_venv/bin/python -c "import vllm; print(vllm.__version__)"'
+docker compose restart gradio
+```
+
 **Q: 构建时 `ninja` 被 kill（exit 137）**
 
 内存不足。将 Dockerfile 中 `ninja -j4` 改为 `ninja -j2` 或 `ninja -j1`，或给 Docker 分配更多内存。

docker/scripts/patch_vllm_platform.py

@@ -6,9 +6,14 @@
 """
 
 import os
+import subprocess
+import sys
 import traceback
 
 VLLM_DIR = '/opt/vllm/vllm'
+VLLM_SRC_DIR = '/opt/vllm'
+VENV_PYTHON = '/opt/mineru_venv/bin/python'
+VENV_PIP = '/opt/mineru_venv/bin/pip'
 
 
 def patch6_init_platform_fallback():
@@ -56,10 +61,42 @@ def patch7_rocm_break_import_cycle():
         print('Patch 7: already applied or pattern not found.')
 
 
+def ensure_vllm_installed():
+    """确保 vLLM Python 包在当前虚拟环境中可导入。
+
+    某些 MinerU 依赖安装流程可能会卸载/覆盖 editable vLLM，导致任务运行时报
+    "Please install vllm"。如果 /opt/vllm 源码仍在，启动时用 --no-deps 重新注册，
+    避免扰动已锁定的 ROCm PyTorch/Triton 依赖。
+    """
+    try:
+        import vllm  # noqa: F401
+        return
+    except ModuleNotFoundError as exc:
+        if exc.name != 'vllm':
+            raise
+
+    if not os.path.isdir(VLLM_SRC_DIR):
+        raise ModuleNotFoundError(
+            'vllm is not installed and /opt/vllm source directory is missing'
+        )
+
+    print('vllm package missing; reinstalling editable /opt/vllm with --no-deps...')
+    subprocess.check_call([
+        VENV_PIP,
+        'install',
+        '-e', VLLM_SRC_DIR,
+        '--no-build-isolation',
+        '--no-deps',
+    ])
+    import vllm  # noqa: F401
+    print('vllm editable reinstall OK.')
+
+
 def main():
     patch6_init_platform_fallback()
     patch7_rocm_break_import_cycle()
     try:
+        ensure_vllm_installed()
         import vllm
         from vllm.platforms import current_platform
         print(f'vllm runtime import OK: {vllm.__version__}, platform={type(current_platform).__name__}')