diff --git a/docker/Dockerfile b/docker/Dockerfile
index 3cd6553..62aadda 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -20,6 +20,7 @@ ARG PIP_INDEX=https://mirrors.aliyun.com/pypi/simple
 # -- 环境变量 ---------------------------------------------------------------
 ENV DEBIAN_FRONTEND=noninteractive \
     PATH=/opt/rocm/bin:/opt/rocm/llvm/bin:${VENV}/bin:${PATH} \
+    PYTHONPATH=/opt/vllm:${PYTHONPATH} \
     PYTORCH_ROCM_ARCH=${ARCH} \
     FLASH_ATTENTION_TRITON_AMD_ENABLE=TRUE \
     MINERU_MODEL_SOURCE=huggingface \
@@ -304,7 +305,6 @@ 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
 
diff --git a/docker/README.md b/docker/README.md
index 12a7972..93aed3d 100644
--- a/docker/README.md
+++ b/docker/README.md
@@ -428,16 +428,17 @@ 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：
+如果日志明确显示 `ModuleNotFoundError: No module named 'vllm'`，常见原因是 vLLM 分发元数据不可见，但 `/opt/vllm` 源码仍在。当前镜像已通过 `PYTHONPATH=/opt/vllm` 和入口脚本兜底保证可导入，避免 editable 安装触发 `pyproject.toml` 元数据校验失败。
 
 ```bash
-cd /opt/vllm && /opt/mineru_venv/bin/pip install -e . --no-build-isolation --no-deps
+export PYTHONPATH=/opt/vllm:${PYTHONPATH}
+/opt/mineru_venv/bin/python -c "import vllm; print(vllm.__version__)"
 ```
 
 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 exec gradio bash -lc 'export PYTHONPATH=/opt/vllm:${PYTHONPATH}; /opt/mineru_venv/bin/python -c "import vllm; print(vllm.__version__)"'
 docker compose restart gradio
 ```
 
diff --git a/docker/scripts/patch_vllm_platform.py b/docker/scripts/patch_vllm_platform.py
index 4f12472..adc8c8c 100644
--- a/docker/scripts/patch_vllm_platform.py
+++ b/docker/scripts/patch_vllm_platform.py
@@ -6,14 +6,11 @@
 """
 
 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():
@@ -64,9 +61,9 @@ def patch7_rocm_break_import_cycle():
 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。
+    某些 MinerU 依赖安装流程后，site-packages 中可能缺少 vLLM 分发元数据，但
+    /opt/vllm 源码仍在。此时直接把 /opt/vllm 加入 PYTHONPATH/sys.path 再导入，
+    避免 editable 安装触发 pyproject 元数据校验失败。
     """
     try:
         import vllm  # noqa: F401
@@ -80,16 +77,16 @@ def ensure_vllm_installed():
             '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',
-    ])
+    print('vllm package missing; trying PYTHONPATH fallback with /opt/vllm...')
+    current = os.environ.get('PYTHONPATH', '')
+    paths = [p for p in current.split(':') if p]
+    if VLLM_SRC_DIR not in paths:
+        os.environ['PYTHONPATH'] = f"{VLLM_SRC_DIR}:{current}" if current else VLLM_SRC_DIR
+    if VLLM_SRC_DIR not in sys.path:
+        sys.path.insert(0, VLLM_SRC_DIR)
+
     import vllm  # noqa: F401
-    print('vllm editable reinstall OK.')
+    print('vllm import recovered via PYTHONPATH fallback.')
 
 
 def main():