x

docker/Dockerfile

@@ -224,38 +224,8 @@ RUN set -ex && \
     cd /opt/vllm && ${VENV}/bin/pip install --no-cache-dir -e . --no-build-isolation && \
     # --no-build-isolation 可能漏装部分运行时依赖，显式补装
     ${VENV}/bin/pip install --no-cache-dir regex && \
-    # ---- 补丁 6：vllm 平台检测 —— torch.version.hip 回退 ----
-    cat > /tmp/patch6.py << 'PYEOF'
-import re
-f = '/opt/vllm/vllm/platforms/__init__.py'
-c = open(f).read()
-old = "    return 'vllm.platforms.rocm.RocmPlatform' if is_rocm else None"
-new = """    # amdsmi fallback: also check torch.version.hip
-    if not is_rocm:
-        try:
-            import torch
-            if torch.version.hip is not None:
-                is_rocm = True
-        except Exception:
-            pass
-    return 'vllm.platforms.rocm.RocmPlatform' if is_rocm else None"""
-c2 = c.replace(old, new)
-if c2 != c: open(f, 'w').write(c2); print('Patch 6 applied.')
-else: print('Patch 6 already applied.')
-PYEOF
-    ${VENV}/bin/python /tmp/patch6.py && \
-    # ---- 补丁 7：vllm rocm.py 断开循环导入 ----
-    cat > /tmp/patch7.py << 'PYEOF'
-f = '/opt/vllm/vllm/platforms/rocm.py'
-c = open(f).read()
-old = 'logger.warning_once('
-new = 'import sys as _sys\n        _sys.stderr.write('
-c2 = c.replace(old, new)
-if c2 != c: open(f, 'w').write(c2); print('Patch 7 applied.')
-else: print('Patch 7 already applied.')
-PYEOF
-    ${VENV}/bin/python /tmp/patch7.py && \
-    rm -f /tmp/patch6.py /tmp/patch7.py && \
+    # 应用 vllm 平台检测补丁（独立脚本，避免 Dockerfile 解析问题）
+    ${VENV}/bin/python /opt/patch_vllm_platform.py && \
     # 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)" && \
     # 先重装 ROCm PyTorch 覆盖可能的 CUDA 版，再清理 CUDA triton 元数据
@@ -273,6 +243,7 @@ PYEOF
 # ===========================================================================
 COPY scripts/apply_mineru_patches.py /opt/apply_mineru_patches.py
 COPY scripts/cache_warmer.py /opt/cache_warmer.py
+COPY scripts/patch_vllm_platform.py /opt/patch_vllm_platform.py
 
 # ===========================================================================
 # 阶段 9：安装 MinerU + RDNA 适配补丁

docker/scripts/patch_vllm_platform.py

@@ -0,0 +1,56 @@
+#!/usr/bin/env python3
+"""vllm 平台检测补丁
+
+问题 1：amdsmi 不可用时 platform 回退到 torch.version.hip
+问题 2：rocm.py 中 logger.warning_once() 导致循环导入
+"""
+
+import os
+
+VLLM_DIR = '/opt/vllm/vllm'
+
+
+def patch6_init_platform_fallback():
+    """补丁 6：platforms/__init__.py —— torch.version.hip 兜底"""
+    f = os.path.join(VLLM_DIR, 'platforms', '__init__.py')
+    c = open(f).read()
+    old = "    return 'vllm.platforms.rocm.RocmPlatform' if is_rocm else None"
+    new = ("    # amdsmi fallback: also check torch.version.hip\n"
+           "    if not is_rocm:\n"
+           "        try:\n"
+           "            import torch\n"
+           "            if torch.version.hip is not None:\n"
+           "                is_rocm = True\n"
+           "        except Exception:\n"
+           "            pass\n"
+           "    return 'vllm.platforms.rocm.RocmPlatform' if is_rocm else None")
+    c2 = c.replace(old, new)
+    if c2 != c:
+        open(f, 'w').write(c2)
+        print('Patch 6: __init__.py platform fallback applied.')
+    else:
+        print('Patch 6: already applied or pattern not found.')
+
+
+def patch7_rocm_break_import_cycle():
+    """补丁 7：platforms/rocm.py —— logger.warning_once → sys.stderr.write"""
+    f = os.path.join(VLLM_DIR, 'platforms', 'rocm.py')
+    c = open(f).read()
+    old = 'logger.warning_once('
+    new = 'import sys as _sys\n        _sys.stderr.write('
+    c2 = c.replace(old, new)
+    if c2 != c:
+        open(f, 'w').write(c2)
+        print('Patch 7: rocm.py circular import broken.')
+    else:
+        print('Patch 7: already applied or pattern not found.')
+
+
+def main():
+    patch6_init_platform_fallback()
+    patch7_rocm_break_import_cycle()
+    print('vllm platform patches done.')
+
+
+if __name__ == '__main__':
+    main()