x

docker/Dockerfile

@@ -64,7 +64,8 @@ RUN sed -i 's|http://.*archive.ubuntu.com|http://mirrors.tuna.tsinghua.edu.cn|g'
 RUN set -ex && \
     # 补丁 1: hipcc/clang 符号链接（hipcc.pl 硬编码 clang-17，实际是 clang-22）
     ln -sf /usr/bin/hipvars.pm /usr/share/perl5/hipvars.pm && \
-    ln -sf /usr/bin/hipcc.pl /opt/rocm/bin/hipcc && \
+    # hipcc.pl 在 WSL2 存在，原生 Linux 不存在；不存在时保留 apt 安装的版本
+    ([ -f /usr/bin/hipcc.pl ] && ln -sf /usr/bin/hipcc.pl /opt/rocm/bin/hipcc) || echo "hipcc.pl not found, keeping apt-installed hipcc" && \
     ln -sf /opt/rocm/llvm/bin/clang-22 /opt/rocm/llvm/bin/clang-17 && \
     ln -sf /opt/rocm/llvm/bin/clang++   /opt/rocm/llvm/bin/clang++-17 && \
     # 补丁 2: __hip_internal::conditional → std::conditional
@@ -130,6 +131,17 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     rocblas-dev rocrand-dev hipfft-dev hipblaslt && \
     apt-get clean && rm -rf /var/lib/apt/lists/*
 
+# ===========================================================================
+# 阶段 6.5：安装 amdsmi（原生 Linux 必需，vllm 平台检测依赖）
+# ===========================================================================
+RUN if [ -d /opt/rocm/share/amd_smi ]; then \
+        cp -r /opt/rocm/share/amd_smi /opt/amd_smi && \
+        cd /opt/amd_smi && ${VENV}/bin/pip install --no-cache-dir . --no-build-isolation && \
+        echo "amdsmi installed."; \
+    else \
+        echo "amdsmi source not found, skipping."; \
+    fi
+
 # ===========================================================================
 # 阶段 7：amd-aiter + flash_attn
 # ===========================================================================
@@ -180,6 +192,14 @@ RUN set -ex && \
     printf 'include(/opt/rocm/lib/cmake/rocblas/rocblas-config.cmake)\nif(TARGET roc::rocblas AND NOT TARGET hip::hipblas)\n  add_library(hip::hipblas ALIAS roc::rocblas)\nendif()\n' \
         > /opt/rocm/lib/cmake/hipblas/hipblas-config.cmake && \
     # cmake 配置
+    # ---- 诊断 HIP cmake（构建成功后删除）----
+    echo "=== HIP cmake files ===" && \
+    (find /opt/rocm/lib/cmake -iname "*hip*" 2>/dev/null || true) && \
+    echo "=== All cmake packages ===" && \
+    (ls /opt/rocm/lib/cmake/ || true) && \
+    echo "=== hipcc check ===" && \
+    (which hipcc && hipcc --version || true) && \
+    echo "=== HIP diagnostic end ===" && \
     mkdir -p /opt/vllm_build && \
     cmake -S /opt/vllm -B /opt/vllm_build -G Ninja \
         -DCMAKE_BUILD_TYPE=RelWithDebInfo \
@@ -204,6 +224,42 @@ 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 ----
+    ${VENV}/bin/python -c "
+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: __init__.py platform fallback applied.')
+else:
+    print('Patch 6: already applied or pattern not found.')
+" && \
+    # ---- 补丁 7：vllm rocm.py 断开循环导入 ----
+    ${VENV}/bin/python -c "
+f = '/opt/vllm/vllm/platforms/rocm.py'
+c = open(f).read()
+# 替换 logger.warning_once( 为 sys.stderr.write(
+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 logger.warning_once → sys.stderr.write applied.')
+else:
+    print('Patch 7: already applied or pattern not found.')
+" && \
     # 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