rm -rf .use_nixl
HYBRID_EP_MULTINODE=1 LIBRARY_PATH=/usr/local/cuda/lib64/stubs:$LIBRARY_PATH TORCH_CUDA_ARCH_LIST='10.0' python setup.py bdist_wheel

FAILED: /root/hybrid-ep-open-source/build/temp.linux-x86_64-cpython-312/csrc/hybrid_ep/buffer/internode_doca.o
/usr/local/cuda/bin/nvcc --generate-dependencies-with-compile --dependency-output /root/hybrid-ep-open-source/build/temp.linux-x86_64-cpython-312/csrc/hybrid_ep/buffer/internode_doca.o.d -I/root/hybrid-ep-open-source/csrc/hybrid_ep/ -I/root/hybrid-ep-open-source/csrc/hybrid_ep/backend/ -I/root/hybrid-ep-open-source/third-party/nccl/src/transport/net_ib/gdaki/doca-gpunetio/include -Iinclude -I/usr/local/lib/python3.12/dist-packages/torch/include -I/usr/local/lib/python3.12/dist-packages/torch/include/torch/csrc/api/include -I/usr/local/cuda/include -I/usr/include/python3.12 -c -c /root/hybrid-ep-open-source/csrc/hybrid_ep/buffer/internode_doca.cu -o /root/hybrid-ep-open-source/build/temp.linux-x86_64-cpython-312/csrc/hybrid_ep/buffer/internode_doca.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -std=c++17 -Xcompiler -fPIC --expt-relaxed-constexpr -O3 --shared '-DSM_ARCH="10.0"' -DHYBRID_EP_BUILD_MULTINODE_ENABLE '-DRDMA_CORE_HOME=""' -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1016"' -DTORCH_EXTENSION_NAME=hybrid_ep_cpp -gencode=arch=compute_100,code=sm_100
In file included from /root/hybrid-ep-open-source/third-party/nccl/src/transport/net_ib/gdaki/doca-gpunetio/include/doca_gpunetio_device.h:41,
                 from /root/hybrid-ep-open-source/csrc/hybrid_ep/buffer/internode_doca.cuh:8,
                 from /root/hybrid-ep-open-source/csrc/hybrid_ep/buffer/internode_doca.cu:4:
/root/hybrid-ep-open-source/third-party/nccl/src/transport/net_ib/gdaki/doca-gpunetio/include/device/doca_gpunetio_dev_verbs_common.cuh:58:2: warning: #warning "warning: doca_gpunetio should be used with a CUDA version >= 12020." [-Wcpp]
   58 | #warning "warning: doca_gpunetio should be used with a CUDA version >= 12020."
      |  ^~~~~~~
In file included from /root/hybrid-ep-open-source/third-party/nccl/src/transport/net_ib/gdaki/doca-gpunetio/include/doca_gpunetio_device.h:41,
                 from /root/hybrid-ep-open-source/csrc/hybrid_ep/buffer/internode_doca.cuh:8,
                 from /root/hybrid-ep-open-source/csrc/hybrid_ep/buffer/internode_doca.cu:4:
/root/hybrid-ep-open-source/third-party/nccl/src/transport/net_ib/gdaki/doca-gpunetio/include/device/doca_gpunetio_dev_verbs_common.cuh:58:2: warning: #warning "warning: doca_gpunetio should be used with a CUDA version >= 12020." [-Wcpp]
   58 | #warning "warning: doca_gpunetio should be used with a CUDA version >= 12020."
      |  ^~~~~~~
/root/hybrid-ep-open-source/csrc/hybrid_ep/buffer/internode_doca.cu(796): error: name followed by "::" must be a class or namespace name
    torch::Tensor buffer = torch::empty({num_bytes}, at::device(at::kCPU).dtype(at::kByte));
    ^

/root/hybrid-ep-open-source/csrc/hybrid_ep/buffer/internode_doca.cu(796): error: expected a ";"
    torch::Tensor buffer = torch::empty({num_bytes}, at::device(at::kCPU).dtype(at::kByte));
                  ^

/root/hybrid-ep-open-source/csrc/hybrid_ep/buffer/internode_doca.cu(797): error: identifier "buffer" is undefined
    memcpy(buffer.data_ptr<uint8_t>(), reinterpret_cast<void *>(src), num_of_qps * sizeof(remote_info));
           ^

/root/hybrid-ep-open-source/csrc/hybrid_ep/buffer/internode_doca.cu(797): error: type name is not allowed
    memcpy(buffer.data_ptr<uint8_t>(), reinterpret_cast<void *>(src), num_of_qps * sizeof(remote_info));
                           ^

/root/hybrid-ep-open-source/csrc/hybrid_ep/buffer/internode_doca.cu(797): error: expected an expression
    memcpy(buffer.data_ptr<uint8_t>(), reinterpret_cast<void *>(src), num_of_qps * sizeof(remote_info));
                                    ^

/root/hybrid-ep-open-source/csrc/hybrid_ep/buffer/internode_doca.cu(805): error: name followed by "::" must be a class or namespace name
      output_list.append(torch::empty_like(buffer));
                         ^

/root/hybrid-ep-open-source/csrc/hybrid_ep/buffer/internode_doca.cu(812): error: name followed by "::" must be a class or namespace name
      auto tensor = output_list[i].cast<torch::Tensor>().cpu();
                                        ^

/root/hybrid-ep-open-source/csrc/hybrid_ep/buffer/internode_doca.cu(813): error: type name is not allowed
      memcpy(dst + num_of_qps * (i / buffer_config.num_of_ranks_per_node), tensor.data_ptr<uint8_t>(), num_of_qps * sizeof(remote_info));
                                                                                           ^

/root/hybrid-ep-open-source/csrc/hybrid_ep/buffer/internode_doca.cu(813): error: expected an expression
      memcpy(dst + num_of_qps * (i / buffer_config.num_of_ranks_per_node), tensor.data_ptr<uint8_t>(), num_of_qps * sizeof(remote_info));
                                                                                                    ^

9 errors detected in the compilation of "/root/hybrid-ep-open-source/csrc/hybrid_ep/buffer/internode_doca.cu".