CMake Error at gpu_cache_generated_nv_gpu_cache.cu.o.cmake:276 (message)

Dear DGL developers,

I am trying to install the GPU version of DGL from the source by using cuda 11.6 and c++ 11.3 on Centos 7. The command "bash script/create_dev_conda_env.sh -g 11.7" works well and finishes successfully. However, when I try to build the shared library for GPU development "bash script/build_dgl.sh -g", it fails with the following error message:

_/usr/include/c++/11/bits/std_function.h:530:146: note: ‘_ArgTypes’
CMake Error at gpu_cache_generated_nv_gpu_cache.cu.o.cmake:276 (message):
Error generating file
/home/jinfeng/soft/dgl/build/CMakeFiles/gpu_cache.dir/third_party/HugeCTR/gpu_cache/src/./gpu_cache_generated_nv_gpu_cache.cu.o

make[2]: *** [CMakeFiles/gpu_cache.dir/build.make:360: CMakeFiles/gpu_cache.dir/third_party/HugeCTR/gpu_cache/src/gpu_cache_generated_nv_gpu_cache.cu.o] Error 1
make[1]: *** [CMakeFiles/Makefile2:210: CMakeFiles/gpu_cache.dir/all] Error 2
make[1]: *** Waiting for unfinished jobs....
/usr/include/c++/11/bits/std_function.h:435:145: error: parameter packs not expanded with ‘...’:
435 | function(_Functor&& __f)
| ^
/usr/include/c++/11/bits/std_function.h:435:145: note: ‘_ArgTypes’
/usr/include/c++/11/bits/std_function.h:530:146: error: parameter packs not expanded with ‘...’:
530 | operator=(_Functor&& __f)
| ^
/usr/include/c++/11/bits/std_function.h:530:146: note: ‘_ArgTypes’
make[5]: *** [CMakeFiles/graphbolt_pytorch_1.13.0.dir/build.make:217: CMakeFiles/graphbolt_pytorch_1.13.0.dir/src/cuda/index_select_impl.cu.o] Error 1
make[4]: *** [CMakeFiles/Makefile2:83: CMakeFiles/graphbolt_pytorch_1.13.0.dir/all] Error 2
make[3]: *** [Makefile:91: all] Error 2
make[2]: *** [CMakeFiles/graphbolt.dir/build.make:70: CMakeFiles/graphbolt] Error 2
make[1]: *** [CMakeFiles/Makefile2:320: CMakeFiles/graphbolt.dir/all] Error 2
make: *** [Makefile:146: all] Error 2_

So, what should I do to solve this problem ? Thanks for any suggestions, and I am looking forward to your reply.

Best,
Jinfeng