about sh build.sh the path for cuda used is fixed

[Huaxingweichen]

When I use

sh build.sh

then I have many error about cuda version. I checked the version of cuda and found the version is 8.0 which is your recommendation. I checked the error log and found the path for cuda is not what I used then I checked the build.sh. I change bulid.sh

nvcc -I/usr/local/cuda/include --expt-extended-lambda -O3 -c -o bn.o bn.cu -x cu -Xcompiler -fPIC -std=c++11 ${CUDA_GENCODE} into my path then worked. Maybe others will meet the same problem. Wish what i did can help you.

[speedinghzl]

THX!

[TianMingChen]

When I use

sh build.sh

then I have many error about cuda version. I checked the version of cuda and found the version is 8.0 which is your recommendation. I checked the error log and found the path for cuda is not what I used then I checked the build.sh. I change bulid.sh

nvcc -I/usr/local/cuda/include --expt-extended-lambda -O3 -c -o bn.o bn.cu -x cu -Xcompiler -fPIC -std=c++11 ${CUDA_GENCODE} into my path then worked. Maybe others will meet the same problem. Wish what i did can help you.

How did you change your build.sh?

[cauivy]

If your default CUDA is not 8.0, then change the path '/usr/local/cuda/include' in the build.sh into your cuda-8.0's path, e.g., '/usr/local/cuda-8.0/include'.