Torch2trt not above to locate CUDA_HOME

I am unable to install torch2trt from source(GitHub - NVIDIA-AI-IOT/torch2trt: An easy to use PyTorch to TensorRT converter), have installed the torch dependencies and NVCC version is visible(meaning the cuda path is specified). Getting the following error:-
:torch2trt$ python3
Traceback (most recent call last):
File “”, line 24, in
plugins_ext_module = CUDAExtension(
File “/home/xxx/.local/lib/python3.8/site-packages/torch/utils/”, line 1074, in CUDAExtension
library_dirs += library_paths(cuda=True)
File “/home/xxx/.local/lib/python3.8/site-packages/torch/utils/”, line 1201, in library_paths
if (not os.path.exists(_join_cuda_home(lib_dir)) and
File “/home/xxx/.local/lib/python3.8/site-packages/torch/utils/”, line 2407, in _join_cuda_home
raise OSError('CUDA_HOME environment variable is not set. ’
OSError: CUDA_HOME environment variable is not set. Please set it to your CUDA install root.

Path is visible on bashrc:-

Move to “TensorRT” forum.