Maarten Meijer

Any fix available?

Fixed on my machine (Jetson Nano, CUDA 10.2, TensorRT 8.4) by commenting line 104 and 106 of `CMakeLists.txt`, as to still include the cub library.

If you still have this problem, or anybody finds it later, this would probably fix it (although I haven't tested it): Change: ```python self.load_state_dict(torch.load(base_file, map_location=lambda storage, loc: storage)) ``` to...