CUDA kernel errors

[jong3]

When I try to run 'run_pyrosetta_ver.sh input.fa .', the error will be reported in 'network.stderr' file. Why is this?
Thanks.

Using backend: pytorch
Traceback (most recent call last):
  File "/home/ganjh/RoseTTAFold/network/predict_pyRosetta.py", line 199, in <module>
    pred = Predictor(model_dir=args.model_dir, use_cpu=args.use_cpu)
  File "/home/ganjh/RoseTTAFold/network/predict_pyRosetta.py", line 67, in __init__
    self.model = RoseTTAFoldModule(**MODEL_PARAM).to(self.device)
  File "/home/ganjh/.conda/envs/RoseTTAFold/lib/python3.8/site-packages/torch/nn/modules/module.py", line 852, in to
    return self._apply(convert)
  File "/home/ganjh/.conda/envs/RoseTTAFold/lib/python3.8/site-packages/torch/nn/modules/module.py", line 530, in _apply
    module._apply(fn)
  File "/home/ganjh/.conda/envs/RoseTTAFold/lib/python3.8/site-packages/torch/nn/modules/module.py", line 530, in _apply
    module._apply(fn)
  File "/home/ganjh/.conda/envs/RoseTTAFold/lib/python3.8/site-packages/torch/nn/modules/module.py", line 552, in _apply
    param_applied = fn(param)
  File "/home/ganjh/.conda/envs/RoseTTAFold/lib/python3.8/site-packages/torch/nn/modules/module.py", line 850, in convert
    return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
RuntimeError: CUDA error: the provided PTX was compiled with an unsupported toolchain.
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.

[jong3]

It seems that CUDA version and Driver version are incompatible .

CUDA and Driver's information are as follow:
NVIDIA-SMI 450.142.00 Driver Version: 450.142.00 CUDA Version: 11.0

[jong3]

I have fixed it by updating my driver version.
Because Torch generally does not use the CUDA version you installed, it uses its own.
By command "print(torch.version.cuda) " in python, I know that Torch's CUDA version is 11.1, which is higher than CUDA version I have installed.