Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

problem: No compatible CUDA device is available #22

Open
CLG68 opened this issue May 11, 2024 · 0 comments
Open

problem: No compatible CUDA device is available #22

CLG68 opened this issue May 11, 2024 · 0 comments

Comments

@CLG68
Copy link

CLG68 commented May 11, 2024

Hi,

I get this message: "No compatible CUDA device is available". As there are 2 environments, I'm not sure under which one I get it, how to solve the problem. I still get results, are they still ok? Why do we need 2 environments, they cannot be merged?

Here is how I built the environment:
To create dynamicbind env:

conda create -n dynamicbind python=3.10
conda activate dynamicbind
conda install pytorch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 pytorch-cuda=11.7 -c pytorch -c nvidia
conda install rdkit==2022.03.5 -c conda-forge
conda install pyg==2.3.0 pyyaml==6.0 biopython==1.78 -c pyg
pip install pyg_lib==0.2.0 torch_scatter==2.1.1 torch_sparse==0.6.17 torch_cluster==1.6.1 torch_spline_conv==1.2.2 -f https://data.pyg.org/whl/torch-2.0.1+cu117.html
pip install e3nn==0.5.1 fair-esm==2.0.0 spyrmsd==0.5.2

To create relax env:

conda create --name relax python=3.8
conda activate relax
conda install -c conda-forge openmm pdbfixer libstdcxx-ng openmmforcefields openff-toolkit ambertools=22 compilers biopython==1.78

to run:

conda activate dynamicbind
export MKL_THREADING_LAYER=GNU #needed this as I have an AMD CPU
python run_single_protein_inference.py protein.pdb ligand.csv --savings_per_complex 40 --inference_steps 20 --header test --device 0 --paper --python /home/christian/anaconda3/envs/dynamicbind/bin/python --relax_python /home/christian/anaconda3/envs/relax/bin/python

The error I get:

...
Skipped 0 complexes
Results are in results/test
inference complete.
0%| | 0/40 [00:00<?, ?it/s]No compatible CUDA device is available
No compatible CUDA device is available
2%|█ | 1/40 [00:03<02:33, 3.94s/it]No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
5%|██▏ | 2/40 [00:04<01:12, 1.91s/it]No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
No compatible CUDA device is available
15%|██████▌ | 6/40 [00:09<00:45, 1.34s/it]No compatible CUDA device is available
100%|███████████████████████████████████████████| 40/40 [00:12<00:00, 3.28it/s]
final step structure relax complete.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant