search

3dem / model-angelo

Automatic atomic model building program for cryo-EM maps
MIT License
110 stars 18 forks source link

Issue with RTX3080 #18

Open mbelouso opened 1 year ago

mbelouso commented 1 year ago

Initially the default pytorch isn't compatible with an RTX3080 GPU. So I edited the install.sh script:

Line 45 for my system should have read:

conda install pytorch torchvision torchaudio pytorch-cuda=11.7 cudatoolkit=11.7 -c pytorch-nightly -c nvidia

After doing this it works fine. Before the version of PyTorch wasn't compatible with the GPU.

Just a heads up for anyone else with a 3000 series card.

jamaliki commented 1 year ago

Hi,

That's interesting, what error message were you getting? Normally CUDA major releases should be interoperable.

Best, Kiarash.

mbelouso commented 1 year ago

The error I got was the following

NVIDIA GeForce RTX 3080 Ti with CUDA capability sm_86 is not compatible with the current PyTorch installation. The current PyTorch install supports CUDA capabilities sm_37 sm_50 sm_60 sm_70. If you want to use the NVIDIA GeForce RTX 3080 Ti GPU with PyTorch, please check the instructions at Start Locally | PyTorch 14

jelka71 commented 1 year ago

I had exactly the same issues with my A100 cards. The above command fixed it. Thanks @mbelouso

Also, first model-angelo installed without any error, but when I ran the job it was really slow. It turned out that the cpu version of pytorch was installed, due to missing environmental variables for CUDA (CUDA_HOME,CUDA_LIB and PATH to bin ...). To check if one has the cuda or much slower cpu branch of pytorch, run this:

conda list | grep "^pytorch " | grep -E 'cuda|cpu'

Best, Jesper

jamaliki commented 1 year ago

Dear @mbelouso and @jelka71

I would like to thank @mbelouso for first noticing the issue and offering a fix. I have now pinned this issue. I am thinking about the best way to perhaps automate this CUDA mismatch in the installation script. If any of you have ideas, please let me know.

Best, Kiarash.