laolanllx

same error here, running successfully before, with ubuntu 20.04, CUDA 11.5 and DRIVER 510.85.02

> same error here, running successfully before, with ubuntu 20.04, CUDA 11.5 and DRIVER 510.85.02 solved, I used the wrong python. Changed the python path solved this.

> Hi @laolanllx ! > > Thanks for your quick feeedback. Did you mean you were running AlphaFold in a python environment and used Python from your system environment? >...

> Hi @laolanllx! Did you change any of the Dockerfile settings to match your CUDA version and OS? I just did it and instead of solving the problem, I got...

> Hi @laolanllx! Did you change any of the Dockerfile settings to match your CUDA version and OS? I just did it and instead of solving the problem, I got...

> I believe this is because [the image was removed, as per this comment](https://github.com/NVIDIA/nvidia-docker/issues/1735#issuecomment-1455744048). > > On Ubuntu 20.04 the following should work: > > `docker run --rm --gpus all...

> > I tried to run AlphaFold latest version on a new machine with **GPU RTX4090, CUDA version 11.8 (downgraded from 12.2), Ubuntu 22.04 LTS.** I used anaconda3 to build...

> Have you tried the solution? #210 I test the gpu and it got gpu as expected. ``` Python 3.10.14 | packaged by conda-forge | (main, Mar 20 2024, 12:45:18)...

> According to the last comment from fatpmeireles, > > ```shell > $ /opt/colabfold-20240509/localcolabfold/colabfold-conda/bin/python3.10 -m pip install --upgrade "jax[cuda12]" -f https://storage.googleapis.com/jax-releases/jax_releases.html > $ /opt/colabfold-20240509/localcolabfold/colabfold-conda/bin/python3.10 -m pip install "colabfold[alphafold] @ git+https://github.com/sokrypton/ColabFold"...

> > After I run these two pip commends and run colabfold, the server crashed. > > Please describe the error log here with the return value of `echo $LD_LIBRARY_PATH`....