openfold
openfold copied to clipboard
aqlaboratory
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
Docker container AttributeError: Did you mean: 'linear_a_p'? when trying to run multimer inference
Hello i build a docker container using the pl_upgrade tagged version of the git, to run openfold on our HPC system, which uses CUDA12. The building of the docker container...
Openfold works with later versions of pytorch, but the newer versions require c++17 for c++ extensions. This PR removes the manual standard specification and let pytorch do the work. They...
Fix versions to make pl_upgrades usable again: * avoid numpy 2 * use own cuda tools with proper explicit gcc version Should fix #494 and #477 and likely few other...
I have recently been trying to run OpenFold on NVIDIA H100 cards; however, I ran into problems from the main and pl_upgrades branches that prevented OpenFold from running. The first...
One of the tests seems to fail inconsistently. Changing nothing, you can re-run the test and it might pass the next time. Possibly something needs to be changed with precision...
I have tried several permutations to get openfold to install on my local machine, but no joy up to this point. Could use some help, as I need to install...
I’m encountering build errors when running python setup.py install in an OpenFold environment with PyTorch (version 2.1.2), CUDA 12.1, and g++ 12.2. The error occurs during the compilation of CUDA...
The current dependencies listed in environment.yml for OpenFold use strict version constraints (e.g., `package==version`). While this approach helps maintain compatibility, it can create challenges, especially for developers looking to integrate...
Using the environment.yml with unspecified numpy version causes it to pull in Numpy 2.1.0 as of today's date. This causes an issue with the specified version of deepspeed. Specifying Numpy...
Metadata
Owner
Metadata
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2