Installation¶
First create a conda environment with all of the required dependencies:
conda env create -f environment.yaml
conda activate emle
Note
If you wish to use librascal for
delta-learning you will need to use the environment_rascal.yaml
file instead.
Note
If you wisth to use emle-engine
with OpenMM
, please use the
environment_sire.yaml
file instead. (This is required as sire
provides the interface between emle-engine
and OpenMM
.)
For GPU functionality, you will need to install appropriate CUDA drivers on
your host system. (This doesn’t come with cudatoolkit
from conda-forge
.)
Finally, install emle-engine
into the active environment:
pip install .
If you are developing and want an editable install, use:
pip install -e .