2.3. Install from pre-compiled C library TensorFlow, JAX JAX#

Note

Supported backends: TensorFlow TensorFlow, JAX JAX

DeePMD-kit provides pre-compiled C library package (libdeepmd_c.tar.gz) in each release. It can be used to build the LAMMPS plugin and GROMACS patch, as well as many third-party software packages, without building TensorFlow and DeePMD-kit on one’s own. It can be downloaded via the shell command:

wget https://github.com/deepmodeling/deepmd-kit/releases/latest/download/libdeepmd_c.tar.gz
tar xzf libdeepmd_c.tar.gz

The library is built in Linux (GLIBC 2.17) with CUDA 12.2 (libdeepmd_c.tar.gz) or 11.8 (libdeepmd_c_cu11.tar.gz). It’s noted that this package does not contain CUDA Toolkit and cuDNN, so one needs to download them from the NVIDIA website.

2.3.1. Use Pre-compiled C Library to build the LAMMPS plugin, i-PI driver, and GROMACS patch#

When one installs DeePMD-kit’s C++ interface, one can use the CMake argument DEEPMD_C_ROOT to the path libdeepmd_c.

cd $deepmd_source_dir/source
mkdir build
cd build
cmake -DDEEPMD_C_ROOT=/path/to/libdeepmd_c -DCMAKE_INSTALL_PREFIX=$deepmd_root ..
make -j8
make install

Then the i-PI driver dp_ipi will be built and installed. One can also follow the manual Install LAMMPS and/or Install GROMACS.

DEEPMD_C_ROOT#

Type: Path

Prefix to the pre-compiled C library.