Source: https:\/\/github.com\/lmuellender\/gmx-nnpot-tools<\/a>, https:\/\/doi.org\/10.48550\/arXiv.2604.21441<\/a><\/p>\n\n\n\n OS, AlmaLinux 8; GPU, NVIDIA TITAN-RTX.<\/p>\n\n\n\ngit clone https://github.com/lmuellender/gmx-nnpot-tools.git\ncd gmx-nnpot-tools\nconda env create -f environment.yaml \nconda activate nnpot\n# To use NVIDIA TITAN-RTX\npip install torch==2.7 --upgrade --index-url https://download.pytorch.org/whl/cu128\nconda install conda-forge::jupyterlab\ncd ..\ngit clone https://github.com/chemle/emle-engine.git\ncd emle-engine\nconda install conda-forge::ambertools \\\n conda-forge::ase \\\n conda-forge::loguru \\\n conda-forge::psutil \\\n conda-forge::pygit2 \\\n conda-forge::pyyaml \\\n conda-forge::xtb-python \\\n --no-update-deps\n\npip install deepmd-kit --no-deps\npip install -e .\n\ncd ../gmx-nnpot-tools\nsed -i 's/self\\.model(atomic_numbers, charges_mm, positions_nn, positions_mm, qm_charge)/self.model(atomic_numbers, charges_mm, positions_nn, positions_mm, None, qm_charge)/' \\\n /home/user/data/gromacs/NNPOT/gmx-nnpot-tools/models/gmx_emle.py\njupyter-lab --no-browser --ip=xxx.xx.xxx.xx\n# Open export.ipynb, conduct the script, and we got ani2x.pt, ani2x_nnpops.pt, mace.pt, emle_ani2x_ala2.pt, and emle_mace_ala2.pt in the "models" directory.\n<\/pre>\n\n\n\n
Gromacs 2026.2\u306e\u30a4\u30f3\u30b9\u30c8\u30fc\u30eb<\/h2>\n\n\n\n
\nconda activate nnpot\nwget https://ftp.gromacs.org/gromacs/gromacs-2026.2.tar.gz\nwget https://www.fftw.org/fftw-3.3.10.tar.gz\ntar xvzf gromacs-2026.2.tar.gz\ncd gromacs-2026.2\nmkdir build_nnpot && cd build_nnpot\nexport FFTW_PATH=${BASEDIR}/fftw-3.3.10.tar.gz\nconda install cmake\nexport Torch_DIR=$(python -c "import torch; print(torch.utils.cmake_prefix_path)")/Torch\ncmake .. -DCMAKE_PREFIX_PATH="${Torch_DIR};${CONDA_PREFIX}"\\\n -DCMAKE_INSTALL_PREFIX=/usr/local/gromacs/2026.2_cuda_torch27 -DGMX_GPU=CUDA -DGMX_USE_CUFFTMP=OFF\\\n -DGMX_NNPOT=TORCH -DCAFFE2_USE_CUDNN=ON -DCAFFE2_USE_CUSPARSELT=ON -DUSE_CUDSS=ON\\\n -DPython_EXECUTABLE=/home/user/miniforge3/envs/nnpot/bin/python -DGMX_BUILD_OWN_FFTW=ON\\\n -DGMX_BUILD_OWN_FFTW_URL=${FFTW_PATH} -DCMAKE_CUDA_COMPILER=/usr/local/cuda-12.9/bin/nvcc\\\n -DCMAKE_CUDA_IMPLICIT_LINK_DIRECTORIES=/usr/local/cuda-12.9/targets/x86_64-linux/lib\\\n -DCUDA_TOOLKIT_ROOT_DIR=/usr/local/cuda-12.9 -DGMX_INSTALL_NBLIB_API=OFF\\\n -DCUDA_NVRTC_SHORTHASH=c3430e8b -DREGRESSIONTEST_DOWNLOAD=ON\\\n -Dnvtx3_dir=/usr/local/cuda-12.9/targets/x86_64-linux/include/nvtx3 -DGMX_USE_TNG=OFF\nmake -j 37\nmake check -j 37\n# 100% tests passed, 0 tests failed out of 98\nsudo make install\nsource /usr/local/gromacs/2026.2_cuda_torch27/bin/GMXRC\ngmx --version\n\n :-) GROMACS - gmx, 2026.2 (-:\n\nExecutable: /usr/local/gromacs/2026.2_cuda_torchcu129/bin/gmx\nData prefix: /usr/local/gromacs/2026.2_cuda_torchcu129\nCommand line:\n gmx --version\n\nGROMACS version: 2026.2\nPrecision: mixed\nMemory model: 64 bit\nMPI library: thread_mpi\nMPI version: built in\nOpenMP support: enabled (GMX_OPENMP_MAX_THREADS = 128)\nGPU support: CUDA\nNBNxM GPU setup: super-cluster 2x2x2 / cluster 8 (cluster-pair splitting on)\nSIMD instructions: AVX_512\nCPU FFT library: fftw-3.3.10-sse2-avx-avx2-avx2_128-avx512\nGPU FFT library: cuFFT\nMulti-GPU FFT: none\nRDTSCP: enabled\nTNG support: enabled\nHwloc support: disabled\nTracing support: disabled\nColvars support: enabled (version 2025-10-13)\nCP2K support: disabled\nTorch support: enabled (version 2.7.0)\nPlumed support: enabled\nC compiler: /home/user/miniforge3/envs/nnpot/bin/x86_64-conda-linux-gnu-cc GNU 14.3.0\nC compiler flags: -fexcess-precision=fast -funroll-all-loops -march=skylake-avx512 -Wno-missing-field-initializers -D_GLIBCXX_USE_CXX11_ABI=1 -O3 -DNDEBUG\nC++ compiler: /home/user/miniforge3/envs/nnpot/bin/x86_64-conda-linux-gnu-c++ GNU 14.3.0\nC++ compiler flags: -fexcess-precision=fast -funroll-all-loops -march=skylake-avx512 -Wno-missing-field-initializers -D_GLIBCXX_USE_CXX11_ABI=1 -Wno-stringop-truncation -Wno-cast-function-type-strict SHELL:-fopenmp -O3 -DNDEBUG\nBLAS library: External - detected on the system\nLAPACK library: External - detected on the system\nCUDA compiler: /usr/local/cuda-12.9/bin/nvcc (NVIDIA 12.9.86)\nCUDA compiler flags: -D_FORCE_INLINES -DONNX_NAMESPACE=onnx_c2 -gencode arch=compute_50,code=sm_50 -gencode arch=compute_52,code=sm_52 -gencode arch=compute_60,code=sm_60 -gencode arch=compute_61,code=sm_61 -gencode arch=compute_70,code=sm_70 -gencode arch=compute_75,code=sm_75 -gencode arch=compute_80,code=sm_80 -gencode arch=compute_86,code=sm_86 -gencode arch=compute_89,code=sm_89 -gencode arch=compute_90,code=sm_90 -gencode arch=compute_100,code=sm_100 -gencode arch=compute_120,code=sm_120 -gencode arch=compute_50,code=compute_50 -gencode arch=compute_120,code=compute_120 -Xcudafe --diag_suppress=cc_clobber_ignored,--diag_suppress=field_without_dll_interface,--diag_suppress=base_class_has_different_dll_interface,--diag_suppress=dll_interface_conflict_none_assumed,--diag_suppress=dll_interface_conflict_dllexport_assumed,--diag_suppress=bad_friend_decl --expt-relaxed-constexpr --expt-extended-lambda -O3 -DNDEBUG -use_fast_math -static-global-template-stub=false -Xptxas=-warn-double-usage -Xptxas=-Werror -diag-suppress=177 -O3 -DNDEBUG\nCUDA targets: 50;52-real;60-real;61-real;70-real;75-real;80-real;86-real;89-real;90-real;100-real;120\nCUDA driver: 13.0\nCUDA runtime: 12.90\nNVSHMEM: disabled<\/pre>\n\n\n\nTest (N<\/em>-acetyl-L-alanine methylamide in water\uff09
<\/h2>\n\n\n\n