2.9. Easy install the latest development version#

DeePMD-kit is actively developed in the devel branch. The documentation of the latest version matches the devel branch.

The following is the way to install the pre-compiled packages without building from source. All of them are built with GitHub Actions.

2.9.1. Install with docker#

The devel tag is used to mark the latest development version with CUDA 12.2 support:

docker pull ghcr.io/deepmodeling/deepmd-kit:devel

For CUDA 11.8 support, use the devel_cu11 tag.

2.9.2. Install with pip#

Follow the documentation for the stable version, but add --pre and --extra-index-url options like below:

pip install -U --pre deepmd-kit[gpu,cu12,lmp,torch] --extra-index-url https://deepmodeling.github.io/deepmd-kit/simple

2.9.3. Download pre-compiled C Library TensorFlow#

Note

Supported backends: TensorFlow TensorFlow

The pre-comiled C library can be downloaded from here, or via a shell command:

wget https://nightly.link/deepmodeling/deepmd-kit/workflows/package_c/devel/libdeepmd_c-0-libdeepmd_c.tar.gz.zip && unzip libdeepmd_c-0-libdeepmd_c.tar.gz.zip

2.9.4. Pre-release conda-forge packages#

Pre-release conda-forge packages are in conda-forge/label/deepmd-kit_dev or conda-forge/label/deepmd-kit_rc channels, other than the conda-forge channel. See conda-forge documentation for more information.