Skip to content

updated lammps docs - #797

Open
jnsLs wants to merge 1 commit into
devfrom
jl/lammps
Open

updated lammps docs#797
jnsLs wants to merge 1 commit into
devfrom
jl/lammps

Conversation

@jnsLs

@jnsLs jnsLs commented Aug 17, 2026

Copy link
Copy Markdown
Collaborator

updated lammps documentation to match schnetpack requirements and latest stable lammps release

Copilot AI lite review requested due to automatic review settings August 17, 2026 20:51

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Updates the LAMMPS interface “how-to” documentation to reflect current SchNetPack requirements and a recent LAMMPS stable release, including refreshed environment setup and build instructions.

Changes:

  • Refreshes dependency requirements (Python/SchNetPack/PyTorch) and adds clearer compiler/CMake/GPU notes.
  • Updates the recommended conda environment setup and the example LAMMPS stable branch checkout.
  • Switches the build instructions to a CMake-based build invocation and expands configuration examples.
Suppressed comments (2)

examples/howtos/lammps.rst:20

  • Use the correct project capitalization here as well; the docs elsewhere refer to "PyTorch" (see docs/getstarted.rst:10).
Make sure that standalone CUDA toolkit and the CUDA version of pytorch match!

examples/howtos/lammps.rst:40

  • "Github" should be spelled "GitHub" (this is the standard capitalization and is used elsewhere in the project).
Please download LAMMPS directly from Github. We recommend to check out a stable release

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

* **CUDA** 11.7
* **cuDNN**
* **python** 3.9 with **schnetpack** 2.0, **pytorch** 1.13, and **mkl-include**
* **python** >= 3.12 with **schnetpack** >= 2.0, **pytorch** >= 2.5 and **mkl-include**
Comment on lines +26 to +28
We recommend to create a new environment for the matching version of pytorch-CUDA together
with schnetpack and all dependencies. The following commands set up a corresponding conda
environment called :code:`spk_lammps` (replace the CUDA version with the one you need)::
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants