Skip to content

Update README.md #217

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
YutackPark merged 1 commit into from
May 17, 2025
Merged

Update README.md #217

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ SevenNet (Scalable EquiVariance-Enabled Neural Network) is a graph neural networ
> We will soon release a CUDA-accelerated version of SevenNet, which will significantly increase the speed of our pretrained models on [Matbench Discovery](https://matbench-discovery.materialsproject.org/).

> [!TIP]
> SevenNet supports NVIDIA's [CuEquivariance](https://github.com/NVIDIA/cuEquivariance) for acceleartion. In our benchmarks, we found that the CuEquivariance improves inference speed by a factor of three for the SevenNet-MF-ompa potential. See [Installation](#installation) for details.
> SevenNet supports NVIDIA's [cuEquivariance](https://github.com/NVIDIA/cuEquivariance) for acceleartion. In our benchmarks, we found that the cuEquivariance improves inference speed by a factor of three for the SevenNet-MF-ompa potential. See [Installation](#installation) for details.

## Features
- Pretrained GNN interatomic potential and fine-tuning interface
Expand Down Expand Up @@ -111,7 +111,7 @@ You can find our legacy models in [pretrained_potentials](./sevenn/pretrained_po
### Requirements
- Python >= 3.8
- PyTorch >= 2.0.0, PyTorch =< 2.5.2
- [Optional] CuEquivariance >= 0.4.0
- [Optional] cuEquivariance >= 0.4.0

For CUDA version, refer to PyTorch's compatibility matrix: https://github.com/pytorch/pytorch/blob/main/RELEASE.md#release-compatibility-matrix

Expand All @@ -124,11 +124,11 @@ pip install sevenn
pip install git+https://github.com/MDIL-SNU/SevenNet.git # for the latest main branch
```

For CuEquivariance
For cuEquivariance
```bash
pip install sevenn --extra cueq12 # cueq11 for CUDA version 11.*
```
CuEquivariance can be enabled using `--enable_cueq` when training with `sevenn` via command line, and by setting `enable_cueq=True` in the `SevenNetCalculator`.
The cuEquivariance can be enabled using `--enable_cueq` when training with `sevenn` via command line, and by setting `enable_cueq=True` in the `SevenNetCalculator`.

## Usage<a name="usage"></a>
### ASE calculator<a name="ase_calculator"></a>
Expand Down