Garden's Almanac of Matter Models ● verified, last 30 days ○ installed, not recently verified — not installed
No cluster has installed any checkpoint of this model yet.
Running this model
1# from a job or interactive session on a supported cluster:
2from rootstock import RootstockCalculator
3
4with RootstockCalculator(
5 cluster=YOUR_CLUSTER_ID, # eg, "perlmutter"
6 checkpoint="torchmdnet-et-oc20",
7 device="cuda",
8) as calc:
9 # model is now running in subprocess on compute node
10 atoms.calc = calc
11 atoms.get_potential_energy()
Environments
Rootstock runs each model family inside an isolated Python environment defined by a single file. This environment file includes the specific dependencies needed, plus a setup() function that loads the model and returns an ASE calculator. These files are usually almost identical for a given model family, but because of cluster-specific quirks (eg, an old CUDA driver) the dependencies and setup code can vary a bit.
torchmdnet_env.py
1# /// script
2# requires-python = ">=3.10"
3# dependencies = [
4# "ase>=3.22",
5# "torch>=2.0",
6# "torch-geometric",
7# "torch-scatter",
8# "torch-sparse",
9# "torch-cluster",
10# ]
11#
12# [tool.uv]
13# find-links = ["https://data.pyg.org/whl/torch-2.4.0+cu121.html"]
14# ///
15"""
16TorchMD-Net environment for Rootstock.
17
18TorchMD-Net provides equivariant transformer architectures for molecular
19dynamics. Includes pretrained universal models (e.g., ET-OC20).
20
21Models:
22 - Path to a local .ckpt file, or a HuggingFace repo ID.
23 - Example pretrained: "tensorfield/ET-OC20" (inorganic) — not universal.
24
25Note: TorchMD-Net's primary use case is organic/biomolecular MD. For
26inorganic universal potentials, prefer TensorNet or M3GNet.
27"""
28
29CHECKPOINTS = {
30 "torchmdnet-et-oc20": "tensorfield/ET-OC20",
31}
32
33
34def setup(checkpoint: str, device: str = "cuda"):
35 """
36 Load a TorchMD-Net calculator.
37
38 Args:
39 checkpoint: Canonical checkpoint id, must be a key of CHECKPOINTS.
40 device: PyTorch device string (e.g., "cuda", "cpu").
41
42 Returns:
43 ASE-compatible calculator.
44 """
45 import torch
46 from torchmdnet.calculators import External
47
48 calc = External(CHECKPOINTS[checkpoint], device=device)
49 return calc
50
51
Built on Perlmutter: 2026-05-13
Couldn't load the current environments from Rootstock.