Skip to main content

ace-jax

PyPI Docs Tests License: MIT

Build, fit and evaluate Atomic Cluster Expansion (ACE) interatomic potentials in Python with JAX, on CPU or GPU. One pip install gives all of these functions.

Documentation: https://acesuit.github.io/ace-jax/. It contains the installation, a quickstart, tutorials, how-to guides, and the CLI and API reference.

What it does

  • Build a basis and fit it with one command. aj fit --order 3 --max-degree 10 --train train.xyz --out fit builds the symmetry-adapted ACE basis and fits it. The fit.yaml file that it writes runs the fit again.
  • Bayesian fits. Linear ACE uses Bayesian linear regression. The fit selects the energy, force and virial noise levels and the prior scale by maximising the evidence, so you do not set weights by hand.
    • An experimental hybrid ACE + Gaussian-process model (--m-per-species > 0) adds a calibrated set of uncertainty approximations (MAP, Laplace, Pathfinder, VI, NUTS). Most fits use the linear model, the default.
    • The linear model has POPS and ARD uncertainties.
    • ARD gives a conformally calibrated per-atom force uncertainty (forces_std, forces_q, a 3x3 forces_cov). aj calibrate recalibrates it on new labelled cells.
    • The fit can also learn the radial basis (--learn-radial).
  • Fast evaluation. ACECalculator and GPCalculator are ASE calculators, fast enough for molecular dynamics. GP and ARD models also predict energy_std and forces_std. export_lammps deploys a model to LAMMPS with lammps-jax. On CPUs, linear ACE runs in LAMMPS as a C++ kernel (aj export --platform cpu).
  • PACE potentials. ace-jax loads, evaluates and writes pacemaker .yace files.
  • Data in, data out. Training data is extended XYZ or a list of ase.Atoms. ace-jax converts stress labels to virials. aj eval writes predictions as extended XYZ, with an RMSE table for each configuration type.

Install

pip install ace-jax

Extras: "ace-jax[cuda]" (CUDA 12 JAX), "ace-jax[cuda13]" (CUDA 13 JAX and nvcc for the GPU kernel; NVIDIA driver 580 or later), "ace-jax[gp]" (the Pathfinder rung), "ace-jax[native]" (C++ code on CPUs: a neighbour list and the kernel), "ace-jax[lammps]" (LAMMPS export with lammps-jax) and "ace-jax[jaxmd]" (MD with JAX-MD).

To build a new basis, ace-jax needs the ace-jax-coupling wheel. This core dependency is available for Linux x86_64 and aarch64, macOS arm64 and Windows x64. On other platforms, fit and evaluate from an existing basis file. See Installation.

Quickstart

Fit a linear ACE model to labelled data, check it on a test set, and evaluate it:

aj fit --order 3 --max-degree 10 --train train.xyz --test test.xyz \
    --e0 lsq --opt lbfgs --out fit
aj eval --model fit/model.npz --data test.xyz --out predictions.xyz

Use the fitted model from Python:

import jax
jax.config.update("jax_enable_x64", True)

from ase.build import bulk
from ace_jax import ACECalculator

atoms = bulk("Si", "diamond", a=5.43, cubic=True)
atoms.calc = ACECalculator("fit/model.npz")
print(atoms.get_potential_energy(), atoms.get_forces())

The Quickstart runs this on a small silicon dataset. The tutorials are notebooks that run on a laptop CPU. Some of them come from the MLIP School 2026. For coding agents, skills/ace-jax/SKILL.md is a compact usage guide.

Performance and validation

Fits agree with the ACEfit design matrix and least-squares solution to 1e-8. PACE evaluation agrees with the ML-PACE C++ code and python-ace. CI checks both. The throughput benchmarks against LAMMPS ML-PACE are in docs/dev/benchmarks.md.

Contributing

See CONTRIBUTING.md for the development setup, tests and the reference-parity jobs. See the changelog for releases. ace-jax has the MIT licence and is part of ACEsuit.

Metadata

Release files for ace-jax 0.5.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ace-jax 0.5.3
File Size Uploaded Provenance Actions
ace_jax-0.5.3.tar.gz 419.7 kB With provenance Details for ace_jax-0.5.3.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for ace-jax 0.5.3
File Interpreter ABI Platform Actions
ace_jax-0.5.3-py3-none-any.whl Python 3 none any Details for ace_jax-0.5.3-py3-none-any.whl

Total release size: 890.4 kB

Release files / ace_jax-0.5.3.tar.gz

Download URL ace_jax-0.5.3.tar.gz
Size 419.7 kB
Tags Source
SHA-256 checksum
How to use checksums
b9b432a8bb0b616f9c124a6f5c11e730a1132e95f3d1d39a4dc4170a55ef0738
BLAKE2b-256 checksum
How to use checksums
b1376e8430013817928d9e1d3b03f8258b08789b593709ccc95aa6a13d9c4e62
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 5, 2026.

Transparency log

Release files / ace_jax-0.5.3-py3-none-any.whl

Download URL ace_jax-0.5.3-py3-none-any.whl
Size 470.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
1ba4440bf24ea850307cafaa9a94afa316274e71c23e0857e63f39796e55e428
BLAKE2b-256 checksum
How to use checksums
2c37d8f7509fcb529a6273120a8ea19e423647ebba16b7367563a3ae1527a1a2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 5, 2026.

Transparency log

Security for ace-jax 0.5.3

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for ace_jax-0.5.3.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 5, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page