MDescriptor

MDescriptor is a batch-oriented periodic atomic-descriptor library. The numerical kernels are implemented in C++17 and all Python descriptors share one input/result/lifecycle contract.

MDescriptor 是面向批量周期结构的原子描述符库。数值核心使用 C++17；所有 Python 描述符共享统一的输入、结果和生命周期契约。

Layout / 布局

The public namespace is intentionally small:

src/mdescriptor/             installable package
src/mdescriptor/core/         Descriptor, StructureBatch, DescriptorResult
src/mdescriptor/descriptors/
  standalone/                 no model required (ACE, matrices/, many_body/, local/, rotational/)
  model_backed/               graph seam plus NEP, DPA4, DPA4C
src/mdescriptor/models/assets/ packaged, hash-verified model resources
tests/golden/              descriptor-owned, benchmark-independent accuracy fixtures
scripts/benchmarking/      controlled local benchmark runners
benchmarks/                local-only benchmark snapshots (ignored by Git)

standalone descriptors never require a model file. model_backed descriptors always resolve a model resource (a packaged default or an explicit model= path). There are no network downloads or implicit model discovery.

standalone 中的描述符不需要模型文件；model_backed 中的 NEP、DPA4、DPA4C 始终解析模型资源（内置默认模型或显式 model= 路径）。不会联网下载，也不会扫描目录自动发现模型。

Installation / 安装

The base package requires Python 3.10+, NumPy and array-api-compat. ASE is optional and is only needed for StructureBatch.from_ase or direct ASE input. Sparse output is provided as SciPy CSR by the optional sparse extra.

基础包需要 Python 3.10+、NumPy 和 array-api-compat。ASE 只在使用 StructureBatch.from_ase 或直接传入 ASE 对象时需要；稀疏输出由可选的 sparse extra 提供。

python -m pip install .
python -m pip install ".[ase]"
python -m pip install ".[sparse]"

DPA4 and DPA4C are CPU-only implementations. Their official .pt checkpoints are parsed by the bundled restricted NumPy reader without importing or installing Torch; the supported default graphs run through the C++17/OpenMP backend and specialised configurations retain the NumPy fallback. No network model download is performed.

性能说明：DPA4 native 路径现在使用固定大小分块的 SGEMM、可复用的计算工作区，并只为每条边计算一次 attention logit；DPA4C 的类型对 MLP 采用每个 calculator 实例独立的惰性缓存。OpenBLAS 仅作为构建依赖，官方 wheel 会内置 prefixed 的 OpenBLAS 及其运行时闭包和许可文件，安装后不需要 scipy-openblas32、Torch 或其他新增运行时依赖。大批量独立结构按结构分块消费，以控制峰值内存。

本地可复现实测（脚本默认 2 次预热、5 次稳态；基线为提交 334e159）可用以下命令生成完整 JSON 报告；报告同时记录构造、首次调用、p95、线程扫描、RSS 和 profiling 构建中的私有阶段计时：

python scripts/benchmark_dpa_native.py \
  --descriptor DPA4 --dataset carbon_dataset_pbc --limit-frames 50 \
  --threads 1,4,32 --output /tmp/dpa4-native.json

当前 Linux 主机的候选测量中，DPA4 的 41 原子小批 median 约为 0.47 s（1 线程）和 0.30 s（32 线程）；50 帧/3200 原子单次吞吐约为 57.8 s（1 线程）和 21.6 s（32 线程）。这些数字用于同机 A/B 门禁，不代表跨机器性能保证。

Input contract / 输入契约

import numpy as np
from mdescriptor import StructureBatch

batch = StructureBatch(
    numbers=np.array([1, 8], dtype=np.int32),
    positions=np.array([[0., 0., 0.], [1., 0., 0.]]),
    cells=np.eye(3, dtype=np.float64)[None] * 12,
    pbc=np.ones((1, 3), dtype=np.int32),
    offsets=np.array([0, 2], dtype=np.int64),
    ids=("water-0",),
)

StructureBatch validates contiguous arrays, finite positions/cells, nonsingular cells, positive atomic numbers, monotonic offsets and fully periodic pbc == (1, 1, 1). ASE conversion is available through StructureBatch.from_ase(...).

Descriptor API / 描述符 API

Algorithm classes live under mdescriptor.descriptors and use canonical names:

from mdescriptor.descriptors import SOAP

soap = SOAP(species=[1, 8], r_cut=4.5, n_max=4, l_max=3, average="off")
result = soap.compute(batch)

assert result.level == "atom"
assert result.values.shape == (batch.atoms, soap.feature_count)
assert len(result.labels) == result.values.shape[1]

with SOAP(species=[1, 8], r_cut=4.5, n_max=2, l_max=2) as descriptor:
    result = descriptor.compute(batch)

ACE (Atomic Cluster Expansion) is available as a standalone atom-level descriptor. Its public options mirror the standard ACE1.jl Utils.rpi_basis path and accept atomic numbers or chemical symbols:

from mdescriptor.descriptors import ACE

ace = ACE(species=["H", "O"], N=3, maxdeg=8, rcut=5.0)
result = ace.compute(batch)

Every descriptor has idempotent close(), a closed property and synchronous context-manager support. Computing after close raises ClosedDescriptorError. Instances are synchronous and not promised to be thread-safe.

每个描述符都提供幂等 close()、closed 属性和同步上下文管理器；关闭后计算会抛出 ClosedDescriptorError。实例是同步的，不承诺线程安全。

DescriptorResult contains values, level (atom, structure, or pair), structure_ids, row offsets, stable labels, JSON-safe metadata, per-row samples, and feature_count. The descriptor itself also retains the latest JSON-safe metadata and its configuration after close(). The standard shapes are (N, F), (S, F), and (P, F) for atom, structure and pair outputs respectively.

Registry / 注册表

Built-ins come from one explicit immutable specification list. Imports are lazy and no decorator or filesystem scan is used.

import mdescriptor
from mdescriptor.descriptors import SOAP

print(mdescriptor.list_descriptors())
soap = SOAP(species=[1, 8], r_cut=4.5, n_max=2, l_max=2)
rebuilt = mdescriptor.create_descriptor(soap.configuration)

child = mdescriptor.DescriptorRegistry(parent=mdescriptor.builtin_registry)
child.register(my_spec)

The built-in list separates AssetPolicy.NONE, OPTIONAL (for example MTP potentials), and REQUIRED (NEP/DPA4/DPA4C). The root package exposes stable contracts, registry functions and errors only; algorithm implementations are not re-exported from the root.

Model resources / 模型资源

ModelResource, ModelResolver, LoadedModel and ModelSession are the shared model-resource seam. Resolution is explicit, local and checksum-aware:

from pathlib import Path
from mdescriptor.descriptors import DPA4
from mdescriptor import ExecutionOptions

dpa4 = DPA4(
    model=Path("/path/to/official-checkpoint.pt"),
    execution=ExecutionOptions(device="cpu"),
)
result = dpa4.compute(batch)

The DPA4/DPA4C checkpoint readers and NumPy reference path remain isolated vendor adapters. The default inference graphs are lowered into the private mdescriptor._native C++17/OpenMP extension.

Development / 开发

.venv/bin/python -m pip install -e . --no-build-isolation
.venv/bin/python -m pytest --import-mode=importlib tests -q

The extension is private (mdescriptor._native). C++ shared math and batch helpers live in named headers under cpp/include/mdescriptor/detail/.

MDescriptor is licensed under the GNU General Public License v3.0; see LICENSE.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mdescriptor-0.2.2.tar.gz (26.3 MB view details)

Uploaded Aug 28, 2026 Source

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

mdescriptor-0.2.2-cp314-cp314-win_amd64.whl (33.7 MB view details)

Uploaded Aug 28, 2026 CPython 3.14Windows x86-64

mdescriptor-0.2.2-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (35.4 MB view details)

Uploaded Aug 28, 2026 CPython 3.14manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

mdescriptor-0.2.2-cp314-cp314-macosx_11_0_arm64.whl (33.2 MB view details)

Uploaded Aug 28, 2026 CPython 3.14macOS 11.0+ ARM64

mdescriptor-0.2.2-cp313-cp313-win_amd64.whl (33.5 MB view details)

Uploaded Aug 28, 2026 CPython 3.13Windows x86-64

mdescriptor-0.2.2-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (35.4 MB view details)

Uploaded Aug 28, 2026 CPython 3.13manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

mdescriptor-0.2.2-cp313-cp313-macosx_11_0_arm64.whl (33.2 MB view details)

Uploaded Aug 28, 2026 CPython 3.13macOS 11.0+ ARM64

mdescriptor-0.2.2-cp312-cp312-win_amd64.whl (33.5 MB view details)

Uploaded Aug 28, 2026 CPython 3.12Windows x86-64

mdescriptor-0.2.2-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (35.4 MB view details)

Uploaded Aug 28, 2026 CPython 3.12manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

mdescriptor-0.2.2-cp312-cp312-macosx_11_0_arm64.whl (33.2 MB view details)

Uploaded Aug 28, 2026 CPython 3.12macOS 11.0+ ARM64

mdescriptor-0.2.2-cp311-cp311-win_amd64.whl (33.5 MB view details)

Uploaded Aug 28, 2026 CPython 3.11Windows x86-64

mdescriptor-0.2.2-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (35.3 MB view details)

Uploaded Aug 28, 2026 CPython 3.11manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

mdescriptor-0.2.2-cp311-cp311-macosx_11_0_arm64.whl (33.2 MB view details)

Uploaded Aug 28, 2026 CPython 3.11macOS 11.0+ ARM64

mdescriptor-0.2.2-cp310-cp310-win_amd64.whl (33.5 MB view details)

Uploaded Aug 28, 2026 CPython 3.10Windows x86-64

mdescriptor-0.2.2-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (35.3 MB view details)

Uploaded Aug 28, 2026 CPython 3.10manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

mdescriptor-0.2.2-cp310-cp310-macosx_11_0_arm64.whl (33.2 MB view details)

Uploaded Aug 28, 2026 CPython 3.10macOS 11.0+ ARM64

File details

Details for the file mdescriptor-0.2.2.tar.gz.

File metadata

Download URL: mdescriptor-0.2.2.tar.gz
Upload date: Aug 28, 2026
Size: 26.3 MB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for mdescriptor-0.2.2.tar.gz
Algorithm	Hash digest
SHA256	`5c55993668e2e1abedd4f0e8ba185cf77964d91593fd3e4a300dc610ebff13eb`
MD5	`4cd6373e7f0e2f96c61eea418370b7be`
BLAKE2b-256	`af7225a8de6f53c8279aa63bd131d03a7454ef17b7ea1c48d56b7dd6b6d374aa`

Algorithm	Hash digest
SHA256	`2c5ffeb834cfe89608b8b9734d55ae40c825fe301d1e6037a94447ccf82a50ef`
MD5	`0aae6044ea2d19e24baaf9ef5cc4aed2`
BLAKE2b-256	`0cd224dcac48c43bb2c0c814a07562de7207e6e770f8debbece9a6a67369f98b`

Algorithm	Hash digest
SHA256	`7429d4dd7ade8d43c7271d5edf1097459ea04f3959c0ed1858ae07906013ed1c`
MD5	`77ba9c3acf53636ef9fb530925bbd142`
BLAKE2b-256	`ae1454506605813cb76d379eb4852fff527370ec34d582ab0922e93c66bb433e`

Algorithm	Hash digest
SHA256	`1f2273a03e516158452563fffb9734c6c973be8a3072d13bb416950f742c927d`
MD5	`a4d825b407db42a56bf331e1473c1153`
BLAKE2b-256	`4439d416bd68e1c3b0c2d9d22170573102d3cc560212cb050238885993384107`

Algorithm	Hash digest
SHA256	`95184165a8310f17191e4f7848adab5de5d83534d7b3a0709439417c5e7dce17`
MD5	`e057ea97c294cdfff51de86585a18229`
BLAKE2b-256	`ebd481d4335d29ee785910dd45fa1728aa09882f69c42472b78bfda5ae20903c`

Algorithm	Hash digest
SHA256	`7b85e28d4d7301ef1def02050c8a66c53e91593b0d8947f5846a1906f79739b2`
MD5	`fc3d88b1bfcfb9ba0ce7fcc1bc2d91cd`
BLAKE2b-256	`1f3d2bbdce1ba297dd75dd7074a8510730384b23935f3cabe972ba5c8c88aeca`

Algorithm	Hash digest
SHA256	`b1ea3be89defea1cf5f733f58dd51ce2052f024fd5dbadf7f630bf1638919a76`
MD5	`82fa9e76b880cf2959ca1a6f3e04d99c`
BLAKE2b-256	`b0466f383a2f8041774ea45c2d93a3b445849bc2d0ebd80c02ebff14df513e7f`

Algorithm	Hash digest
SHA256	`7744b7f4bcd5e8ff36d8b6d04d1b27d20ec1ced7f0bf7200c5ec62422d3f92a9`
MD5	`cbd7273a8699be8211b79b5e6a8b4315`
BLAKE2b-256	`cb1576ee2ec2d72122264640af30f3eeef278ef97540cc1836ee6cd4b3f97b47`

Algorithm	Hash digest
SHA256	`b857708b09da6b7645ba96a0e59d976a452931bdb5e9c7606391b86a885e7310`
MD5	`1850eaaf95da10f88f454fc76454e0b6`
BLAKE2b-256	`f79c08fb1bfb24a5e34037d8e5e305be8bbf0648c3120a8c6c6aa98ded391dd8`

Algorithm	Hash digest
SHA256	`dcc440758852c9815afcdabb4b54bbaaf6c57b9c50980508bc6f45e9d29eb4ee`
MD5	`a5ab30e7f4edbb11b013fa1248173f64`
BLAKE2b-256	`ccd13193ad0aa4b0315e752759cabf3549da556b280b0a9ec1942145db7ee80e`

Algorithm	Hash digest
SHA256	`a4b629f003dcdab483651db235b9b206c7dddb221a24002258215affa695b4fb`
MD5	`c41bd1ca8dba0dfaebd8e9b939482d49`
BLAKE2b-256	`6186c5f50dfffe2707f8de296b0f9b1908c29c01aa629adacbac2d5f1f5f335e`

Algorithm	Hash digest
SHA256	`7362d4f3a89dc0e9c3263e0a4c12e50e3a1d51be156340b443c69a5b6d029b93`
MD5	`d2e8185e0630732913491e645cae9bc0`
BLAKE2b-256	`b0dbc0145a876b7fec23e1f98227fa770ccfb57ec687a0a44f1978b294ae2f22`

Algorithm	Hash digest
SHA256	`890c70f7b666ae71e0904f2d06ad16add5872ff3540ca0ac2438d2df2b1c9488`
MD5	`807cb2368a2d452d5c75c6c4e06f093f`
BLAKE2b-256	`65459ba3ea5627547a4382eca8b6ea12f23d751ee1b0636a41c8424b4376a65b`

Algorithm	Hash digest
SHA256	`8620af76cd92c7b7e91b5d3315f233ee4bc7d772ea4bb098e7bc170782b3ea00`
MD5	`f32d48414f826c5963023f4f7d50c5e0`
BLAKE2b-256	`4b0b864296fd6dadc355142ea5903232cf050c2ecbc18840f80ad4036b5e9cb7`

Algorithm	Hash digest
SHA256	`729330eb223cd6a8fe7b1c59cefbf81472fd81f135b1dbd923236cba68550e31`
MD5	`1d2f7b17e34ab64221020b10e360162b`
BLAKE2b-256	`77150af26da36926f3e169b25b30e20e1e41c2bd8c6bdb59fc73a384657adf6b`

Algorithm	Hash digest
SHA256	`ad53cb89c1af0788150758acb9846cc043838b253f330a01a9c2a0c1859e830a`
MD5	`e340da4aec696ab1699766c0a0efb48b`
BLAKE2b-256	`31fced260afbae6d419b3b9cb0846a8828190bc531cca0c8298ffa4c5b5d0758`

MDescriptor 0.2.2

MDescriptor

Layout / 布局

Installation / 安装

Input contract / 输入契约

Descriptor API / 描述符 API

Registry / 注册表

Model resources / 模型资源

Development / 开发

Key dates

1 maintainer

License

Requires

Provides Extra

Download files

Source Distribution

Built Distributions

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes