Orbax provides common checkpointing and persistence utilities for JAX users

Second Order Optimization and Curvature Estimation with K-FAC in JAX.

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Node Equivariant Message Passing Neural Network

Differentiable, Hardware Accelerated, Molecular Dynamics

cuEquivariance is a math library that is a collective of low-level primitives and tensor ops to accelerate widely-used models, like DiffDock, MACE, Allegro and NEQUIP, based on equivariant neural n…

A Universal Neural Network Solver for The Schrödinger Equation

Implementation of Forward Laplacian algorithm in JAX

For advanced physics-driven combined with neural network enhancement force field.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Quantum chemistry and solid state physics software package

i-PI: a universal force engine

Deep learning quantum Monte Carlo for electrons in real space

Pytorch implementation of KFAC - this is a port of https://github.com/tensorflow/kfac/

Public development project of the LAMMPS MD software package

add the influence of external field to REANN model

Yaolong Zhang's great work

Self-describing sparse tensor data format for atomistic machine learning and beyond

“连续八年成为全世界最受喜爱的语言，无 GC 也无需手动内存管理、极高的性能和安全性、过程/OO/函数式编程、优秀的包管理、JS 未来基石" — 工作之余的第二语言来试试 Rust 吧。本书拥有全面且深入的讲解、生动贴切的示例、德芙般丝滑的内容，这可能是目前最用心的 Rust 中文学习教程 / Book

Generating Deep Potential with Python

百度网盘不限速客户端, golang + qt5, 跨平台图形界面

Curve fitting comparison between Adam and L-BFGS optimizer

Fast and flexible nonadiabatic molecular dynamics in Julia!

MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.