Stars
Model Context Protocol Servers
Lightweight coding agent that runs in your terminal
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
Pocket Flow: Codebase to Tutorial
An elegant PyTorch deep reinforcement learning library.
Qiskit is an open-source SDK for working with quantum computers at the level of extended quantum circuits, operators, and primitives.
Sphinx theme from Read the Docs
The fastest and most memory efficient lattice Boltzmann CFD software, running on all GPUs and CPUs via OpenCL. Free for non-commercial use.
A library for scientific machine learning and physics-informed learning
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods
A differentiable PDE solving framework for machine learning
A simple and well styled PPO implementation. Based on my Medium series: https://medium.com/@eyyu/coding-ppo-from-scratch-with-pytorch-part-1-4-613dfc1b14c8.
A coupling library for partitioned multi-physics simulations, including, but not restricted to fluid-structure interaction and conjugate heat transfer simulations.
Fast and simple fluid simulator in Julia
Implementation of the Deep Deterministic Policy Gradient (DDPG) using PyTorch
Firedrake is an automated system for the portable solution of partial differential equations using the finite element method (FEM)
PyTorch implementation of DDPG algorithm for continuous action reinforcement learning problem.
Unstructured Compressible Navier Stokes 3D code (UCNS3D)
Exascale simulation of multiphase/physics fluid dynamics
A code for fast, massively-parallel direct numerical simulations (DNS) of canonical flows