nvidia-warp

A Python framework for GPU-accelerated simulation, robotics, and machine learning.

An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

A PyTorch Library for Accelerating 3D Deep Learning Research

Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods

GPU-optimized version of the MuJoCo physics simulator, designed for NVIDIA hardware.

XLB: Accelerated Lattice Boltzmann (XLB) for Physics-based ML

[CoRL 2025] Neural Robot Dynamics

Build 3D Gaussian Splatting from scratch with NVIDIA Warp in Python — CPU/GPU compatible, with a clean and minimalist design focused on learning modern graphics.

Taccel: Scaling-up Vision-based Tactile Robotics with High-performance GPU Simulation

Reinforcement learning in differentiable multiphysics simulation with NVIDIA Warp.

DEXTRAH

L​ibrary for using the models trained in PhysicsNeMo in Engineering and CFD workflows

FABRICS

Omniverse Kit sample for CAE use-cases

Exposes NVIDIA's Warp framework to Houdini.

Warp-based implementation of the SAP contact formulation

Examples calling Warp precompiled (cached) kernels directly from C++ (without Python)

Physical Engine for 2D rigid/soft simulation. We will use it to create 2D world model later.

GPU accelerated DEM code

CUDA Graphable Neural Networks for NVIDIA Warp