Stars
Agentic Design Patterns: A Hands-On Guide to Building Intelligent Systems by Antonio Gulli
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!
A lightweight framework for building Physics-Informed Neural Networks (PINNs) with symbolic PDE definitions using SymPy and automatic differentiation in PyTorch. It provides flexible neural archite…
Diffusion-based image restoration & inverse problems; implementations of DiffPIR, DPS, RePaint, DDRM for inpainting, CT, and deblurring.
Fast CUDA implementation of (differentiable) soft dynamic time warping for PyTorch
LLM with Tool call on top of existing rock physics libary (experimental)
A PyTorch native platform for training generative AI models
NVIDIA curated collection of educational resources related to general purpose GPU programming.
Materials for SCIML2024 workshop
Interactively inspect module inputs, outputs, parameters, and gradients.
Tutorial material for self-supervised blind-spot and blind-mask denoising for random and coherent noise, respectively.
Generating seismic data and associated labels to train deep learning networks.
Code repository for the CVPR 2023 paper "Explaining Image Classifiers with Multiscale Directional Image Representation"
NVIDIA Math Libraries for the Python Ecosystem
Follow this series to learn about CUDA programming from scratch with Python
Pytorch implementation of U-Net, R2U-Net, Attention U-Net, and Attention R2U-Net.
extensive Python library for rock physics modelling
Julia2925: learn a fast and intuitive programming language in two workdays.
Low memory, matrix free slovers useful for image scale optimization
A JupyterLab extension for displaying dashboards of GPU usage.
DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning