A C++ library for the creation of a large dataset of amino acid sidechain perturbations, own PDB Parser code included and some other things related.

High-performance graph algorithms optimized for Apple's MLX framework. Features random walks, biased random walks (Node2Vec), and neighbor sampling

HET: The HET Hetero-GNN Kernel Optimization and Code Generation Project

FPLearner is a DL-based tool to predict performance and accuracy of mixed-precision programs that can be used in dynamic precision tuners to save time.

Code for Large Graph Convolutional Network Training with GPU-Oriented Data Communication Architecture (accepted by PVLDB).The outdated write-up (https://arxiv.org/abs/2101.07956) explains engineering details, but only a portion of the functionality is migrated to this newer PyTorch version 1.8.0nightly (e152ca5).

Graph Attention-Guided Search for Dense Multi-Agent Pathfinding (AAAI-26)

GeoT: Tensor Centric Library for Graph Neural Network via Efficient Segment Reduction on GPU

❤️ CUDA/C++ GPU graph analytics simplified.

PySCF on IPU

This shows a basic implementation of the global nearest neighbour (GNN) multi target Tracker. Kalman filter is used for Tracking and Auction Algorithm for determining the assignment of measurments to filters.

High performance RDMA-based distributed feature collection component for training GNN model on EXTREMELY large graph

Dorylus: Affordable, Scalable, and Accurate GNN Training

[RSS 2024] AdaptiGraph: Material-Adaptive Graph-Based Neural Dynamics for Robotic Manipulation

🍇 A C++ library for parallel graph processing (GRAPE) 🍇

Programmable CUDA/C++ GPU Graph Analytics

An Industrial Graph Neural Network Framework