pyg-team/pyg-lib
Low-Level Graph Neural Network Operators for PyG
This is a foundational library for developers working with Graph Neural Networks (GNNs). It provides highly optimized building blocks to speed up tasks like processing large datasets represented as graphs. It takes raw graph data and operations, and outputs more efficient computations for GNN models. This is for machine learning engineers and researchers building advanced GNN applications.
224 stars.
Use this if you are a Python developer or researcher building Graph Neural Network models and need to accelerate their performance on various hardware setups.
Not ideal if you are an end-user looking for a pre-built application or a high-level API to solve a domain-specific problem without deep technical expertise.
Stars
224
Forks
58
Language
C++
License
—
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pyg-team/pyg-lib"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
a-r-j/graphein
Protein Graph Library
raamana/graynet
Subject-wise networks from structural MRI, both vertex- and voxel-wise features (thickness, GM...
pykale/pykale
Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for...
dmlc/dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.