RelBench: Relational Deep Learning Benchmark

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Airspeed Velocity: A simple Python benchmarking tool with web-based reporting

Graph Neural Network Library for PyTorch

The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.

Low-Level Graph Neural Network Operators for PyG

Flexible interface for high-performance research using SOTA Transformers leveraging Pytorch Lightning, Transformers, and Hydra.

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

Real-time inference for Stable Diffusion - 0.88s latency. Covers AITemplate, nvFuser, TensorRT, FlashAttention.

VS Code extension for working with Azure Pipelines YAML files

Join the GitHub Graduation Yearbook and "walk the stage" on June 11.

Simple tooling for marking deprecated functions or classes and re-routing to the new successors' instance.

Automate issue discovery for your projects against Lightning nightly and releases.

Reference data processing code and model for the xView3 prize challenge.

Enabling PyTorch on Google TPU

PyTorch Lightning Bolts is a toolbox of models, callbacks, and datasets for AI/ML researchers.

A hyperparameter optimization framework

Collection of tasks for fast prototyping, baselining, finetuning and solving problems with deep learning.

Machine learning metrics for distributed, scalable PyTorch applications.

CaretTab - New Tab Page Replacement

拙著「問題解決力を鍛える!アルゴリズムとデータ構造」の補足資料。ソースコードと、章末問題への略解を掲載。