[ICLR 2025] Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation

Graph Neural Network Library for PyTorch

RelBench: Relational Deep Learning Benchmark

Multimodal Graph Learning: how to encode multiple multimodal neighbors with their relations into LLMs

SimpleHTTPServer with support for Range requests

DALL·E Mini - Generate images from a text prompt

Python package built to ease deep learning on graph, on top of existing DL frameworks.

NLP made easy

End-to-End Object Detection with Transformers

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

A PyTorch Library for Accelerating 3D Deep Learning Research

Datasets, Transforms and Models specific to Computer Vision

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Gluon CV Toolkit

Open deep learning compiler stack for cpu, gpu and specialized accelerators

i-RevNet Pytorch Code

The Deadlock Empire: Slay dragons, learn concurrency!

Run compilers interactively from your web browser and interact with the assembly

StyleGAN - Official TensorFlow Implementation

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

Seamless operability between C++11 and Python

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

TensorFlow code and pre-trained models for BERT

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

A library that uses hardware acceleration to load sequences of video frames to facilitate machine learning training

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

Open-Source CUDA/OpenCL Speed Of Light Ray-tracer