junesookang

GIDS

empirical-study-of-GNNs

ringattention

Transformers with Arbitrarily Large Context

bam

gds-nvidia-fs

NVIDIA GPUDirect Storage Driver

DeepGNN

DeepGNN is a framework for training machine learning models on large scale graph data.

ptgnn

A PyTorch Graph Neural Network Library

DeepPlan

Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access (ACM EuroSys '23)

pytorch-direct_dgl

PyTorch-Direct code on top of PyTorch-1.8.0nightly (e152ca5) for Large Graph Convolutional Network Training with GPU-Oriented Data Communication Architecture (accepted by PVLDB)

ogb

Benchmark datasets, data loaders, and evaluators for graph machine learning

IGB-Datasets

Largest realworld open-source graph dataset - Worked done under IBM-Illinois Discovery Accelerator Institute and Amazon Research Awards and in collaboration with NVIDIA Research.

gdrcopy

A fast GPU memory copy library based on NVIDIA GPUDirect RDMA technology

mscclpp

MSCCL++: A GPU-driven communication stack for scalable AI applications

ark

A GPU-driven system framework for scalable AI applications

cuda-samples

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

MoA

Together Mixture-Of-Agents (MoA) – 65.1% on AlpacaEval with OSS models

graph-based-deep-learning-literature

links to conference publications in graph-based deep learning

mamba

Mamba SSM architecture

DUCATI_SIGMOD

Accepted paper of SIGMOD 2023, DUCATI: A Dual-Cache Training System for Graph Neural Networks on Giant Graphs with the GPU

matmulfreellm

Implementation for MatMul-free LM.

community_detection

LongLM

[ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

dgSPARSE-Lib

PyTorch-Based Fast and Efficient Processing for Various Machine Learning Applications with Diverse Sparsity

ThunderKittens

Tile primitives for speedy kernels

history-cache

backprop

Backpropagation in Python, C++, and Cuda

nnfusion

A flexible and efficient deep neural network (DNN) compiler that generates high-performance executable from a DNN model description.

onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

cutlass

CUDA Templates for Linear Algebra Subroutines

cudnn.torch

Torch-7 FFI bindings for NVIDIA CuDNN