HyTruongSon / GraphFlowLinks
Deep Learning framework in C++/CUDA that supports symbolic/automatic differentiation, dynamic computation graphs, tensor/matrix operations accelerated by GPU and implementations of various state-of-the-art graph neural networks and other Machine Learning models including Covariant Compositional Networks For Learning Graphs [Risi et al]
☆53Updated 4 years ago
Alternatives and similar repositories for GraphFlow
Users that are interested in GraphFlow are comparing it to the libraries listed below
Sorting:
- Light-weight GPU kernel interface for graph operations☆15Updated 5 years ago
- ☆23Updated 6 years ago
- The Surprisingly ParalleL spArse Tensor Toolkit.☆73Updated 3 years ago
- Experiments with Message Passing GNNs in C++ and PyTorch.☆26Updated last year
- Distributed NMF/NTF Library☆48Updated 10 months ago
- Einsum optimization using opt_einsum and PyTorch FX graph rewriting☆22Updated 3 years ago
- A Distributed Multi-GPU System for Fast Graph Processing☆65Updated 7 years ago
- A fast implementation of spectral clustering on GPU-CPU Platform☆32Updated 7 years ago
- Computations involving Lie groups and harmonic analysis☆205Updated 8 months ago
- IPC: A Graph Data Set Compiled from International Planning Competitions☆46Updated 5 years ago
- ☆94Updated 8 years ago
- ☆70Updated 2 years ago
- Structured matrices for compressing neural networks☆67Updated 2 years ago
- HogWild++: A New Mechanism for Decentralized Asynchronous Stochastic Gradient Descent☆33Updated 9 years ago
- Kernel Fusion and Runtime Compilation Based on NNVM☆71Updated 8 years ago
- Implementation of the Spline-Based Convolution Operator of SplineCNN in PyTorch☆184Updated 2 months ago
- ☆35Updated 5 months ago
- Deriving Neural Architectures from Sequence and Graph Kernels☆59Updated 7 years ago
- Deep learning with a multiplication budget☆47Updated 7 years ago
- Parallel Tensor Infrastructure (ParTI!)☆30Updated 5 years ago
- CUDA implementation of the Blocked Floyd Warshall All pairs shortest path graph algorithm☆42Updated 7 years ago
- Sparse Matrix-Matrix Multiplication Benchmark on Intel Xeon and Xeon Phi (KNC, KNL) from blog post:☆12Updated 9 years ago
- G3: A Programmable GNN Training System on GPU☆43Updated 5 years ago
- This repository is the summary of all of our works for the XLA.☆11Updated 7 years ago
- implement distributed machine learning with Pytorch + OpenMPI☆52Updated 6 years ago
- Introduction to CUDA programming☆128Updated 8 years ago
- Tensor decomposition implemented in TensorFlow☆63Updated 6 years ago
- Efficient Unitary Neural Network(EUNN) implementation in Tensorflow☆73Updated 6 years ago
- Scalable Log Determinants for Gaussian Process Kernel Learning (https://arxiv.org/abs/1711.03481) (NIPS 2017)☆18Updated 7 years ago
- Implements the frequent directions algorithm for approximating matrices in streams☆33Updated 8 years ago