Highlights
- Pro
Lists (2)
Sort Name ascending (A-Z)
Stars
A C++20 library for sequence-orientated programming
Open-source CUDA, Triton and HIP compiler targeting multiple GPU and CPU architectures.
A description of Minotaur can be found in https://arxiv.org/abs/2306.00229.
Ongoing research training transformer models at scale
Fast and memory-efficient exact attention
Extremely fast Query Engine for DataFrames, written in Rust
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Linear algebra foundation for the Rust programming language
A flutter hack project made with Flame Engine
🚀 A modern-looking Code Editor
The Flutter code generator for your assets, fonts, colors, … — Get rid of all String-based APIs.
Barbershop: GAN-based Image Compositing using Segmentation Masks (SIGGRAPH Asia 2021)
A TensorFlow Implementation of the Transformer: Attention Is All You Need
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
A dx12 river renderer using wave particles with interactive vortices.
Implementation of abstractive summarization using LSTM in the encoder-decoder architecture with local attention.
Abstractive summarisation using Bert as encoder and Transformer Decoder
TensorFlow code and pre-trained models for BERT
CUDAfy .NET allows easy development of high performance GPGPU applications completely from the .NET. It's developed in C#.
MIT-Jaipur e-cell Hackathon 2021, Health Database application
Material UI: Comprehensive React component library that implements Google's Material Design. Free forever.
All Algorithms implemented in Python