TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

Transformer related optimization, including BERT, GPT

attention implemenation

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Connected components on discrete and continuous multilabel 3D & 2D images. Handles 26, 18, and 6 connected variants; periodic boundaries (4, 8, & 6)

YACCLAB: Yet Another Connected Components Labeling Benchmark

Dive into CPython internals, trying to illustrate every detail of CPython implementation

The best way to write secure and reliable applications. Write nothing; deploy nowhere.

PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

Official implementation of "SinIR: Efficient General Image Manipulation with Single Image Reconstruction" (ICML 2021)

My collection of machine learning papers

Cinder is Meta's internal performance-oriented production version of CPython.

Rich is a Python library for rich text and beautiful formatting in the terminal.

oneAPI Deep Neural Network Library (oneDNN)

PyTorch implementation of Pix2Pix based GAN for Hologram(QPI)

📊 A simple command-line utility for querying and monitoring GPU status

Source code examples from the Parallel Forall Blog

📚 Modern C++ Tutorial: C++11/14/17/20 On the Fly | https://changkun.de/modern-cpp/

The C++ Core Guidelines are a set of tried-and-true guidelines, rules, and best practices about coding in C++

Official Pytorch Implementation of "TResNet: High-Performance GPU-Dedicated Architecture" (WACV 2021)

2020년 상반기에 진행하는 C++20 스터디 관련 자료입니다.

StarDist - Object Detection with Star-convex Shapes

napari: a fast, interactive, multi-dimensional image viewer for python

🛠 All-in-one web-based IDE specialized for machine learning and data science.

MSVC's implementation of the C++ Standard Library.

OpenMMLab Detection Toolbox and Benchmark

Python을 이용한, 메신저 Telegram의 "키워드 알림" 기능을 수행하는 Bot입니다.

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

A PyTorch implementation of "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks".

Repo for counting stars and contributing. Press F to pay respect to glorious developers.