This is an online course where you can learn and master the skill of low-level performance analysis and tuning.

Moved to Codeberg

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

A natural language interface for computers

[ICCV 2023, Official Code] for paper "Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives". Official Weights and Demos provided.

Large World Model -- Modeling Text and Video with Millions Context

The official PyTorch implementation of Google's Gemma models

A collection of learning resources for curious software engineers

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

lightweight, standalone C++ inference engine for Google's Gemma models.

A deep learning library for video understanding research.

Development repository for the Triton language and compiler

Extremely fast Query Engine for DataFrames, written in Rust

The simplest, fastest repository for training/finetuning medium-sized GPTs.

The "Python Machine Learning (3rd edition)" book code repository

Turbopilot is an open source large-language-model based code completion engine that runs locally on CPU

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

Neural Networks: Zero to Hero

Jupyter notebooks for the code samples of the book "Deep Learning with Python"

CUDA integration for Python, plus shiny features

The fundamental package for scientific computing with Python.

Python 3 Bindings for NVML library. Get NVIDIA GPU status inside your program.

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

JupyterLab desktop application, based on Electron.

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

A CUDA implementation of SIFT for NVidia GPUs (1.2 ms on a GTX 1060)

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

Projects in Analytics and ML

An opinionated list of awesome Python frameworks, libraries, software and resources.

Automated CI toolchain to produce precompiled opencv-python, opencv-python-headless, opencv-contrib-python and opencv-contrib-python-headless packages.