Helpful kernel tutorials and examples for tile-based GPU programming

[CVPR 2025] 🎉 Official repository of "ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning"

Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods

Sampling profiler for Python programs

Machine Learning Engineering Open Book

The Art of Debugging Open Book

A high-throughput and memory-efficient inference and serving engine for LLMs

A Fusion Code Generator for NVIDIA GPUs (commonly known as "nvFuser")

Making large AI models cheaper, faster and more accessible

Running large language models on a single GPU for throughput-oriented scenarios.

Awesome resources for GPUs

Solve puzzles. Improve your pytorch.

Pyjion - A JIT for Python based upon CoreCLR

A high-performance, zero-overhead, extensible Python compiler with built-in NumPy support

Ocolos is the first open-sourced online code layout optimization system for unmodified applications written in unmanaged languages.

An optimizing compiler for decision tree ensemble inference.

Reinforcement learning environments for compiler and program optimization tasks

A speculative mechanism to accelerate long-latency off-chip load requests by removing on-chip cache access latency from their critical path, as described by MICRO 2022 paper by Bera et al. (https:/…

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Ceras is yet another tiny deep learning engine, in pure c++ and header only.

Compile Time Regular Expression in C++

Ecosystem of libraries and tools for writing and executing fast GPU code fully in Rust.

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

Papers on Graph Analytics, Mining, and Learning

Fluid simulation engine for computer graphics applications

Study Group of Deep Learning Compiler

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

⚓ 我的游戏程序员生涯的读书笔记合辑。你可以把它看作一个加强版的Blog。涉及图形学、实时渲染、编程实践、GPU编程、设计模式、软件工程等内容。Keep Reading , Keep Writing , Keep Coding.