A privacy-first app that strips AI watermarks from content you own.

FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.

14MB foundation model for tiny devices; phones, wearables, smart home, and robots.

Universal LLM Deployment Engine with ML Compilation

Tile primitives for speedy kernels

cuTile is a programming model for writing parallel kernels for NVIDIA GPUs

DeepSeek Harness: Everything is a Plugin.

Automatic verification of LLVM optimizations

A list of awesome compiler projects and papers for tensor computation and deep learning.

The definitive vLLM runtime for dual RTX 2080 Ti 22GB + NVLink, delivering Qwen 27B local inference with maximum 100+ tok/s single-request decode with support of FP8 weight ( Join Discord :https://…

Achieve a tiny STL in C++11

A simple C++11 Thread Pool implementation

📚 Modern C++ Tutorial: C++11 to C++26 On the Fly | https://changkun.de/modern-cpp/

Empowering everyone to build reliable and efficient software.

egraphs + datalog!

egg is a flexible, high-performance e-graph library

The Z3 Theorem Prover

Fast, flexible LLM inference

Open-source high-performance RISC-V processor

The CORE-V CVA6 is a highly configurable, 6-stage RISC-V core for both application and embedded applications. Application class configurations are capable of booting Linux.

An experimental modular OS written in Rust.

Tile-Based Runtime for Ultra-Low-Latency LLM Inference

A tutorial on modern GPU programming for machine learning systems

🍎 One kernel a day keeps high latency away. A hands-on CUDA learning path featuring a rich collection of kernels, from the basics to peak performance, seamlessly integrated as PyTorch C++ extensions.

PyTorch Tutorial for Deep Learning Researchers

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Open Machine Learning Compiler Framework

Open ABI and FFI for Machine Learning Systems

mold: A Modern Linker 🦠

Learning TileLang with 10 puzzles!