slime is an LLM post-training framework for RL Scaling.

Intel staging area for llvm.org contribution. Home for Intel LLVM-based projects.

Tutorials for the Kokkos C++ Performance Portability Programming Ecosystem

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

A new (MLIR based) high-level IR for clang.

VAST is an experimental compiler pipeline designed for program analysis of C and C++. It provides a tower of IRs as MLIR dialects to choose the best fit representations for a program analysis or fu…

The absolute trainer to light up AI agents.

Learning materials for Taskflow programming

Reliable & unreliable messages over UDP. Robust message fragmentation & reassembly. P2P networking / NAT traversal. Encryption.

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

[Start here!] Flow-IPC - Modern C++ toolkit for high-speed inter-process communication (IPC)

⚕️ the world's first unified, lifecycle-centric regulatory framework specifically designed for autonomous AI agents in medical environments (270+ requirements, 3 risk categories).

ImageMagick is a free, open-source software suite for creating, editing, converting, and displaying images. It supports 200+ formats and offers powerful command-line tools and APIs for automation, …

A header only library for creating and validating json web tokens in c++

distributed builds for C, C++ and Objective C

C++ DataFrame for statistical, financial, and ML analysis in modern C++

💫 Toolkit to help you get started with Spec-Driven Development

A C++17 cross-platform implementation for UUIDs

A library for efficient similarity search and clustering of dense vectors.

Cross-platform wrapper for the Zoom RTMS C SDK, providing bindings for Node.js, Python, and Go

Lightpanda: the headless browser designed for AI and automation

AutoML simultaneous bayesian hyperparameter optimization and feature selection

Python Multi-Agent Reinforcement Learning framework

SMAC: The StarCraft Multi-Agent Challenge

Learning Complex Teamwork Tasks using a Sub-task Curriculum

Tabular Deep Learning Library for PyTorch

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.

In this project, I explored how to extract knowledge graphs from text using LLMs, such as OpenAI GPT4o.