gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

top #1 and most feature rich GPT wrapper for git — generate commit messages with an LLM in 1 sec — works best with Claude or GPT, supports local models too

s1: Simple test-time scaling

The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

Perplexica is an AI-powered answering engine. It is an Open source alternative to Perplexity AI

Fully open reproduction of DeepSeek-R1

LLM training in simple, raw C/CUDA

PyTorch native post-training library

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Inference Llama 2 in one file of pure C

Development repository for the Triton language and compiler

LLM inference in C/C++

Official Code for DragGAN (SIGGRAPH 2023)

Universal LLM Deployment Engine with ML Compilation

Beyond Straight-Through

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Transformer related optimization, including BERT, GPT

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Inference code for Llama models

VaLM: Visually-augmented Language Modeling. ICLR 2023.

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

APPS: Automated Programming Progress Standard (NeurIPS 2021)

Seminar on Large Language Models (COMP790-101 at UNC Chapel Hill, Fall 2022)