TPU inference for vLLM, with unified JAX and PyTorch support.

A modular, documentation-driven framework using Cursor custom modes (VAN, PLAN, CREATIVE, IMPLEMENT) to provide persistent memory and guide AI through a structured development workflow with visual …

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

llmbasedos — Local-First OS Where Your AI Agents Wake Up and Work

ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.

An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

📄 Configuration files that enhance Cursor AI editor experience with custom rules and behaviors

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

[ECCV 2024 Oral] DriveLM: Driving with Graph Visual Question Answering

[CVPR 2024 Highlight] GenAD: Generalized Predictive Model for Autonomous Driving

[NeurIPS 2024] A Generalizable World Model for Autonomous Driving

[CVPR 2023 Best Paper Award] Planning-oriented Autonomous Driving

Property based testing framework for JavaScript (like QuickCheck) written in TypeScript

🎥 Python and OpenCV-based scene cut/transition detection program & library.

Get down and dirty with FlashAttention2.0 in pytorch, plug in and play no complex CUDA kernels

Official repository for LongChat and LongEval

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

Metadata from Project Gutenberg

Accessible large language models via k-bit quantization for PyTorch.

ChatGPT and Bing AI prompt curation

This repo includes ChatGPT prompt curation to use ChatGPT and other LLM tools better.

(ICLR 2023 Spotlight) MPCFormer: fast, performant, and private transformer inference with MPC

(NeurIPS 2022) Automatically finding good model-parallel strategies, especially for complex models and clusters.

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

NumPy & SciPy for GPU