Stars
FastAPI framework, high performance, easy to learn, fast to code, ready for production
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)
A high-throughput and memory-efficient inference and serving engine for LLMs
The simplest, fastest repository for training/finetuning medium-sized GPTs.
aider is AI pair programming in your terminal
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚
The lean application framework for Python. Build sophisticated user interfaces with a simple Python API. Run your apps in the terminal and a web browser.
You like pytorch? You like micrograd? You love tinygrad! ❤️
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
The official Python library for the OpenAI API
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Official inference framework for 1-bit LLMs
Code for the paper "Language Models are Unsupervised Multitask Learners"
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Fast and memory-efficient exact attention
Open standard for machine learning interoperability
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
Stable Diffusion with Core ML on Apple Silicon
Train transformer language models with reinforcement learning.
verl: Volcano Engine Reinforcement Learning for LLMs
A framework for managing and maintaining multi-language pre-commit hooks.
Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud.
Convert Machine Learning Code Between Frameworks
Open deep learning compiler stack for cpu, gpu and specialized accelerators