Models and examples built with TensorFlow

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

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

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

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

the only cheat sheet you need

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

You like pytorch? You like micrograd? You love tinygrad! ❤️

Image-to-Image Translation in PyTorch

DALL·E Mini - Generate images from a text prompt

Convert Machine Learning Code Between Frameworks

Open Machine Learning Compiler Framework

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

Universal Radio Hacker: Investigate Wireless Protocols Like A Boss

Modular visual interface for GDB in Python

A command-line tool to download photos from iCloud

Minimal and clean examples of machine learning algorithms implementations

Source code for Twitter's Recommendation Algorithm

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

Refine high-quality datasets and visual AI models

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

An open Apple AirDrop implementation written in Python

💎1MB lightweight face detection model (1MB轻量级人脸检测模型)

The FLARE team's open-source tool to identify capabilities in executable files.

The x86 processor fuzzer

Easily document cables and wiring harnesses.

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.