Stars
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Command-line program to download videos from YouTube.com and other video sites
🦜🔗 The platform for reliable agents.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
scikit-learn: machine learning in Python
A high-throughput and memory-efficient inference and serving engine for LLMs
A natural language interface for computers
openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
A community-maintained Python framework for creating mathematical animations.
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
A generative world for general-purpose robotics & embodied AI learning.
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
SGLang is a fast serving framework for large language models and vision language models.
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
verl: Volcano Engine Reinforcement Learning for LLMs
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
A collaboration friendly studio for NeRFs
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
OpenMMLab Pose Estimation Toolbox and Benchmark.
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.