tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Mamba SSM architecture

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

LLM agents built for control. Designed for real-world use. Deployed in minutes.

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

TuShare is a utility for crawling historical data of China stocks

Open source code for AlphaFold 2.

Pythonic HTML Parsing for Humans™

Pyodide is a Python distribution for the browser and Node.js based on WebAssembly

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

An open source implementation of CLIP.

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Generate 3D objects conditioned on text or images

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

Synapse: Matrix homeserver written in Python/Twisted.

Universal Radio Hacker: Investigate Wireless Protocols Like A Boss

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

🐍 Geometric Computer Vision Library for Spatial AI

Spark-TTS Inference Code

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

Tensorflow2.0 🍎🍊 is delicious, just eat it! 😋😋

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

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

Implementation of Nougat Neural Optical Understanding for Academic Documents

Come and join us, we need you!

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, 17+ clouds, or on-prem).

ImageBind One Embedding Space to Bind Them All