# pytorch

🤗 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.

Stable Diffusion web UI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

We write your reusable computer vision tools. 💜

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

vLLM-Omniは、テキストだけでなく画像・動画・音声など複数の種類のデータを同時に扱えるAIモデルを、高速かつ低コストで動かすためのフレームワーク（ソフトウェアの骨組み）です。もともとテキスト専用だったvLLMという人気の高速推論エンジ

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

A platform for reproducible world model research and evaluation