Unofficial extension implementation of Self-Forcing to support I2V && 14B training.

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

A high-performance and light-weight router for vLLM large scale deployment

An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

TORCH_LOGS parser for PT2

Ultralytics YOLO 🚀

A framework for efficient model inference with omni-modality models

A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM

Easy, Fast, and Scalable Multimodal AI

A PyTorch native platform for training generative AI models

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

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

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including CUDA, x86 and ARMv9.

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

Official Docker image for the NATS server

System Level Intelligent Router for Mixture-of-Models at Cloud, Enterprise and Edge

A parallelism VAE avoids OOM for high resolution image generation

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

Wan: Open and Advanced Large-Scale Video Generative Models

An open-source, all-in-one AI API router

AAAI2026 X2Edit: Revisiting Arbitrary-Instruction Image Editing through Self-Constructed Data and Task-Aware Representation Learning

cloc counts blank lines, comment lines, and physical lines of source code in many programming languages.

Light Image Video Generation Inference Framework

Qwen-Image-Lightning: Speed up Qwen-Image model with distillation

🤗A PyTorch-native and Flexible Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs.

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Enjoy the magic of Diffusion models!