RL training framework for diffusion and omni-modality models

A framework for efficient model inference with omni-modality models

Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching

JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents

Common recipes to run vLLM

a collection of skills for vllm-omni

verl: Volcano Engine Reinforcement Learning for LLMs

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

one for all, Optimal generator with No Exception

Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"

mindspore-lab models

the way -> '道' ; focus on multimodal large language model mllm

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

HunyuanVideo: A Systematic Framework For Large Video Generation Model

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

运行在Cloudflare Worker上的RSS订阅生成器

A toolbox of OCR models, algorithms, and pipelines based on MindSpore