📖 Introduction

This repository compiles experience and best practices for deploying, tuning, and running AI models on HCU hardware, covering:

• Large Language Models (LLM) — text generation, dialogue, code completion, etc.
• Multimodal Models (VLM) — vision-language models, image generation, speech recognition, etc.
• Omni Models (Omni) — unified understanding and generation of text, image, and audio

🐳 Docker Image List

View recommended Docker images and pull commands

📋 Model List

✅ Verified  |  🚧 In development  |  - Not yet verified

📄 License and Third-Party Sources

This project is licensed under the MIT License.

The repository does not directly embed third-party source code. Models, inference frameworks, tools, and services referenced in the documentation remain subject to the licenses of their respective projects. See THIRD_PARTY_NOTICES.md for details.

🤝…