Skip to content

Latest commit

 

History

History
20 lines (14 loc) · 692 Bytes

File metadata and controls

20 lines (14 loc) · 692 Bytes

Adding a New Model

This section provides comprehensive guidance on how to add a new model to vLLM-Omni.

Documentation

The guide covers:

  • Directory structure and organization
  • Implementing stage components (thinker, talker, code2wav)
  • Creating the unified model class
  • Model registration
  • Stage configuration
  • Stage input processors
  • Testing strategies

Quick Start

For a quick reference, see the Adding a New Model Guide which walks through the complete implementation of Qwen3-Omni, a multi-stage omni-modality model.