hsliu
154d9ca4ff
- Add complete directory structure for multimodal and non-autoregressive processing - Include AsyncLLM, OmniEngine, and DiffusionEngine modules - Add processors, schedulers, executors, and output processors - Add API interfaces for Higress, Gradio, and ComfyUI - Add configuration management and CLI interface - Add comprehensive test structure and documentation - Add pyproject.toml with dependencies and project configuration - Add examples and documentation structure
vLLM-omni Examples
This directory contains examples demonstrating how to use vLLM-omni for various tasks.
Basic Examples
- Text Generation - Basic text generation using AR models
- Image Generation - Image generation using diffusion models
- Multimodal Processing - Processing text and images together
Advanced Examples
- Custom Model Integration - Integrating custom models
- Batch Processing - Efficient batch processing
- Streaming Output - Real-time streaming output
Multimodal Examples
- Image-to-Text - Image captioning and description
- Text-to-Image - Text-to-image generation
- Audio Processing - Audio generation and processing
- Video Generation - Video generation workflows
API Examples
- REST API - Using the REST API interface
- Gradio Interface - Creating Gradio web interfaces
- ComfyUI Integration - ComfyUI workflow integration
Configuration Examples
- Custom Configuration - Custom configuration setup
- Multi-GPU Setup - Multi-GPU configuration
- Distributed Processing - Distributed processing setup
Getting Started
-
Install vLLM-omni:
pip install vllm-omni -
Run a basic example:
python examples/basic/text_generation.py -
Explore the examples in each subdirectory for more advanced usage.
Requirements
Most examples require additional dependencies. Install them with:
pip install -r requirements.txt
For development examples, install the development dependencies:
pip install -r requirements-dev.txt