Initial vLLM-omni repository structure

- 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/diffusion_engine/__init__.py

@@ -0,0 +1,18 @@
+"""
+Diffusion Engine: Diffusion Transformer (DiT) processing modules.
+
+This module provides specialized processing for diffusion models including
+step management, cache management, and model wrapping.
+"""
+
+from .step_manager import DiffusionStepManager
+from .cache_manager import DiffusionCacheManager
+from .models import DiffusionModel
+from .base import BaseDiffusionEngine
+
+__all__ = [
+    "DiffusionStepManager",
+    "DiffusionCacheManager",
+    "DiffusionModel",
+    "BaseDiffusionEngine",
+]