change omni.py to serve.py and mv to cli

vllm_omni/entrypoints/cli/__init__.py

@@ -0,0 +1,5 @@
+"""CLI helpers for vLLM-omni entrypoints."""
+
+from .serve import OmniServeCommand
+
+__all__ = ["OmniServeCommand"]

vllm_omni/entrypoints/cli/main.py

@@ -5,7 +5,7 @@ CLI entry point for vLLM-omni that intercepts vLLM commands.
 import sys
 import argparse
 from typing import List, Optional
-from vllm_omni.entrypoints.omni import OmniServeCommand
+from vllm_omni.entrypoints.cli.serve import OmniServeCommand
 
 
 def main():

vllm_omni/entrypoints/cli/serve.py

@@ -6,7 +6,7 @@ import argparse
 import asyncio
 from typing import List, Optional
 
-from .omni_llm import AsyncOmniLLM
+from ..omni_llm import AsyncOmniLLM
 from vllm_omni.config import (
     DiTConfig,
     create_ar_stage_config,