support multi image input of local files

vllm/multimodal/utils.py

@@ -6,6 +6,7 @@ from typing import Any, List, Optional, Tuple, TypeVar, Union
 import numpy as np
 import numpy.typing as npt
 from PIL import Image
+import os
 
 from vllm.connections import global_http_connection
 from vllm.envs import VLLM_AUDIO_FETCH_TIMEOUT, VLLM_IMAGE_FETCH_TIMEOUT
@@ -30,6 +31,10 @@ def _load_image_from_data_url(image_url: str):
     return load_image_from_base64(image_base64)
 
 
+def _load_image_from_file(file_path: str) -> Image.Image:  
+    # Load image directly from file  
+    return Image.open(file_path) 
+
 def fetch_image(image_url: str, *, image_mode: str = "RGB") -> Image.Image:
     """
     Load a PIL image from a HTTP or base64 data URL.
@@ -43,6 +48,11 @@ def fetch_image(image_url: str, *, image_mode: str = "RGB") -> Image.Image:
 
     elif image_url.startswith('data:image'):
         image = _load_image_from_data_url(image_url)
+        
+    elif os.path.isfile(image_url):  
+        # Load image from local file path  
+        image = _load_image_from_file(image_url) 
+        
     else:
         raise ValueError("Invalid 'image_url': A valid 'image_url' must start "
                          "with either 'data:image' or 'http'.")