Fix vllm-project#19130 (vllm-project#19132)

Signed-off-by: 汪志鹏 <[email protected]>

Author: princepride

examples/offline_inference/vision_language_multi_image.py

@@ -593,21 +593,21 @@ def load_qwen_vl_chat(question: str, image_urls: list[str]) -> ModelRequestData:
 
 def load_qwen2_vl(question: str, image_urls: list[str]) -> ModelRequestData:
     try:
-        from qwen_vl_utils import process_vision_info
+        from qwen_vl_utils import smart_resize
     except ModuleNotFoundError:
         print(
             "WARNING: `qwen-vl-utils` not installed, input images will not "
             "be automatically resized. You can enable this functionality by "
             "`pip install qwen-vl-utils`."
         )
-        process_vision_info = None
+        smart_resize = None
 
     model_name = "Qwen/Qwen2-VL-7B-Instruct"
 
     # Tested on L40
     engine_args = EngineArgs(
         model=model_name,
-        max_model_len=32768 if process_vision_info is None else 4096,
+        max_model_len=32768 if smart_resize is None else 4096,
         max_num_seqs=5,
         limit_mm_per_prompt={"image": len(image_urls)},
     )
@@ -630,10 +630,18 @@ def load_qwen2_vl(question: str, image_urls: list[str]) -> ModelRequestData:
         messages, tokenize=False, add_generation_prompt=True
     )
 
-    if process_vision_info is None:
+    if smart_resize is None:
         image_data = [fetch_image(url) for url in image_urls]
     else:
-        image_data, _ = process_vision_info(messages)
+
+        def post_process_image(image: Image) -> Image:
+            width, height = image.size
+            resized_height, resized_width = smart_resize(
+                height, width, max_pixels=1024 * 28 * 28
+            )
+            return image.resize((resized_width, resized_height))
+
+        image_data = [post_process_image(fetch_image(url)) for url in image_urls]
 
     return ModelRequestData(
         engine_args=engine_args,
@@ -644,20 +652,20 @@ def load_qwen2_vl(question: str, image_urls: list[str]) -> ModelRequestData:
 
 def load_qwen2_5_vl(question: str, image_urls: list[str]) -> ModelRequestData:
     try:
-        from qwen_vl_utils import process_vision_info
+        from qwen_vl_utils import smart_resize
     except ModuleNotFoundError:
         print(
             "WARNING: `qwen-vl-utils` not installed, input images will not "
             "be automatically resized. You can enable this functionality by "
             "`pip install qwen-vl-utils`."
         )
-        process_vision_info = None
+        smart_resize = None
 
     model_name = "Qwen/Qwen2.5-VL-3B-Instruct"
 
     engine_args = EngineArgs(
         model=model_name,
-        max_model_len=32768 if process_vision_info is None else 4096,
+        max_model_len=32768 if smart_resize is None else 4096,
         max_num_seqs=5,
         limit_mm_per_prompt={"image": len(image_urls)},
     )
@@ -680,10 +688,18 @@ def load_qwen2_5_vl(question: str, image_urls: list[str]) -> ModelRequestData:
         messages, tokenize=False, add_generation_prompt=True
     )
 
-    if process_vision_info is None:
+    if smart_resize is None:
         image_data = [fetch_image(url) for url in image_urls]
     else:
-        image_data, _ = process_vision_info(messages, return_video_kwargs=False)
+
+        def post_process_image(image: Image) -> Image:
+            width, height = image.size
+            resized_height, resized_width = smart_resize(
+                height, width, max_pixels=1024 * 28 * 28
+            )
+            return image.resize((resized_width, resized_height))
+
+        image_data = [post_process_image(fetch_image(url)) for url in image_urls]
 
     return ModelRequestData(
         engine_args=engine_args,