[Multi Modal] Configurable MM Profiling (#25631)

Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

vllm/model_executor/models/paligemma.py

@@ -8,6 +8,7 @@ from torch import nn
 from transformers import BatchFeature, PaliGemmaConfig
 
 from vllm.config import VllmConfig
+from vllm.config.multimodal import BaseDummyOptions
 from vllm.logger import init_logger
 from vllm.multimodal import MULTIMODAL_REGISTRY
 from vllm.multimodal.inputs import (MultiModalDataDict, MultiModalFieldConfig,
@@ -106,6 +107,7 @@ class PaliGemmaDummyInputsBuilder(
         self,
         seq_len: int,
         mm_counts: Mapping[str, int],
+        mm_options: Optional[Mapping[str, BaseDummyOptions]] = None,
     ) -> MultiModalDataDict:
         hf_config = self.info.get_hf_config()
         vision_config = hf_config.vision_config
@@ -113,11 +115,14 @@ class PaliGemmaDummyInputsBuilder(
 
         num_images = mm_counts.get("image", 0)
 
+        image_overrides = mm_options.get("image") if mm_options else None
+
         return {
             "image":
             self._get_dummy_images(width=max_image_size,
                                    height=max_image_size,
-                                   num_images=num_images)
+                                   num_images=num_images,
+                                   overrides=image_overrides)
         }