[Core] Simplify and unify mm uuid handling & auto-generated mm hash overrides processing. (#24271)

Signed-off-by: Chenheli Hua <huachenheli@outlook.com>

vllm/model_executor/models/pixtral.py

@@ -35,7 +35,7 @@ from vllm.model_executor.model_loader.weight_utils import default_weight_loader
 from vllm.model_executor.sampling_metadata import SamplingMetadata
 from vllm.multimodal import MULTIMODAL_REGISTRY, MultiModalKwargsItems
 from vllm.multimodal.inputs import (MultiModalDataDict, MultiModalFieldConfig,
-                                    NestedTensors)
+                                    MultiModalUUIDDict, NestedTensors)
 from vllm.multimodal.parse import (ImageProcessorItems, ImageSize,
                                    MultiModalDataItems)
 from vllm.multimodal.processing import (BaseMultiModalProcessor,
@@ -316,14 +316,14 @@ class PixtralMultiModalProcessor(BaseMultiModalProcessor[PixtralProcessingInfo]
         mm_data_items: MultiModalDataItems,
         hf_processor_mm_kwargs: Mapping[str, object],
         tokenization_kwargs: Mapping[str, object],
-        mm_hash_overrides: Optional[dict[str, list[str]]] = None,
+        mm_uuids: Optional[MultiModalUUIDDict] = None,
     ) -> tuple[list[int], MultiModalProcessingInfo, bool]:
         prompt_ids, mm_info, _ = super()._cached_apply_hf_processor(
             prompt=prompt,
             mm_data_items=mm_data_items,
             hf_processor_mm_kwargs=hf_processor_mm_kwargs,
             tokenization_kwargs=tokenization_kwargs,
-            mm_hash_overrides=mm_hash_overrides,
+            mm_uuids=mm_uuids,
         )
 
         # NOTE: The tokens are already inserted by the chat template