[VLM] Generalized prompt updates for multi-modal processor (#13964)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

vllm/model_executor/models/aria.py

@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: Apache-2.0
-
-from typing import (Iterable, List, Mapping, Optional, Set, Tuple, TypedDict,
-                    Union)
+from collections.abc import Iterable, Mapping, Sequence
+from typing import List, Optional, Set, Tuple, TypedDict, Union
 
 import torch
 import torch.nn as nn
@@ -26,7 +25,8 @@ from vllm.multimodal.inputs import (MultiModalFieldConfig, MultiModalKwargs,
                                     NestedTensors)
 from vllm.multimodal.parse import MultiModalDataItems
 from vllm.multimodal.processing import (BaseMultiModalProcessor,
-                                        BaseProcessingInfo, PromptReplacement)
+                                        BaseProcessingInfo, PromptReplacement,
+                                        PromptUpdate)
 from vllm.multimodal.profiling import BaseDummyInputsBuilder, ProcessorInputs
 from vllm.sequence import IntermediateTensors
 
@@ -457,12 +457,12 @@ class AriaMultiModalProcessor(BaseMultiModalProcessor[AriaProcessingInfo]):
             pixel_mask=MultiModalFieldConfig.batched("image"),
         )
 
-    def _get_prompt_replacements(
+    def _get_prompt_updates(
         self,
         mm_items: MultiModalDataItems,
         hf_processor_mm_kwargs: Mapping[str, object],
         out_mm_kwargs: MultiModalKwargs,
-    ) -> list[PromptReplacement]:
+    ) -> Sequence[PromptUpdate]:
         hf_config = self.info.get_hf_config()
         image_token_id = hf_config.image_token_index