[Misc]] Move processing context to multimodal directory (#25548)

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

vllm/model_executor/models/hyperclovax_vision.py

@@ -29,7 +29,6 @@ from transformers import BatchFeature, CLIPVisionConfig, SiglipVisionConfig
 from transformers.modeling_utils import no_init_weights
 
 from vllm.config import VllmConfig
-from vllm.inputs import InputProcessingContext
 from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.multimodal import MULTIMODAL_REGISTRY
 from vllm.multimodal.cache import BaseMultiModalProcessorCache
@@ -37,8 +36,9 @@ from vllm.multimodal.inputs import (MultiModalDataDict, MultiModalFieldConfig,
                                     MultiModalKwargsItems)
 from vllm.multimodal.parse import ImageSize, MultiModalDataItems
 from vllm.multimodal.processing import (BaseMultiModalProcessor,
-                                        BaseProcessingInfo, PromptReplacement,
-                                        PromptUpdate)
+                                        BaseProcessingInfo,
+                                        InputProcessingContext,
+                                        PromptReplacement, PromptUpdate)
 from vllm.multimodal.profiling import BaseDummyInputsBuilder
 from vllm.sequence import IntermediateTensors