fix legacy import

Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>

vllm/model_executor/models/kimi_k25.py

@@ -22,6 +22,7 @@ from transformers import BatchFeature
 from transformers.processing_utils import ProcessorMixin
 
 from vllm.config import VllmConfig
+from vllm.config.multimodal import BaseDummyOptions
 from vllm.distributed import get_pp_group
 from vllm.logger import init_logger
 from vllm.model_executor.layers.fused_moe import SharedFusedMoE
@@ -50,13 +51,13 @@ from vllm.multimodal.inputs import (
 )
 from vllm.multimodal.parse import MultiModalDataItems, VisionChunkProcessorItems
 from vllm.multimodal.processing import (
+    BaseDummyInputsBuilder,
     BaseMultiModalProcessor,
     BaseProcessingInfo,
     InputProcessingContext,
     PromptReplacement,
     PromptUpdate,
 )
-from vllm.multimodal.profiling import BaseDummyInputsBuilder, BaseDummyOptions
 from vllm.sequence import IntermediateTensors
 from vllm.transformers_utils.configs import KimiK25Config
 from vllm.transformers_utils.processor import cached_get_image_processor

vllm/model_executor/models/kimi_k25_vit.py

@@ -18,11 +18,11 @@ import torch.nn as nn
 import torch.nn.functional as F
 from transformers.activations import GELUActivation
 
-from vllm.attention.layers.mm_encoder_attention import MMEncoderAttention
 from vllm.config import MultiModalConfig
 from vllm.distributed import divide, get_tensor_model_parallel_world_size
 from vllm.logger import init_logger
 from vllm.model_executor.layers.activation import get_act_fn
+from vllm.model_executor.layers.attention.mm_encoder_attention import MMEncoderAttention
 from vllm.model_executor.layers.linear import (
     ColumnParallelLinear,
     QKVParallelLinear,