[1/N][Attention] Restructure attention: move files (#31916)

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>

vllm/model_executor/models/qwen2_vl.py

@@ -43,14 +43,13 @@ from transformers.models.qwen2_vl.configuration_qwen2_vl import (
 from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
 from transformers.models.qwen2_vl.video_processing_qwen2_vl import Qwen2VLVideoProcessor
 
-from vllm.attention.backends.registry import AttentionBackendEnum
-from vllm.attention.layers.mm_encoder_attention import MMEncoderAttention
 from vllm.config import MultiModalConfig, VllmConfig
 from vllm.config.multimodal import BaseDummyOptions
 from vllm.distributed import parallel_state, tensor_model_parallel_all_gather
 from vllm.distributed import utils as dist_utils
 from vllm.logger import init_logger
 from vllm.model_executor.layers.activation import QuickGELU
+from vllm.model_executor.layers.attention.mm_encoder_attention import MMEncoderAttention
 from vllm.model_executor.layers.conv import Conv3dLayer
 from vllm.model_executor.layers.linear import (
     ColumnParallelLinear,
@@ -90,6 +89,7 @@ from vllm.multimodal.profiling import BaseDummyInputsBuilder
 from vllm.sequence import IntermediateTensors
 from vllm.tokenizers import TokenizerLike
 from vllm.utils.tensor_schema import TensorSchema, TensorShape
+from vllm.v1.attention.backends.registry import AttentionBackendEnum
 
 from .interfaces import (
     MultiModalEmbeddings,