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

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

vllm/model_executor/models/paddleocr_vl.py

@@ -30,14 +30,13 @@ from transformers.modeling_outputs import (
 )
 from transformers.utils import torch_int
 
-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
 from vllm.distributed import utils as dist_utils
+from vllm.model_executor.layers.attention.mm_encoder_attention import (
+    MMEncoderAttention,
+)
 from vllm.model_executor.layers.conv import Conv2dLayer
 from vllm.model_executor.layers.linear import (
     QKVParallelLinear,
@@ -72,6 +71,7 @@ from vllm.multimodal.processing import (
 from vllm.multimodal.profiling import BaseDummyInputsBuilder
 from vllm.sequence import IntermediateTensors
 from vllm.utils.tensor_schema import TensorSchema, TensorShape
+from vllm.v1.attention.backends.registry import AttentionBackendEnum
 
 from .ernie45 import Ernie4_5ForCausalLM
 from .interfaces import MultiModalEmbeddings, SupportsMRoPE, SupportsMultiModal