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

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

vllm/model_executor/models/glm4_1v.py

@@ -46,15 +46,14 @@ from transformers.models.glm4v.image_processing_glm4v import (
 from transformers.models.glm4v.video_processing_glm4v import Glm4vVideoProcessor
 from transformers.video_utils import VideoMetadata
 
-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, VideoDummyOptions
 from vllm.distributed import get_tensor_model_parallel_world_size, parallel_state
 from vllm.distributed import utils as dist_utils
 from vllm.logger import init_logger
+from vllm.model_executor.layers.attention.mm_encoder_attention import (
+    MMEncoderAttention,
+)
 from vllm.model_executor.layers.conv import Conv2dLayer, Conv3dLayer
 from vllm.model_executor.layers.layernorm import RMSNorm
 from vllm.model_executor.layers.linear import (
@@ -89,6 +88,7 @@ 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 ..layers.activation import SiluAndMul
 from .interfaces import (