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

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

vllm/v1/attention/backends/rocm_aiter_fa.py

@@ -7,25 +7,25 @@ from typing import ClassVar
 
 import torch
 
-from vllm.attention.backends.abstract import (
-    AttentionBackend,
-    AttentionImpl,
-    AttentionType,
-    MultipleOf,
-)
 from vllm.attention.layer import Attention
-from vllm.attention.ops.merge_attn_states import merge_attn_states
 from vllm.config import VllmConfig, get_layers_from_vllm_config
 from vllm.logger import init_logger
 from vllm.platforms import current_platform
 from vllm.utils.math_utils import cdiv
 from vllm.utils.platform_utils import get_cu_count
+from vllm.v1.attention.backend import (
+    AttentionBackend,
+    AttentionImpl,
+    AttentionType,
+    MultipleOf,
+)
 from vllm.v1.attention.backends.utils import (
     AttentionCGSupport,
     AttentionMetadataBuilder,
     CommonAttentionMetadata,
     split_decodes_prefills_and_extends,
 )
+from vllm.v1.attention.ops.merge_attn_states import merge_attn_states
 from vllm.v1.kv_cache_interface import AttentionSpec
 
 _PARTITION_SIZE_ROCM = 256