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

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

vllm/v1/attention/backends/triton_attn.py

@@ -7,17 +7,6 @@ from typing import ClassVar
 
 import torch
 
-from vllm.attention.backends.abstract import (
-    AttentionBackend,
-    AttentionImpl,
-    AttentionType,
-    MultipleOf,
-)
-from vllm.attention.ops.triton_prefill_attention import context_attention_fwd
-from vllm.attention.ops.triton_reshape_and_cache_flash import (
-    triton_reshape_and_cache_flash,
-)
-from vllm.attention.ops.triton_unified_attention import unified_attention
 from vllm.config import CUDAGraphMode, VllmConfig
 from vllm.config.cache import CacheDType
 from vllm.logger import init_logger
@@ -28,11 +17,22 @@ from vllm.model_executor.layers.quantization.utils.quant_utils import (
 from vllm.platforms import current_platform
 from vllm.platforms.interface import DeviceCapability
 from vllm.utils.math_utils import next_power_of_2
+from vllm.v1.attention.backend import (
+    AttentionBackend,
+    AttentionImpl,
+    AttentionType,
+    MultipleOf,
+)
 from vllm.v1.attention.backends.utils import (
     AttentionCGSupport,
     AttentionMetadataBuilder,
     CommonAttentionMetadata,
 )
+from vllm.v1.attention.ops.triton_prefill_attention import context_attention_fwd
+from vllm.v1.attention.ops.triton_reshape_and_cache_flash import (
+    triton_reshape_and_cache_flash,
+)
+from vllm.v1.attention.ops.triton_unified_attention import unified_attention
 from vllm.v1.kv_cache_interface import AttentionSpec
 
 logger = init_logger(__name__)