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

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

vllm/config/multimodal.py

@@ -7,9 +7,9 @@ from typing import Any, Literal, TypeAlias
 from pydantic import ConfigDict, Field, field_validator, model_validator
 from pydantic.dataclasses import dataclass
 
-from vllm.attention.backends.registry import AttentionBackendEnum
 from vllm.config.utils import config
 from vllm.utils.hashing import safe_hash
+from vllm.v1.attention.backends.registry import AttentionBackendEnum
 
 
 @dataclass
@@ -124,7 +124,7 @@ class MultiModalConfig:
     mm_encoder_attn_backend: AttentionBackendEnum | None = None
     """Optional override for the multi-modal encoder attention backend when
     using vision transformers. Accepts any value from
-    `vllm.attention.backends.registry.AttentionBackendEnum` (e.g. `FLASH_ATTN`)."""
+    `vllm.v1.attention.backends.registry.AttentionBackendEnum` (e.g. `FLASH_ATTN`)."""
     interleave_mm_strings: bool = False
     """Enable fully interleaved support for multimodal prompts, while using
     --chat-template-content-format=string."""