remove get_metadata_cls (#4087)

remove get_metadata_cls. It's only used for V0 engine and has been removed from vLLM already.

- vLLM version: v0.11.0
- vLLM main:
83f478bb19

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

vllm_ascend/attention/sfa_v1.py

@@ -4,9 +4,7 @@ from typing import TYPE_CHECKING, ClassVar, Optional, Tuple, Type, TypeVar
 import torch
 import torch_npu
 from torch import nn
-from vllm.attention.backends.abstract import (AttentionBackend,
-                                              AttentionMetadata,
-                                              MLAAttentionImpl)
+from vllm.attention.backends.abstract import AttentionBackend, MLAAttentionImpl
 from vllm.config import VllmConfig
 from vllm.distributed import get_tensor_model_parallel_world_size
 from vllm.model_executor.layers.linear import (LinearBase,
@@ -35,10 +33,6 @@ class AscendSFABackend(AttentionBackend):
     def get_name() -> str:
         return "ASCEND_SFA"
 
-    @staticmethod
-    def get_metadata_cls() -> type["AttentionMetadata"]:
-        return AscendSFAMetadata
-
     @staticmethod
     def get_builder_cls():
         return AscendSFAMetadataBuilder