[Cherry-pick][0.11.0] Adapted to torch_npu.npu_fused_infer_attention_score (#4202)

### What this PR does / why we need it?
Fixes a compatible bug with torch_npu.npu_fused_infer_attention_score
which is discribed in
https://github.com/vllm-project/vllm-ascend/issues/4020.
@momo609 tells us this solution.
cherry-pick: https://github.com/vllm-project/vllm-ascend/pull/4025

### Does this PR introduce _any_ user-facing change?
N/A

### How was this patch tested?
CI passed with new added/existing test.

Signed-off-by: Icey <1790571317@qq.com>

vllm_ascend/attention/attention_v1.py

@@ -115,7 +115,7 @@ class AscendAttentionBackend(AttentionBackend):
 
     @staticmethod
     def get_supported_block_size() -> list[int]:
-        return [64]
+        return [128]
 
 
 class AscendAttentionState(Enum):