[CI] Fix broken ci (#2530)

vLLM commit https://github.com/vllm-project/vllm/pull/22711 changed the
encode cache entries logic, this PR adapt the same change for vllm
ascend to make CI happy.

Co-Authored-By: zhoux77899 <zhouxiang100@huawei.com>

- vLLM version: v0.10.1.1
- vLLM main:
0ff902f3b4

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

vllm_ascend/worker/npu_input_batch.py

@@ -47,6 +47,8 @@ class CachedRequestState:
     prompt_token_ids: list[int]
     mm_kwargs: list[MultiModalKwargsItem]
     mm_positions: list[PlaceholderRange]
+    # TODO: remove Optional after 0.10.1.1
+    mm_hashes: Optional[list[str]]
     sampling_params: Optional[SamplingParams]
     pooling_params: Optional[PoolingParams]
     generator: Optional[torch.Generator]