update

Signed-off-by: shen-shanshan <467638484@qq.com>

Author: shen-shanshan

vllm_ascend/worker/model_runner_v1.py

@@ -37,7 +37,7 @@
 from vllm.multimodal import MULTIMODAL_REGISTRY, MultiModalKwargs
 from vllm.sampling_params import SamplingType
 from vllm.sequence import IntermediateTensors
-from vllm.utils import (DeviceMemoryProfiler, LayerBlockType, cdiv, LazyLoader)
+from vllm.utils import DeviceMemoryProfiler, LayerBlockType, LazyLoader, cdiv
 from vllm.v1.core.encoder_cache_manager import compute_encoder_budget
 from vllm.v1.kv_cache_interface import (FullAttentionSpec, KVCacheConfig,
                                         KVCacheSpec)
@@ -50,7 +50,7 @@
 from vllm_ascend.platform import NPUPlatform
 
 if TYPE_CHECKING:
-    import xgrammar as xgr
+    import xgrammar as xgr  # type: ignore[import-untyped]
     from vllm.v1.core.sched.output import SchedulerOutput
 else:
     xgr = LazyLoader("xgr", globals(), "xgrammar")