diff --git a/vllm_ascend/worker/model_runner_v1.py b/vllm_ascend/worker/model_runner_v1.py
index ae9c695..a400f90 100644
--- a/vllm_ascend/worker/model_runner_v1.py
+++ b/vllm_ascend/worker/model_runner_v1.py
@@ -3147,7 +3147,7 @@ class NPUModelRunner(LoRAModelRunnerMixin):
 
         if block_sizes != [
                 self.cache_config.block_size
-        ] or kernel_block_sizes != [self.cache_config.block_size]:
+        ] or kernel_block_sizes != [[self.cache_config.block_size]]:
             assert self.cache_config.cpu_offload_gb == 0, (
                 "Cannot re-initialize the input batch when CPU weight "
                 "offloading is enabled. See https://github.com/vllm-project/vllm/pull/18298 "  # noqa: E501