diff --git a/vllm_ascend/worker.py b/vllm_ascend/worker.py
index d1e0765a..bcb6bdeb 100644
--- a/vllm_ascend/worker.py
+++ b/vllm_ascend/worker.py
@@ -22,7 +22,6 @@
 
 import torch
 import torch.distributed
-import torch_npu
 from torch import nn
 from vllm import envs
 from vllm.config import ParallelConfig, VllmConfig
@@ -124,6 +123,8 @@ def __init__(
         # Torch profiler. Enabled and configured through env vars:
         # VLLM_TORCH_PROFILER_DIR=/path/to/save/trace
         if envs.VLLM_TORCH_PROFILER_DIR:
+            # lazy import so that torch_npu is not required for normal use.
+            import torch_npu
             torch_profiler_trace_dir = envs.VLLM_TORCH_PROFILER_DIR
             logger.info("Profiling enabled. Traces will be saved to: %s",
                         torch_profiler_trace_dir)