diff --git a/vllm/v1/worker/gpu_worker.py b/vllm/v1/worker/gpu_worker.py
index d61177d4245dd..f83a4f4faeb5e 100644
--- a/vllm/v1/worker/gpu_worker.py
+++ b/vllm/v1/worker/gpu_worker.py
@@ -292,7 +292,6 @@ class Worker(WorkerBase):
             allocator = CuMemAllocator.get_instance()
             context = allocator.use_memory_pool(tag="kv_cache")
         else:
-            from contextlib import nullcontext
             context = nullcontext()
         with context:
             self.model_runner.initialize_kv_cache(kv_cache_config)
diff --git a/vllm/worker/worker.py b/vllm/worker/worker.py
index 7a01e585ba6d0..fc24d95b80f2c 100644
--- a/vllm/worker/worker.py
+++ b/vllm/worker/worker.py
@@ -3,6 +3,7 @@
 """A GPU worker class."""
 import gc
 import os
+from contextlib import nullcontext
 from typing import Dict, List, Optional, Set, Tuple, Type, Union
 
 import torch
@@ -206,7 +207,6 @@ class Worker(LocalOrDistributedWorkerBase):
                 "used for one instance per process.")
             context = allocator.use_memory_pool(tag="weights")
         else:
-            from contextlib import nullcontext
             context = nullcontext()
         with context:
             self.model_runner.load_model()
@@ -330,7 +330,6 @@ class Worker(LocalOrDistributedWorkerBase):
             allocator = CuMemAllocator.get_instance()
             context = allocator.use_memory_pool(tag="kv_cache")
         else:
-            from contextlib import nullcontext
             context = nullcontext()
         with context:
             self._init_cache_engine()