update

Signed-off-by: shen-shanshan <[email protected]>

Author: shen-shanshan

vllm_ascend/utils.py

@@ -17,8 +17,8 @@
 # Adapted from vllm-project/vllm/vllm/worker/worker.py
 #
 
-import gc
 import atexit
+import gc
 import math
 from contextlib import contextmanager, nullcontext
 from threading import Lock

vllm_ascend/worker/worker.py

@@ -49,7 +49,7 @@
 from vllm_ascend.device_allocator.camem import CaMemAllocator
 from vllm_ascend.distributed.parallel_state import init_ascend_model_parallel
 from vllm_ascend.platform import NPUPlatform
-from vllm_ascend.utils import try_register_lib, clear_npu_memory
+from vllm_ascend.utils import clear_npu_memory, try_register_lib
 from vllm_ascend.worker.model_runner import NPUModelRunner
 from vllm_ascend.worker.pooling_model_runner import NPUPoolingModelRunner
 

vllm_ascend/worker/worker_v1.py

@@ -43,7 +43,7 @@
 from vllm_ascend.device_allocator.camem import CaMemAllocator
 from vllm_ascend.distributed.parallel_state import init_ascend_model_parallel
 from vllm_ascend.platform import NPUPlatform
-from vllm_ascend.utils import try_register_lib, clear_npu_memory
+from vllm_ascend.utils import clear_npu_memory, try_register_lib
 from vllm_ascend.worker.model_runner_v1 import NPUModelRunner