活动介绍

WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator())

时间: 2025-07-04 10:45:52 浏览: 34
<think>好的,我现在需要解决用户在PyTorch中遇到的关于ProcessGroupNCCL未销毁的警告问题。首先,我得理解这个警告的具体含义。用户提到的警告是“ProcessGroupNCCL was not destroyed”,这意味着在程序结束时,NCCL进程组没有被正确销毁,可能导致资源泄漏或潜在的问题。 接下来,我应该考虑可能的原因。通常,这种警告发生在分布式训练环境中,特别是在使用多进程时,比如通过torch.multiprocessing或者DistributedDataParallel。可能的原因包括进程没有正确调用destroy_process_group(),或者进程在退出前没有协调好销毁操作。 然后,我需要回忆PyTorch的官方文档和社区讨论中的解决方案。根据经验,正确的做法是在每个进程的训练结束后显式调用torch.distributed.destroy_process_group()。此外,还需要确保所有进程在销毁之前已经完成了同步,比如使用dist.barrier()。 另一个可能的原因是程序异常退出,导致destroy_process_group()没有被执行。这时候,可能需要检查代码中是否有适当的异常处理机制,确保在出现错误时也能正确清理资源。 用户提供的参考引用是关于文本预处理的,可能与当前问题无关,但需要确认是否有其他潜在因素。不过,当前问题主要与分布式训练的资源管理有关,应专注于这方面的解决方案。 接下来,我需要验证这些解决方案的正确性。例如,在分布式训练脚本中,每个进程在训练结束后应调用destroy_process_group(),并且在初始化进程组时使用适当的后端(如'nccl')。同时,确保所有进程都达到销毁点,避免某些进程提前退出。 此外,用户可能没有正确设置cleanup函数,特别是在使用fork启动子进程的情况下,可能需要注册atexit处理程序来确保销毁操作。或者,在单机多卡训练中,使用torch.cuda.device()上下文管理器来管理不同GPU上的操作,防止资源未释放。 最后,总结常见的解决步骤:显式销毁进程组、确保同步、处理异常情况、正确初始化后端,以及可能的资源管理技巧。需要将这些步骤以清晰的方式呈现给用户,帮助他们逐步排查和解决问题。</think>关于PyTorch分布式训练中出现的`ProcessGroupNCCL was not destroyed`警告,以下是分步解决方案: ### 1. 显式销毁进程组 在分布式训练代码的**每个进程**结束时,必须调用: ```python torch.distributed.destroy_process_group() ``` 这是清除NCCL资源的必要操作[^1]。建议将代码封装在`try/finally`块中确保执行: ```python try: # 分布式训练代码 finally: torch.distributed.destroy_process_group() ``` ### 2. 进程同步机制 在销毁前插入同步屏障: ```python torch.distributed.barrier() torch.distributed.destroy_process_group() ``` 这确保所有进程都完成训练任务后才执行销毁操作。 ### 3. 后端初始化验证 检查进程组初始化是否正确指定`backend='nccl'`: ```python torch.distributed.init_process_group( backend='nccl', init_method='env://', world_size=world_size, rank=rank ) ``` 错误的backend配置会导致资源管理异常。 ### 4. 进程终止处理 对于使用`fork`启动的子进程,建议注册清理函数: ```python import atexit atexit.register(torch.distributed.destroy_process_group) ``` ### 5. 单机多卡优化 使用CUDA设备上下文管理器: ```python with torch.cuda.device(device_id): # 训练代码 ``` 这可以防止不同GPU间的资源竞争。
阅读全文

相关推荐

INFO 07-06 22:09:23 __init__.py:207] Automatically detected platform cuda. (VllmWorkerProcess pid=10542) INFO 07-06 22:09:23 multiproc_worker_utils.py:229] Worker ready; awaiting tasks (VllmWorkerProcess pid=10542) INFO 07-06 22:09:24 cuda.py:178] Cannot use FlashAttention-2 backend for Volta and Turing GPUs. (VllmWorkerProcess pid=10542) INFO 07-06 22:09:24 cuda.py:226] Using XFormers backend. (VllmWorkerProcess pid=10542) INFO 07-06 22:09:25 utils.py:916] Found nccl from library libnccl.so.2 (VllmWorkerProcess pid=10542) INFO 07-06 22:09:25 pynccl.py:69] vLLM is using nccl==2.21.5 INFO 07-06 22:09:25 utils.py:916] Found nccl from library libnccl.so.2 INFO 07-06 22:09:25 pynccl.py:69] vLLM is using nccl==2.21.5 INFO 07-06 22:09:25 custom_all_reduce_utils.py:206] generating GPU P2P access cache in /root/.cache/vllm/gpu_p2p_access_cache_for_0,1.json INFO 07-06 22:09:39 custom_all_reduce_utils.py:244] reading GPU P2P access cache from /root/.cache/vllm/gpu_p2p_access_cache_for_0,1.json (VllmWorkerProcess pid=10542) INFO 07-06 22:09:39 custom_all_reduce_utils.py:244] reading GPU P2P access cache from /root/.cache/vllm/gpu_p2p_access_cache_for_0,1.json WARNING 07-06 22:09:39 custom_all_reduce.py:145] Custom allreduce is disabled because your platform lacks GPU P2P capability or P2P test failed. To silence this warning, specify disable_custom_all_reduce=True explicitly. (VllmWorkerProcess pid=10542) WARNING 07-06 22:09:39 custom_all_reduce.py:145] Custom allreduce is disabled because your platform lacks GPU P2P capability or P2P test failed. To silence this warning, specify disable_custom_all_reduce=True explicitly. INFO 07-06 22:09:39 shm_broadcast.py:258] vLLM message queue communication handle: Handle(connect_ip='127.0.0.1', local_reader_ranks=[1], buffer_handle=(1, 4194304, 6, 'psm_b99a0acb'), local_subscribe_port=57279, remote_subscribe_port=None) INFO 07-06 22:09:39 model_runner.py:1110] Starting to load model /home/user/Desktop/DeepSeek-R1-Distill-Qwen-32B... (VllmWorkerProcess pid=10542) INFO 07-06 22:09:39 model_runner.py:1110] Starting to load model /home/user/Desktop/DeepSeek-R1-Distill-Qwen-32B... ERROR 07-06 22:09:39 engine.py:400] CUDA out of memory. Tried to allocate 136.00 MiB. GPU 0 has a total capacity of 21.49 GiB of which 43.50 MiB is free. Including non-PyTorch memory, this process has 21.44 GiB memory in use. Of the allocated memory 21.19 GiB is allocated by PyTorch, and 20.25 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables) ERROR 07-06 22:09:39 engine.py:400] Traceback (most recent call last): ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/engine/multiprocessing/engine.py", line 391, in run_mp_engine ERROR 07-06 22:09:39 engine.py:400] engine = MQLLMEngine.from_engine_args(engine_args=engine_args, ERROR 07-06 22:09:39 engine.py:400] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/engine/multiprocessing/engine.py", line 124, in from_engine_args ERROR 07-06 22:09:39 engine.py:400] return cls(ipc_path=ipc_path, ERROR 07-06 22:09:39 engine.py:400] ^^^^^^^^^^^^^^^^^^^^^^ ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/engine/multiprocessing/engine.py", line 76, in __init__ ERROR 07-06 22:09:39 engine.py:400] self.engine = LLMEngine(*args, **kwargs) ERROR 07-06 22:09:39 engine.py:400] ^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/engine/llm_engine.py", line 273, in __init__ ERROR 07-06 22:09:39 engine.py:400] self.model_executor = executor_class(vllm_config=vllm_config, ) ERROR 07-06 22:09:39 engine.py:400] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/executor/executor_base.py", line 271, in __init__ ERROR 07-06 22:09:39 engine.py:400] super().__init__(*args, **kwargs) ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/executor/executor_base.py", line 52, in __init__ ERROR 07-06 22:09:39 engine.py:400] self._init_executor() ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/executor/mp_distributed_executor.py", line 125, in _init_executor ERROR 07-06 22:09:39 engine.py:400] self._run_workers("load_model", ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/executor/mp_distributed_executor.py", line 185, in _run_workers ERROR 07-06 22:09:39 engine.py:400] driver_worker_output = run_method(self.driver_worker, sent_method, ERROR 07-06 22:09:39 engine.py:400] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/utils.py", line 2196, in run_method ERROR 07-06 22:09:39 engine.py:400] return func(*args, **kwargs) ERROR 07-06 22:09:39 engine.py:400] ^^^^^^^^^^^^^^^^^^^^^ ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/worker/worker.py", line 183, in load_model ERROR 07-06 22:09:39 engine.py:400] self.model_runner.load_model() ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/worker/model_runner.py", line 1112, in load_model ERROR 07-06 22:09:39 engine.py:400] self.model = get_model(vllm_config=self.vllm_config) ERROR 07-06 22:09:39 engine.py:400] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/model_loader/__init__.py", line 14, in get_model ERROR 07-06 22:09:39 engine.py:400] return loader.load_model(vllm_config=vllm_config) ERROR 07-06 22:09:39 engine.py:400] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/model_loader/loader.py", line 406, in load_model ERROR 07-06 22:09:39 engine.py:400] model = _initialize_model(vllm_config=vllm_config) ERROR 07-06 22:09:39 engine.py:400] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/model_loader/loader.py", line 125, in _initialize_model ERROR 07-06 22:09:39 engine.py:400] return model_class(vllm_config=vllm_config, prefix=prefix) ERROR 07-06 22:09:39 engine.py:400] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/models/qwen2.py", line 453, in __init__ ERROR 07-06 22:09:39 engine.py:400] self.model = Qwen2Model(vllm_config=vllm_config, ERROR 07-06 22:09:39 engine.py:400] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/compilation/decorators.py", line 151, in __init__ ERROR 07-06 22:09:39 engine.py:400] old_init(self, vllm_config=vllm_config, prefix=prefix, **kwargs) ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/models/qwen2.py", line 307, in __init__ ERROR 07-06 22:09:39 engine.py:400] self.start_layer, self.end_layer, self.layers = make_layers( ERROR 07-06 22:09:39 engine.py:400] ^^^^^^^^^^^^ ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/models/utils.py", line 557, in make_layers ERROR 07-06 22:09:39 engine.py:400] [PPMissingLayer() for _ in range(start_layer)] + [ ERROR 07-06 22:09:39 engine.py:400] ^ ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/models/utils.py", line 558, in ERROR 07-06 22:09:39 engine.py:400] maybe_offload_to_cpu(layer_fn(prefix=f"{prefix}.{idx}")) ERROR 07-06 22:09:39 engine.py:400] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/models/qwen2.py", line 309, in <lambda> ERROR 07-06 22:09:39 engine.py:400] lambda prefix: Qwen2DecoderLayer(config=config, ERROR 07-06 22:09:39 engine.py:400] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/models/qwen2.py", line 220, in __init__ ERROR 07-06 22:09:39 engine.py:400] self.mlp = Qwen2MLP( ERROR 07-06 22:09:39 engine.py:400] ^^^^^^^^^ ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/models/qwen2.py", line 82, in __init__ ERROR 07-06 22:09:39 engine.py:400] self.down_proj = RowParallelLinear( ERROR 07-06 22:09:39 engine.py:400] ^^^^^^^^^^^^^^^^^^ ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/layers/linear.py", line 1062, in __init__ ERROR 07-06 22:09:39 engine.py:400] self.quant_method.create_weights( ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/layers/linear.py", line 129, in create_weights ERROR 07-06 22:09:39 engine.py:400] weight = Parameter(torch.empty(sum(output_partition_sizes), ERROR 07-06 22:09:39 engine.py:400] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 07-06 22:09:39 engine.py:400] File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/torch/utils/_device.py", line 106, in __torch_function__ ERROR 07-06 22:09:39 engine.py:400] return func(*args, **kwargs) ERROR 07-06 22:09:39 engine.py:400] ^^^^^^^^^^^^^^^^^^^^^ ERROR 07-06 22:09:39 engine.py:400] torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 136.00 MiB. GPU 0 has a total capacity of 21.49 GiB of which 43.50 MiB is free. Including non-PyTorch memory, this process has 21.44 GiB memory in use. Of the allocated memory 21.19 GiB is allocated by PyTorch, and 20.25 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables) Process SpawnProcess-1: INFO 07-06 22:09:39 multiproc_worker_utils.py:128] Killing local vLLM worker processes Traceback (most recent call last): File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/engine/multiprocessing/engine.py", line 402, in run_mp_engine raise e File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/engine/multiprocessing/engine.py", line 391, in run_mp_engine engine = MQLLMEngine.from_engine_args(engine_args=engine_args, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/engine/multiprocessing/engine.py", line 124, in from_engine_args return cls(ipc_path=ipc_path, ^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/engine/multiprocessing/engine.py", line 76, in __init__ self.engine = LLMEngine(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/engine/llm_engine.py", line 273, in __init__ self.model_executor = executor_class(vllm_config=vllm_config, ) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/executor/executor_base.py", line 271, in __init__ super().__init__(*args, **kwargs) File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/executor/executor_base.py", line 52, in __init__ self._init_executor() File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/executor/mp_distributed_executor.py", line 125, in _init_executor self._run_workers("load_model", File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/executor/mp_distributed_executor.py", line 185, in _run_workers driver_worker_output = run_method(self.driver_worker, sent_method, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/utils.py", line 2196, in run_method return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/worker/worker.py", line 183, in load_model self.model_runner.load_model() File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/worker/model_runner.py", line 1112, in load_model self.model = get_model(vllm_config=self.vllm_config) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/model_loader/__init__.py", line 14, in get_model return loader.load_model(vllm_config=vllm_config) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/model_loader/loader.py", line 406, in load_model model = _initialize_model(vllm_config=vllm_config) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/model_loader/loader.py", line 125, in _initialize_model return model_class(vllm_config=vllm_config, prefix=prefix) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/models/qwen2.py", line 453, in __init__ self.model = Qwen2Model(vllm_config=vllm_config, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/compilation/decorators.py", line 151, in __init__ old_init(self, vllm_config=vllm_config, prefix=prefix, **kwargs) File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/models/qwen2.py", line 307, in __init__ self.start_layer, self.end_layer, self.layers = make_layers( ^^^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/models/utils.py", line 557, in make_layers [PPMissingLayer() for _ in range(start_layer)] + [ ^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/models/utils.py", line 558, in maybe_offload_to_cpu(layer_fn(prefix=f"{prefix}.{idx}")) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/models/qwen2.py", line 309, in <lambda> lambda prefix: Qwen2DecoderLayer(config=config, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/models/qwen2.py", line 220, in __init__ self.mlp = Qwen2MLP( ^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/models/qwen2.py", line 82, in __init__ self.down_proj = RowParallelLinear( ^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/layers/linear.py", line 1062, in __init__ self.quant_method.create_weights( File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/model_executor/layers/linear.py", line 129, in create_weights weight = Parameter(torch.empty(sum(output_partition_sizes), ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/torch/utils/_device.py", line 106, in __torch_function__ return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 136.00 MiB. GPU 0 has a total capacity of 21.49 GiB of which 43.50 MiB is free. Including non-PyTorch memory, this process has 21.44 GiB memory in use. Of the allocated memory 21.19 GiB is allocated by PyTorch, and 20.25 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables) [rank0]:[W706 22:09:40.345098611 ProcessGroupNCCL.cpp:1250] Warning: WARNING: process group has NOT been destroyed before we destruct ProcessGroupNCCL. On normal program exit, the application should call destroy_process_group to ensure that any pending NCCL operations have finished in this process. In rare cases this process can exit before this point and block the progress of another member of the process group. This constraint has always been present, but this warning has only been added since PyTorch 2.4 (function operator()) Traceback (most recent call last): File "/root/miniconda3/envs/deepseek_vllm/bin/vllm", line 8, in <module> sys.exit(main()) ^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/entrypoints/cli/main.py", line 73, in main args.dispatch_function(args) File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/entrypoints/cli/serve.py", line 34, in cmd uvloop.run(run_server(args)) File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/uvloop/__init__.py", line 105, in run return runner.run(wrapper()) ^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/asyncio/runners.py", line 118, in run return self._loop.run_until_complete(task) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/uvloop/__init__.py", line 61, in wrapper return await main ^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/entrypoints/openai/api_server.py", line 947, in run_server async with build_async_engine_client(args) as engine_client: File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/contextlib.py", line 210, in __aenter__ return await anext(self.gen) ^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/entrypoints/openai/api_server.py", line 139, in build_async_engine_client async with build_async_engine_client_from_engine_args( File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/contextlib.py", line 210, in __aenter__ return await anext(self.gen) ^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/envs/deepseek_vllm/lib/python3.11/site-packages/vllm/entrypoints/openai/api_server.py", line 233, in build_async_engine_client_from_engine_args raise RuntimeError( RuntimeError: Engine process failed to start. See stack trace for the root cause. (deepseek_vllm) root@user-X99:/home/user/Desktop# /root/miniconda3/envs/deepseek_vllm/lib/python3.11/multiprocessing/resource_tracker.py:254: UserWarning: resource_tracker: There appear to be 1 leaked shared_memory objects to clean up at shutdown warnings.warn('resource_tracker: There appear to be %d ' (deepseek_vllm) root@user-X99:/home/user/Desktop#

import logging import time from enum import Enum from typing import List, Dict, Optional, Any from threading import Lock from dataclasses import dataclass from PySide6.QtWidgets import QWidget, QVBoxLayout from PySide6.QtCore import Slot, Signal, QTimer from lightweight_charts.widgets import QtChart # 配置日志系统 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s') logger = logging.getLogger(__name__) class ChartState(Enum): """图表状态枚举""" INITIALIZING = "initializing" WEBVIEW_LOADING = "webview_loading" CHART_LOADING = "chart_loading" READY = "ready" ERROR = "error" @dataclass class ChartConfig: """图表配置类""" # 重试配置 max_retries: int = 5 initial_retry_interval: int = 500 # 毫秒 max_retry_interval: int = 5000 # 毫秒 # 缓存配置 max_pending_updates: int = 100 cache_cleanup_interval: int = 30 # 秒 max_cache_age: int = 300 # 秒 # 性能配置 batch_update_threshold: int = 10 # JavaScript检测配置 js_ready_check_interval: int = 100 # 毫秒 js_ready_max_attempts: int = 50 class DataValidator: """数据验证器""" @staticmethod def validate_historical_data(klines: List[Any]) -> bool: """验证历史K线数据格式""" if not klines or not isinstance(klines, list): return False try: for kline in klines: if not isinstance(kline, (list, tuple)) or len(kline) < 6: return False # 检查数值类型 for i in range(1, 6): # open, high, low, close, volume float(kline[i]) # 检查时间戳 int(kline[0]) return True except (ValueError, TypeError, IndexError): return False @staticmethod def validate_kline_update(kline: Dict[str, Any]) -> bool: """验证实时K线更新数据格式""" required_keys = ['t', 'o', 'h', 'l', 'c', 'v'] if not isinstance(kline, dict): return False try: for key in required_keys: if key not in kline: return False # 验证数值 float(kline['o']) # open float(kline['h']) # high float(kline['l']) # low float(kline['c']) # close float(kline['v']) # volume int(kline['t']) # timestamp # 验证价格逻辑(high >= max(open,close), low <= min(open,close)) o, h, l, c = float(kline['o']), float(kline['h']), float(kline['l']), float(kline['c']) if h < max(o, c) or l > min(o, c): logger.warning("K线数据价格逻辑不一致") return False return True except (ValueError, TypeError, KeyError): return False class LightweightChartWidget(QWidget): """ 一个使用 lightweight-charts 库来显示高性能金融图表的封装组件。 """ # 信号定义 chartReady = Signal() chartError = Signal(str) # 新增错误信号 stateChanged = Signal(str) # 新增状态变化信号 def __init__(self, symbol: str, interval: str, config: Optional[ChartConfig] = None, parent=None): super().__init__(parent) self.symbol = symbol self.interval = interval self.config = config or ChartConfig() # 状态管理 self._state = ChartState.INITIALIZING self._state_lock = Lock() self._is_destroyed = False # 销毁标志 # 数据缓存(增加时间戳) self._pending_historical_data: Optional[List[Any]] = None self._pending_updates: List[Dict[str, Any]] = [] self._cache_timestamps: List[float] = [] # 重试机制 self._retry_count = 0 self._current_retry_interval = self.config.initial_retry_interval # JavaScript就绪检测 self._js_ready_attempts = 0 self._js_ready_timer = QTimer() self._js_ready_timer.timeout.connect(self._check_javascript_ready) # 缓存清理定时器 self._cache_cleanup_timer = QTimer() self._cache_cleanup_timer.timeout.connect(self._cleanup_old_cache) self._cache_cleanup_timer.start(self.config.cache_cleanup_interval * 1000) # 性能优化:批量更新 self._batch_updates: List[Dict[str, Any]] = [] self._batch_timer = QTimer() self._batch_timer.setSingleShot(True) self._batch_timer.timeout.connect(self._process_batch_updates) self._setup_ui() self._set_state(ChartState.WEBVIEW_LOADING) def _setup_ui(self): """设置用户界面""" self.layout = QVBoxLayout(self) self.layout.setContentsMargins(0, 0, 0, 0) self.chart = QtChart(widget=self, inner_width=1, inner_height=1) self.webview = self.chart.get_webview() self.layout.addWidget(self.webview) # 应用样式配置 self._apply_chart_styles() # 连接WebView信号 self.webview.loadFinished.connect(self._on_webview_loaded) def _apply_chart_styles(self): """应用图表样式配置""" try: self.chart.layout( background_color='#131722', text_color='#D9D9D9', font_size=12 ) self.chart.grid( vert_enabled=True, horz_enabled=True, color='#3C4048', style='solid' ) self.chart.candle_style( up_color='#26a69a', down_color='#ef5350', border_up_color='#26a69a', border_down_color='#ef5350', wick_up_color='#26a69a', wick_down_color='#ef5350' ) self.chart.volume_config( up_color='rgba(38, 166, 154, 0.5)', down_color='rgba(239, 83, 80, 0.5)' ) except Exception as e: logger.error(f"应用图表样式时发生错误: {e}") def _set_state(self, new_state: ChartState): """线程安全的状态设置""" if getattr(self, '_is_destroyed', False): return with self._state_lock: if self._state != new_state: old_state = self._state self._state = new_state logger.info(f"[{self.symbol}] 状态变化: {old_state.value} -> {new_state.value}") try: self.stateChanged.emit(new_state.value) except (RuntimeError, AttributeError): # 信号可能已经断开 pass def get_state(self) -> ChartState: """获取当前状态""" with self._state_lock: return self._state @Slot(bool) def _on_webview_loaded(self, success: bool): """WebView加载完成处理""" if success: logger.info(f"[{self.symbol}] WebView加载成功,开始检测JavaScript就绪状态") self._set_state(ChartState.CHART_LOADING) self._reset_retry_state() self._start_javascript_ready_check() else: self._handle_load_failure() def _start_javascript_ready_check(self): """开始JavaScript就绪状态检测""" self._js_ready_attempts = 0 self._js_ready_timer.start(self.config.js_ready_check_interval) def _check_javascript_ready(self): """检测JavaScript图表库是否就绪""" self._js_ready_attempts += 1 # 检测代码:验证图表对象是否存在并可用 js_code = """ (function() { try { return window.chart && typeof window.chart === 'object' && typeof window.chart.update === 'function'; } catch(e) { return false; } })(); """ def on_result(result): if result: self._on_javascript_ready() elif self._js_ready_attempts >= self.config.js_ready_max_attempts: self._on_javascript_timeout() try: # 使用WebView的页面执行JavaScript self.webview.page().runJavaScript(js_code, on_result) except Exception as e: logger.warning(f"JavaScript就绪检测失败: {e}") if self._js_ready_attempts >= self.config.js_ready_max_attempts: self._on_javascript_timeout() def _on_javascript_ready(self): """JavaScript就绪处理""" self._js_ready_timer.stop() self._set_state(ChartState.READY) logger.info(f"[{self.symbol}] 图表完全就绪") # 发射就绪信号 self.chartReady.emit() # 处理缓存数据 self._process_cached_data() def _on_javascript_timeout(self): """JavaScript检测超时处理""" self._js_ready_timer.stop() error_msg = f"图表JavaScript初始化超时 (尝试了 {self._js_ready_attempts} 次)" logger.error(f"[{self.symbol}] {error_msg}") self._set_state(ChartState.ERROR) self.chartError.emit(error_msg) def _handle_load_failure(self): """处理加载失败""" self._retry_count += 1 error_msg = f"WebView加载失败 (尝试 {self._retry_count}/{self.config.max_retries})" logger.error(f"[{self.symbol}] {error_msg}") if self._retry_count < self.config.max_retries: # 指数退避重试 self._current_retry_interval = min( self._current_retry_interval * 2, self.config.max_retry_interval ) QTimer.singleShot(self._current_retry_interval, lambda: self.webview.reload()) else: error_msg = f"达到最大重试次数,加载失败" logger.critical(f"[{self.symbol}] {error_msg}") self._set_state(ChartState.ERROR) self.chartError.emit(error_msg) def _reset_retry_state(self): """重置重试状态""" self._retry_count = 0 self._current_retry_interval = self.config.initial_retry_interval def _process_cached_data(self): """处理缓存的数据""" try: # 处理历史数据 if self._pending_historical_data is not None: self._apply_historical_data(self._pending_historical_data) self._pending_historical_data = None # 处理缓存的更新 if self._pending_updates: for kline in self._pending_updates: self._apply_kline_update_internal(kline) self._clear_cache() except Exception as e: logger.error(f"[{self.symbol}] 处理缓存数据时发生错误: {e}") @Slot(list) def set_historical_data(self, klines: List[Any]): """设置历史数据""" if getattr(self, '_is_destroyed', False): return if not DataValidator.validate_historical_data(klines): error_msg = "历史K线数据格式验证失败" logger.error(f"[{self.symbol}] {error_msg}") try: self.chartError.emit(error_msg) except (RuntimeError, AttributeError): pass return if self.get_state() != ChartState.READY: logger.info(f"[{self.symbol}] 图表未就绪,缓存历史数据 ({len(klines)} 条)") self._pending_historical_data = klines return self._apply_historical_data(klines) def _apply_historical_data(self, klines: List[Any]): """应用历史数据到图表""" try: logger.info(f"[{self.symbol}] 处理 {len(klines)} 条历史K线数据") # 优化的数据处理:避免不必要的列操作 chart_data = [{ 'time': int(kline[0]), 'open': float(kline[1]), 'high': float(kline[2]), 'low': float(kline[3]), 'close': float(kline[4]), 'volume': float(kline[5]) } for kline in klines] self.chart.set(chart_data) logger.info(f"[{self.symbol}] 历史数据加载成功") except Exception as e: error_msg = f"处理历史数据时发生错误: {e}" logger.error(f"[{self.symbol}] {error_msg}") self.chartError.emit(error_msg) @Slot(dict) def update_kline(self, kline: Dict[str, Any]): """更新K线数据""" if getattr(self, '_is_destroyed', False): return if not DataValidator.validate_kline_update(kline): logger.warning(f"[{self.symbol}] 实时K线数据格式验证失败") return if self.get_state() != ChartState.READY: self._cache_update(kline) return # 批量处理优化 self._batch_updates.append(kline) if len(self._batch_updates) >= self.config.batch_update_threshold: self._process_batch_updates() else: # 延迟处理,允许批量积累 try: if hasattr(self, '_batch_timer') and not self._batch_timer.isActive(): self._batch_timer.start(50) # 50ms延迟 except (RuntimeError, AttributeError): # 定时器可能已被删除,直接处理 self._process_batch_updates() def _cache_update(self, kline: Dict[str, Any]): """缓存更新数据""" current_time = time.time() # 清理过期缓存 self._cleanup_old_cache() # 限制缓存大小 if len(self._pending_updates) >= self.config.max_pending_updates: # 移除最旧的数据 self._pending_updates.pop(0) self._cache_timestamps.pop(0) self._pending_updates.append(kline) self._cache_timestamps.append(current_time) def _process_batch_updates(self): """处理批量更新""" if not self._batch_updates: return try: # 处理最新的数据(通常只需要最后一条) latest_kline = self._batch_updates[-1] self._apply_kline_update_internal(latest_kline) self._batch_updates.clear() except Exception as e: logger.error(f"[{self.symbol}] 批量更新处理失败: {e}") def _apply_kline_update_internal(self, kline: Dict[str, Any]): """内部K线更新实现""" try: update_data = { 'time': pd.to_datetime(kline['t'], unit='ms'), 'open': float(kline['o']), 'high': float(kline['h']), 'low': float(kline['l']), 'close': float(kline['c']), 'volume': float(kline['v']) } kline_series = pd.Series(update_data) self.chart.update(kline_series) except Exception as e: logger.error(f"[{self.symbol}] 更新图表失败: {e}") def _cleanup_old_cache(self): """清理过期缓存""" if not self._cache_timestamps: return current_time = time.time() cutoff_time = current_time - self.config.max_cache_age # 找到第一个未过期的索引 valid_index = 0 for i, timestamp in enumerate(self._cache_timestamps): if timestamp >= cutoff_time: valid_index = i break else: valid_index = len(self._cache_timestamps) if valid_index > 0: self._pending_updates = self._pending_updates[valid_index:] self._cache_timestamps = self._cache_timestamps[valid_index:] logger.info(f"[{self.symbol}] 清理了 {valid_index} 条过期缓存") def _clear_cache(self): """清空所有缓存""" self._pending_updates.clear() self._cache_timestamps.clear() def force_refresh(self): """强制刷新图表""" logger.info(f"[{self.symbol}] 执行强制刷新") self._set_state(ChartState.WEBVIEW_LOADING) self._reset_retry_state() self.webview.reload() def get_cache_info(self) -> Dict[str, Any]: """获取缓存信息(用于调试)""" return { 'pending_updates_count': len(self._pending_updates), 'has_pending_historical': self._pending_historical_data is not None, 'batch_updates_count': len(self._batch_updates), 'state': self._state.value, 'retry_count': self._retry_count } def cleanup(self): """清理资源""" try: logger.info(f"[{self.symbol}] 开始清理资源") # 安全停止定时器 - 检查对象是否仍然有效 timers = [ ('js_ready_timer', self._js_ready_timer), ('cache_cleanup_timer', self._cache_cleanup_timer), ('batch_timer', self._batch_timer) ] for timer_name, timer in timers: try: if timer is not None and hasattr(timer, 'isActive') and timer.isActive(): timer.stop() logger.debug(f"[{self.symbol}] 已停止 {timer_name}") except (RuntimeError, AttributeError) as e: logger.debug(f"[{self.symbol}] {timer_name} 已被Qt清理: {e}") # 清理缓存 self._clear_cache() self._pending_historical_data = None logger.info(f"[{self.symbol}] 资源清理完成") except Exception as e: # 在析构过程中,日志系统可能也不可用,所以使用try-except try: logger.error(f"[{self.symbol}] 清理资源时发生错误: {e}") except: pass def __del__(self): """析构函数 - 安全版本""" try: if hasattr(self, '_is_destroyed') and not self._is_destroyed: if hasattr(self, '_pending_updates'): self._pending_updates.clear() if hasattr(self, '_cache_timestamps'): self._cache_timestamps.clear() if hasattr(self, '_batch_updates'): self._batch_updates.clear() self._pending_historical_data = None except: pass # 静默处理日志错误 def destroy_widget(self): """手动销毁组件(推荐使用此方法而非依赖析构函数)""" try: self.cleanup() try: self.chartReady.disconnect() self.chartError.disconnect() self.stateChanged.disconnect() if hasattr(self.webview, 'loadFinished'): self.webview.loadFinished.disconnect() except (RuntimeError, TypeError): pass # 信号可能已经断开或对象已删除 self._is_destroyed = True except Exception as e: try: logger.error(f"[{self.symbol}] 销毁组件时发生错误: {e}") except: pass 这样修复对吗?

npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code EPERM npm ERR! syscall open npm ERR! path D:\Node\node_cache\_cacache\tmp\eb2d693d npm ERR! errno -4048 npm ERR! Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\eb2d693d' npm ERR! [OperationalError: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\eb2d693d'] { npm ERR! cause: [Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\eb2d693d'] { npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\eb2d693d' npm ERR! }, npm ERR! isOperational: true, npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\eb2d693d' npm ERR! } npm ERR! npm ERR! The operation was rejected by your operating system. npm ERR! It's possible that the file was already in use (by a text editor or antivirus), npm ERR! or that you lack permissions to access it. npm ERR! npm ERR! If you believe this might be a permissions issue, please double-check the npm ERR! permissions of the file and its containing directories, or try running npm ERR! the command again as root/Administrator. npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code EPERM npm ERR! syscall open npm ERR! path D:\Node\node_cache\_cacache\tmp\eb2d693d npm ERR! errno -4048 npm ERR! Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\eb2d693d' npm ERR! [OperationalError: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\eb2d693d'] { npm ERR! cause: [Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\eb2d693d'] { npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\eb2d693d' npm ERR! }, npm ERR! isOperational: true, npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\eb2d693d' npm ERR! } npm ERR! npm ERR! The operation was rejected by your operating system. npm ERR! It's possible that the file was already in use (by a text editor or antivirus), npm ERR! or that you lack permissions to access it. npm ERR! npm ERR! If you believe this might be a permissions issue, please double-check the npm ERR! permissions of the file and its containing directories, or try running npm ERR! the command again as root/Administrator. npm ERR! code EPERM npm ERR! syscall open npm ERR! path D:\Node\node_cache\_cacache\tmp\a4a16f53 npm ERR! errno -4048 npm ERR! Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\a4a16f53' npm ERR! [OperationalError: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\a4a16f53'] { npm ERR! cause: [Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\a4a16f53'] { npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\a4a16f53' npm ERR! }, npm ERR! isOperational: true, npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\a4a16f53' npm ERR! } npm ERR! npm ERR! The operation was rejected by your operating system. npm ERR! It's possible that the file was already in use (by a text editor or antivirus), npm ERR! or that you lack permissions to access it. npm ERR! npm ERR! If you believe this might be a permissions issue, please double-check the npm ERR! permissions of the file and its containing directories, or try running npm ERR! the command again as root/Administrator. npm WARN registry Unexpected warning for https://registry.npmjs.org/: Miscellaneous Warning EPERM: EPERM: operation not permitted, open 'D:\\Node\\node_cache\\_cacache\\tmp\\6ee0a780' npm WARN registry Using stale data from https://registry.npmjs.org/ due to a request error during revalidation. npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code EPERM npm ERR! syscall open npm ERR! path D:\Node\node_cache\_cacache\tmp\aa34d15e npm ERR! errno -4048 npm ERR! Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\aa34d15e' npm ERR! [OperationalError: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\aa34d15e'] { npm ERR! cause: [Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\aa34d15e'] { npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\aa34d15e' npm ERR! }, npm ERR! isOperational: true, npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\aa34d15e' npm ERR! } npm ERR! npm ERR! The operation was rejected by your operating system. npm ERR! It's possible that the file was already in use (by a text editor or antivirus), npm ERR! or that you lack permissions to access it. npm ERR! npm ERR! If you believe this might be a permissions issue, please double-check the npm ERR! permissions of the file and its containing directories, or try running npm ERR! the command again as root/Administrator. npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code EPERM npm ERR! syscall open npm ERR! path D:\Node\node_cache\_cacache\tmp\dd6cc8ed npm ERR! errno -4048 npm ERR! Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\dd6cc8ed' npm ERR! [OperationalError: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\dd6cc8ed'] { npm ERR! cause: [Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\dd6cc8ed'] { npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\dd6cc8ed' npm ERR! }, npm ERR! isOperational: true, npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\dd6cc8ed' npm ERR! } npm ERR! npm ERR! The operation was rejected by your operating system. npm ERR! It's possible that the file was already in use (by a text editor or antivirus), npm ERR! or that you lack permissions to access it. npm ERR! npm ERR! If you believe this might be a permissions issue, please double-check the npm ERR! permissions of the file and its containing directories, or try running npm ERR! the command again as root/Administrator. npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code EPERM npm ERR! syscall open npm ERR! path D:\Node\node_cache\_cacache\tmp\df92457e npm ERR! errno -4048 npm ERR! Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\df92457e' npm ERR! [OperationalError: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\df92457e'] { npm ERR! cause: [Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\df92457e'] { npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\df92457e' npm ERR! }, npm ERR! isOperational: true, npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\df92457e' npm ERR! } npm ERR! npm ERR! The operation was rejected by your operating system. npm ERR! It's possible that the file was already in use (by a text editor or antivirus), npm ERR! or that you lack permissions to access it. npm ERR! npm ERR! If you believe this might be a permissions issue, please double-check the npm ERR! permissions of the file and its containing directories, or try running npm ERR! the command again as root/Administrator. npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code EPERM npm ERR! syscall open npm ERR! path D:\Node\node_cache\_cacache\tmp\dd6cc8ed npm ERR! errno -4048 npm ERR! Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\dd6cc8ed' npm ERR! [OperationalError: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\dd6cc8ed'] { npm ERR! cause: [Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\dd6cc8ed'] { npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\dd6cc8ed' npm ERR! }, npm ERR! isOperational: true, npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\dd6cc8ed' npm ERR! } npm ERR! npm ERR! The operation was rejected by your operating system. npm ERR! It's possible that the file was already in use (by a text editor or antivirus), npm ERR! or that you lack permissions to access it. npm ERR! npm ERR! If you believe this might be a permissions issue, please double-check the npm ERR! permissions of the file and its containing directories, or try running npm ERR! the command again as root/Administrator. npm ERR! code EPERM npm ERR! syscall open npm ERR! path D:\Node\node_cache\_cacache\tmp\01bdab06 npm ERR! errno -4048 npm ERR! Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\01bdab06' npm ERR! [OperationalError: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\01bdab06'] { npm ERR! cause: [Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\01bdab06'] { npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\01bdab06' npm ERR! }, npm ERR! isOperational: true, npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\01bdab06' npm ERR! } npm ERR! npm ERR! The operation was rejected by your operating system. npm ERR! It's possible that the file was already in use (by a text editor or antivirus), npm ERR! or that you lack permissions to access it. npm ERR! npm ERR! If you believe this might be a permissions issue, please double-check the npm ERR! permissions of the file and its containing directories, or try running npm ERR! the command again as root/Administrator. npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code EPERM npm ERR! syscall open npm ERR! path D:\Node\node_cache\_cacache\tmp\eb849235 npm ERR! errno -4048 npm ERR! Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\eb849235' npm ERR! [OperationalError: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\eb849235'] { npm ERR! cause: [Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\eb849235'] { npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\eb849235' npm ERR! }, npm ERR! isOperational: true, npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\eb849235' npm ERR! } npm ERR! npm ERR! The operation was rejected by your operating system. npm ERR! It's possible that the file was already in use (by a text editor or antivirus), npm ERR! or that you lack permissions to access it. npm ERR! npm ERR! If you believe this might be a permissions issue, please double-check the npm ERR! permissions of the file and its containing directories, or try running npm ERR! the command again as root/Administrator. npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code EPERM npm ERR! syscall open npm ERR! path D:\Node\node_cache\_cacache\tmp\df92457e npm ERR! errno -4048 npm ERR! Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\df92457e' npm ERR! [OperationalError: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\df92457e'] { npm ERR! cause: [Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\df92457e'] { npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\df92457e' npm ERR! }, npm ERR! isOperational: true, npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\df92457e' npm ERR! } npm ERR! npm ERR! The operation was rejected by your operating system. npm ERR! It's possible that the file was already in use (by a text editor or antivirus), npm ERR! or that you lack permissions to access it. npm ERR! npm ERR! If you believe this might be a permissions issue, please double-check the npm ERR! permissions of the file and its containing directories, or try running npm ERR! the command again as root/Administrator. npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code EPERM npm ERR! syscall open npm ERR! path D:\Node\node_cache\_cacache\tmp\3688e03a npm ERR! errno -4048 npm ERR! Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\3688e03a' npm ERR! [OperationalError: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\3688e03a'] { npm ERR! cause: [Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\3688e03a'] { npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\3688e03a' npm ERR! }, npm ERR! isOperational: true, npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\3688e03a' npm ERR! } npm ERR! npm ERR! The operation was rejected by your operating system. npm ERR! It's possible that the file was already in use (by a text editor or antivirus), npm ERR! or that you lack permissions to access it. npm ERR! npm ERR! If you believe this might be a permissions issue, please double-check the npm ERR! permissions of the file and its containing directories, or try running npm ERR! the command again as root/Administrator. npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code EPERM npm ERR! syscall open npm ERR! path D:\Node\node_cache\_cacache\tmp\35daa67e npm ERR! errno -4048 npm ERR! Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\35daa67e' npm ERR! [OperationalError: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\35daa67e'] { npm ERR! cause: [Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\35daa67e'] { npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\35daa67e' npm ERR! }, npm ERR! isOperational: true, npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\35daa67e' npm ERR! } npm ERR! npm ERR! The operation was rejected by your operating system. npm ERR! It's possible that the file was already in use (by a text editor or antivirus), npm ERR! or that you lack permissions to access it. npm ERR! npm ERR! If you believe this might be a permissions issue, please double-check the npm ERR! permissions of the file and its containing directories, or try running npm ERR! the command again as root/Administrator. npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code EPERM npm ERR! syscall open npm ERR! path D:\Node\node_cache\_cacache\tmp\35daa67e npm ERR! errno -4048 npm ERR! Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\35daa67e' npm ERR! [OperationalError: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\35daa67e'] { npm ERR! cause: [Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\35daa67e'] { npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\35daa67e' npm ERR! }, npm ERR! isOperational: true, npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\35daa67e' npm ERR! } npm ERR! npm ERR! The operation was rejected by your operating system. npm ERR! It's possible that the file was already in use (by a text editor or antivirus), npm ERR! or that you lack permissions to access it. npm ERR! npm ERR! If you believe this might be a permissions issue, please double-check the npm ERR! permissions of the file and its containing directories, or try running npm ERR! the command again as root/Administrator. npm ERR! code EPERM npm ERR! syscall open npm ERR! path D:\Node\node_cache\_cacache\tmp\01bdab06 npm ERR! errno -4048 npm ERR! Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\01bdab06' npm ERR! [OperationalError: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\01bdab06'] { npm ERR! cause: [Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\01bdab06'] { npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\01bdab06' npm ERR! }, npm ERR! isOperational: true, npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\01bdab06' npm ERR! } npm ERR! npm ERR! The operation was rejected by your operating system. npm ERR! It's possible that the file was already in use (by a text editor or antivirus), npm ERR! or that you lack permissions to access it. npm ERR! npm ERR! If you believe this might be a permissions issue, please double-check the npm ERR! permissions of the file and its containing directories, or try running npm ERR! the command again as root/Administrator. npm ERR! code EPERM npm ERR! syscall open npm ERR! path D:\Node\node_cache\_cacache\tmp\884bfc72 npm ERR! errno -4048 npm ERR! Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\884bfc72' npm ERR! [OperationalError: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\884bfc72'] { npm ERR! cause: [Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\884bfc72'] { npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\884bfc72' npm ERR! }, npm ERR! isOperational: true, npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\884bfc72' npm ERR! } npm ERR! npm ERR! The operation was rejected by your operating system. npm ERR! It's possible that the file was already in use (by a text editor or antivirus), npm ERR! or that you lack permissions to access it. npm ERR! npm ERR! If you believe this might be a permissions issue, please double-check the npm ERR! permissions of the file and its containing directories, or try running npm ERR! the command again as root/Administrator. npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code EPERM npm ERR! syscall open npm ERR! path D:\Node\node_cache\_cacache\tmp\aa34d15e npm ERR! errno -4048 npm ERR! Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\aa34d15e' npm ERR! [OperationalError: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\aa34d15e'] { npm ERR! cause: [Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\aa34d15e'] { npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\aa34d15e' npm ERR! }, npm ERR! isOperational: true, npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\aa34d15e' npm ERR! } npm ERR! npm ERR! The operation was rejected by your operating system. npm ERR! It's possible that the file was already in use (by a text editor or antivirus), npm ERR! or that you lack permissions to access it. npm ERR! npm ERR! If you believe this might be a permissions issue, please double-check the npm ERR! permissions of the file and its containing directories, or try running npm ERR! the command again as root/Administrator. npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code ERR_STREAM_DESTROYED npm ERR! Cannot call write after a stream was destroyed npm ERR! code EPERM npm ERR! syscall open npm ERR! path D:\Node\node_cache\_cacache\tmp\3688e03a npm ERR! errno -4048 npm ERR! Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\3688e03a' npm ERR! [OperationalError: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\3688e03a'] { npm ERR! cause: [Error: EPERM: operation not permitted, open 'D:\Node\node_cache\_cacache\tmp\3688e03a'] { npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\3688e03a' npm ERR! }, npm ERR! isOperational: true, npm ERR! errno: -4048, npm ERR! code: 'EPERM', npm ERR! syscall: 'open', npm ERR! path: 'D:\\Node\\node_cache\\_cacache\\tmp\\3688e03a' npm ERR! } npm ERR! npm ERR! The operation was rejected by your operating system. npm ERR! It's possible that the file was already in use (by a text editor or antivirus), npm ERR! or that you lack permissions to access it. npm ERR! npm ERR! If you believe this might be a permissions issue, please double-check the npm ERR! permissions of the file and its containing directories, or try running npm ERR! the command again as root/Administrator.

最新推荐

recommend-type

Comsol声子晶体能带计算:六角与三角晶格原胞选取及布里渊区高对称点选择 - 声子晶体 v1.0

内容概要:本文详细探讨了利用Comsol进行声子晶体能带计算过程中,六角晶格和三角晶格原胞选取的不同方法及其对简约布里渊区高对称点选择的影响。文中不仅介绍了两种晶格类型的基矢量定义方式,还强调了正确设置周期性边界条件(特别是相位补偿)的重要性,以避免计算误差如鬼带现象。同时,提供了具体的MATLAB代码片段用于演示关键步骤,并分享了一些实践经验,例如如何通过观察能带图中的狄拉克锥特征来验证路径设置的准确性。 适合人群:从事材料科学、物理学研究的专业人士,尤其是那些正在使用或计划使用Comsol软件进行声子晶体模拟的研究人员。 使用场景及目标:帮助研究人员更好地理解和掌握在Comsol环境中针对不同类型晶格进行精确的声子晶体能带计算的方法和技术要点,从而提高仿真精度并减少常见错误的发生。 其他说明:文章中提到的实际案例展示了因晶格类型混淆而导致的问题,提醒使用者注意细节差异,确保模型构建无误。此外,文中提供的代码片段可以直接应用于相关项目中作为参考模板。
recommend-type

springboot213大学生心理健康管理系统的设计与实现.zip

springboot213大学生心理健康管理系统的设计与实现
recommend-type

三轴自动锁螺丝机PLC配方编程:吸钉式锁螺丝智能调整与注释详解 变址寄存器 高效版

一种基于三菱FX系列PLC的三轴自动锁螺丝机的配方编程方法。该系统采用吸钉式锁螺丝方式,通过PLC进行智能管理和调整。主要内容包括:利用D寄存器阵列和变址寄存器Z来存储和管理不同配方的数据,如坐标和螺丝数量;通过触摸屏和示教器简化调试流程,使工人能够快速设置和保存参数;并通过RS指令将数据保存到触摸屏内置存储中。此外,还展示了具体的PLC程序片段,解释了如何通过简单的寄存器操作实现复杂的配方管理和自动化操作。 适合人群:从事工业自动化领域的工程师和技术人员,尤其是熟悉PLC编程和机械设备调试的专业人士。 使用场景及目标:适用于需要提高生产效率和简化调试流程的制造业企业。主要目标是帮助技术人员掌握如何使用PLC进行配方管理,优化自动锁螺丝机的操作流程,减少人工干预,提升设备的智能化水平。 其他说明:文中提供的具体PLC程序代码和详细的注释有助于读者更好地理解和应用相关技术。同时,通过实例演示了如何利用PLC寄存器寻址特性和变址寄存器简化程序逻辑,为类似项目提供有价值的参考。
recommend-type

基于QT与STM32的Modbus-TCP四遥功能实现及源码解析

基于Qt开发的Modbus-TCP远程控制系统,用于实现四遥(遥测、遥控、遥信、遥调)功能。系统由上位机和下位机组成,上位机使用Qt进行图形界面开发,下位机采用STM32和W5500以太网模块,所有Modbus功能均自行实现,未使用第三方库。文中具体展示了各个功能的实现细节,包括ADC数据采集、LED控制、按键状态读取以及参数调节等功能的具体代码实现。 适合人群:具有一定嵌入式开发经验的研发人员,尤其是熟悉Qt和STM32的开发者。 使用场景及目标:适用于工业自动化、智能家居等领域,旨在帮助开发者理解和实现基于Modbus-TCP协议的远程控制系统,掌握四遥功能的具体实现方法。 其他说明:文中提供了详细的代码片段和技术难点解析,有助于读者深入理解系统的实现过程。同时,针对常见的开发问题给出了具体的解决方案,如浮点数转换、字节序处理等。
recommend-type

ERP系统客户与供应商信息视图创建:Oracle数据库中客户和供应商数据整合查询设计

内容概要:本文档定义了一个名为 `xxx_SCustSuplier_info` 的视图,用于整合和展示客户(Customer)和供应商(Supplier)的相关信息。视图通过连接多个表来获取组织单位、客户账户、站点使用、位置、财务代码组合等数据。对于客户部分,视图选择了与账单相关的记录,并提取了账单客户ID、账单站点ID、客户名称、账户名称、站点代码、状态、付款条款等信息;对于供应商部分,视图选择了有效的供应商及其站点信息,包括供应商ID、供应商名称、供应商编号、状态、付款条款、财务代码组合等。视图还通过外连接确保即使某些字段为空也能显示相关信息。 适合人群:熟悉Oracle ERP系统,尤其是应付账款(AP)和应收账款(AR)模块的数据库管理员或开发人员;需要查询和管理客户及供应商信息的业务分析师。 使用场景及目标:① 数据库管理员可以通过此视图快速查询客户和供应商的基本信息,包括账单信息、财务代码组合等;② 开发人员可以利用此视图进行报表开发或数据迁移;③ 业务分析师可以使用此视图进行数据分析,如信用评估、付款周期分析等。 阅读建议:由于该视图涉及多个表的复杂连接,建议读者先熟悉各个表的结构和关系,特别是 `hz_parties`、`hz_cust_accounts`、`ap_suppliers` 等核心表。此外,注意视图中使用的外连接(如 `gl_code_combinations_kfv` 表的连接),这可能会影响查询结果的完整性。
recommend-type

Web前端开发:CSS与HTML设计模式深入解析

《Pro CSS and HTML Design Patterns》是一本专注于Web前端设计模式的书籍,特别针对CSS(层叠样式表)和HTML(超文本标记语言)的高级应用进行了深入探讨。这本书籍属于Pro系列,旨在为专业Web开发人员提供实用的设计模式和实践指南,帮助他们构建高效、美观且可维护的网站和应用程序。 在介绍这本书的知识点之前,我们首先需要了解CSS和HTML的基础知识,以及它们在Web开发中的重要性。 HTML是用于创建网页和Web应用程序的标准标记语言。它允许开发者通过一系列的标签来定义网页的结构和内容,如段落、标题、链接、图片等。HTML5作为最新版本,不仅增强了网页的表现力,还引入了更多新的特性,例如视频和音频的内置支持、绘图API、离线存储等。 CSS是用于描述HTML文档的表现(即布局、颜色、字体等样式)的样式表语言。它能够让开发者将内容的表现从结构中分离出来,使得网页设计更加模块化和易于维护。随着Web技术的发展,CSS也经历了多个版本的更新,引入了如Flexbox、Grid布局、过渡、动画以及Sass和Less等预处理器技术。 现在让我们来详细探讨《Pro CSS and HTML Design Patterns》中可能包含的知识点: 1. CSS基础和选择器: 书中可能会涵盖CSS基本概念,如盒模型、边距、填充、边框、背景和定位等。同时还会介绍CSS选择器的高级用法,例如属性选择器、伪类选择器、伪元素选择器以及选择器的组合使用。 2. CSS布局技术: 布局是网页设计中的核心部分。本书可能会详细讲解各种CSS布局技术,包括传统的浮动(Floats)布局、定位(Positioning)布局,以及最新的布局模式如Flexbox和CSS Grid。此外,也会介绍响应式设计的媒体查询、视口(Viewport)单位等。 3. 高级CSS技巧: 这些技巧可能包括动画和过渡效果,以及如何优化性能和兼容性。例如,CSS3动画、关键帧动画、转换(Transforms)、滤镜(Filters)和混合模式(Blend Modes)。 4. HTML5特性: 书中可能会深入探讨HTML5的新标签和语义化元素,如`<article>`、`<section>`、`<nav>`等,以及如何使用它们来构建更加标准化和语义化的页面结构。还会涉及到Web表单的新特性,比如表单验证、新的输入类型等。 5. 可访问性(Accessibility): Web可访问性越来越受到重视。本书可能会介绍如何通过HTML和CSS来提升网站的无障碍访问性,比如使用ARIA标签(Accessible Rich Internet Applications)来增强屏幕阅读器的使用体验。 6. 前端性能优化: 性能优化是任何Web项目成功的关键。本书可能会涵盖如何通过优化CSS和HTML来提升网站的加载速度和运行效率。内容可能包括代码压缩、合并、避免重绘和回流、使用Web字体的最佳实践等。 7. JavaScript与CSS/HTML的交互: 在现代Web开发中,JavaScript与CSS及HTML的交云并用是不可或缺的。书中可能会讲解如何通过JavaScript动态地修改样式、操作DOM元素以及使用事件监听和响应用户交互。 8. Web框架和预处理器: 这本书可能会提到流行的Web开发框架和预处理器,比如Bootstrap、Foundation、Sass和Less等,它们是如何简化和加速开发流程的。 9. 测试和维护: 书中也可能包含关于如何测试网页以及如何持续优化和维护CSS和HTML代码的章节。例如,使用断言测试、自动化测试、性能分析工具等。 最后,鉴于文件名称列表中的“压缩包子文件”的表述,这可能是对“压缩包”文件的一种误译或误用,此处“压缩包”应该指的是包含该书籍PDF文件的压缩文件格式,如ZIP或RAR。而“Pro CSS and HTML Design Patterns.pdf”指的就是该书籍的PDF格式电子版文件。 以上所述,构成了《Pro CSS and HTML Design Patterns》一书可能包含的核心知识点。通过学习这些内容,Web前端开发者可以掌握更为高效和优雅的设计模式,从而在日常工作中更高效地解决实际问题。
recommend-type

Zotero 7数据同步:Attanger插件安装&设置,打造文献管理利器

/i.s3.glbimg.com/v1/AUTH_08fbf48bc0524877943fe86e43087e7a/internal_photos/bs/2018/L/j/ipKA8TRPyt4ptaG1DGww/t-m-01.png) # 1. Zotero 7数据同步简介 在数字时代,管理研究数据变得日益重要,而Zot
recommend-type

卷积神经网络的基础理论200字

<think>我们正在回答用户关于卷积神经网络(CNN)基础理论的询问。根据提供的引用资料,我们可以概述CNN的基本结构和工作原理。引用[1]提到CNN是一种前馈神经网络,信息从输入单向流动到输出。引用[2]指出CNN在图像处理等领域应用广泛,通过层次结构和参数调整实现模式识别。引用[3]说明CNN包含卷积层,使用卷积核提取局部特征,减少参数量,提高效率。引用[4]则提到了训练过程,包括前向传播、误差计算和反向传播(梯度下降)。因此,我们将从以下几个方面概述CNN:1.CNN的基本结构(卷积层、池化层、全连接层)2.卷积操作的工作原理(局部感受野、权重共享)3.训练过程(前向传播、损失函数、反
recommend-type

轻便实用的Java库类查询工具介绍

标题 "java2库类查询" 和描述表明,所提及的工具是一个专门用于查询Java库类的应用程序。此软件旨在帮助开发者快速地查找和引用Java的标准开发工具包(SDK)中包含的所有应用程序编程接口(API)类。通过这样的工具,开发者可以节省大量在官方文档或搜索引擎上寻找类定义和使用方法的时间。它被描述为轻巧且方便,这表明其占用的系统资源相对较少,同时提供直观的用户界面,使得查询过程简洁高效。 从描述中可以得出几个关键知识点: 1. Java SDK:Java的软件开发工具包(SDK)是Java平台的一部分,提供了一套用于开发Java应用软件的软件包和库。这些软件包通常被称为API,为开发者提供了编程界面,使他们能够使用Java语言编写各种类型的应用程序。 2. 库类查询:这个功能对于开发者来说非常关键,因为它提供了一个快速查找特定库类及其相关方法、属性和使用示例的途径。良好的库类查询工具可以帮助开发者提高工作效率,减少因查找文档而中断编程思路的时间。 3. 轻巧性:软件的轻巧性通常意味着它对计算机资源的要求较低。这样的特性对于资源受限的系统尤为重要,比如老旧的计算机、嵌入式设备或是当开发者希望最小化其开发环境占用空间时。 4. 方便性:软件的方便性通常关联于其用户界面设计,一个直观、易用的界面可以让用户快速上手,并减少在使用过程中遇到的障碍。 5. 包含所有API:一个优秀的Java库类查询软件应当能够覆盖Java所有标准API,这包括Java.lang、Java.util、Java.io等核心包,以及Java SE平台的所有其他标准扩展包。 从标签 "java 库 查询 类" 可知,这个软件紧密关联于Java编程语言的核心功能——库类的管理和查询。这些标签可以关联到以下知识点: - Java:一种广泛用于企业级应用、移动应用(如Android应用)、网站后端、大型系统和许多其他平台的编程语言。 - 库:在Java中,库是一组预打包的类和接口,它们可以被应用程序重复使用。Java提供了庞大的标准库,以支持各种常见的任务和功能。 - 查询:查询指的是利用软件工具搜索、定位和检索信息的过程。对于Java库类查询工具来说,这意味着可以通过类名、方法签名或其他标识符来查找特定的API条目。 最后,压缩包文件列表包含了两个文件:“java.dit”和“Java.exe”。其中“Java.exe”很可能是程序的可执行文件,而“java.dit”可能是一个数据文件,用于存储Java类的索引或数据。由于文件名后缀通常与文件类型相关联,但“dit”并不是一个常见的文件扩展名。这可能是一个特定于软件的自定义格式,或是一个打字错误。 总结来说,"java2库类查询" 是一个针对Java开发者的实用工具,它提供了一个轻量级、易用的平台来查询和定位Java标准库中的所有类和API。此工具对优化开发流程,减少查找Java类文档的时间大有裨益,尤其适合需要频繁查阅Java API的开发者使用。
recommend-type

【Zotero 7终极指南】:新手必备!Attanger插件全攻略与数据同步神技

# 1. Zotero 7与Attanger插件的介绍 在当今的学术研究和知识管理领域,高效的文献管理工具至关重要。Zotero 7作为一个流行的参考文献管理软件,因其强大的功能和用户友好的界面而受到专业人士的青睐。而Attanger插件则为Zotero 7带来了更多定制化和高级功能,极大地增强