File "D:\QwenAgent\index03.py", line 3, in <module> from qwen_agent import retrieve ImportError: cannot import name 'retrieve' from 'qwen_agent' (E:\miniconda3\envs\qwenagent\lib\site-packages\qwen_agent\__init__.py)

时间: 2025-06-10 10:00:19 浏览: 39
<think>好的,我现在遇到了一个导入错误的问题,具体是ImportError: 无法从'qwen_agent'中导入名称'retrieve'。我需要解决这个问题,但首先得弄清楚原因。 根据用户提供的引用内容,里面提到将elastic检索作为工具,但get_relevant_documents函数的输入只能由大模型控制,只能输入一个条件。这可能意味着当前的qwen_agent库中的retrieve模块可能已经被修改或者移除了,或者可能没有正确安装或导入。 首先,我应该检查是否安装了正确版本的qwen-agent库。有时候库的版本更新会导致某些函数或模块被重命名或弃用。用户可能安装的是旧版本或新版本,而代码中引用的retrieve模块在当前版本中不存在。 其次,查看库的官方文档或源代码(如果有权限的话),确认retrieve是否确实存在于qwen_agent模块中。如果文档中没有提到retrieve,可能这个模块已经被替换为其他名称,比如retrieve_tool或者其他类似的名称。例如,引用中提到的get_relevant_documents可能是一个相关的函数,需要确认其所在的模块。 另外,检查代码中导入语句是否正确。是否有拼写错误,比如Retrieve的大小写是否正确,或者是否在子模块中。例如,可能需要从qwen_agent.tools中导入retrieve,而不是直接从qwen_agent导入。 还有一种可能性是,retrieve可能已经被废弃,推荐使用其他方法来实现相同的功能。例如,根据引用中的描述,可能需要通过agent的方式来调用检索工具,而不是直接导入retrieve。比如,使用工具注册的方式,或者通过配置agent来调用相应的检索功能。 此外,如果库的结构发生了变化,可能需要更新导入路径。例如,原本retrieve可能位于qwen_agent模块的顶层,但现在被移动到子模块如qwen_agent.tools中,所以正确的导入应该是from qwen_agent.tools import retrieve。 最后,如果所有方法都尝试过仍然无法解决,可能需要联系库的维护者或查看社区的讨论,看看是否有其他人遇到同样的问题,是否有已知的解决方案或替代方法。 总结可能的解决步骤: 1. 确认qwen-agent库的版本,并尝试升级或降级到兼容版本。 2. 检查导入语句的正确性,包括模块路径和拼写。 3. 查阅官方文档或源代码,确认retrieve模块的存在和正确用法。 4. 尝试使用替代的导入方式或函数名称。 5. 如果问题依旧,考虑重构代码以适应库的最新结构,或者寻求社区支持。</think>要解决无法从`qwen_agent`导入`retrieve`的问题,请按以下步骤排查: ### 1. **检查库版本与文档兼容性** - 确认安装的`qwen-agent`版本是否支持`retrieve`模块。若库已更新,该模块可能被重命名或移除。尝试: ```bash pip install --upgrade qwen-agent ``` 或回退到旧版本(如已知兼容版本): ```bash pip install qwen-agent==0.3.0 # 替换为具体版本号 ``` ### 2. **验证模块路径与命名** - 根据引用中提到的工具化设计[^1],`retrieve`可能已整合到其他子模块中。尝试以下导入方式: ```python from qwen_agent.tools import retrieve_tool # 常见替代名称 ``` 或通过`Agent`类调用工具: ```python from qwen_agent import Agent agent = Agent(tools=['retrieve']) # 通过配置启用检索工具 ``` ### 3. **检查代码依赖关系** - 若库要求额外依赖(如Elasticsearch连接器),确保已安装: ```bash pip install elasticsearch qwen-agent[extras] ``` ### 4. **替代方案与代码调整** - 若模块确实不存在,可参考引用中工具化思路,直接调用底层函数: ```python from qwen_agent.utils import get_relevant_documents result = get_relevant_documents(query="your_query", name="doc_name") ``` ### 5. **联系维护者** - 通过GitHub Issues或官方社区反馈问题,附上错误日志和环境信息。 ---
阅读全文

相关推荐

Successfully installed huggingface_hub-0.9.1 (latentsync) [[email protected] ~/TujiaProjects/AiDigitalHuman/CosyVoice]$ python demo.py Traceback (most recent call last): File "/home/q/qitjwang/.conda/envs/latentsync/lib/python3.10/site-packages/modelscope/utils/hf_util/auto_class.py", line 80, in <module> get_all_imported_modules(), wrap=True) File "/home/q/qitjwang/.conda/envs/latentsync/lib/python3.10/site-packages/modelscope/utils/hf_util/patcher.py", line 35, in get_all_imported_modules import transformers File "/home/q/qitjwang/.conda/envs/latentsync/lib/python3.10/site-packages/transformers/__init__.py", line 26, in <module> from . import dependency_versions_check File "/home/q/qitjwang/.conda/envs/latentsync/lib/python3.10/site-packages/transformers/dependency_versions_check.py", line 16, in <module> from .utils.versions import require_version, require_version_core File "/home/q/qitjwang/.conda/envs/latentsync/lib/python3.10/site-packages/transformers/utils/__init__.py", line 22, in <module> from huggingface_hub.constants import HF_HUB_DISABLE_TELEMETRY as DISABLE_TELEMETRY # for backward compatibility ImportError: cannot import name 'HF_HUB_DISABLE_TELEMETRY' from 'huggingface_hub.constants' (/home/q/qitjwang/.conda/envs/latentsync/lib/python3.10/site-packages/huggingface_hub/constants.py) Traceback (most recent call last): File "/home/q/qitjwang/TujiaProjects/AiDigitalHuman/CosyVoice/demo.py", line 3, in <module> from cosyvoice.cli.cosyvoice import CosyVoice, CosyVoice2 File "/home/q/qitjwang/TujiaProjects/AiDigitalHuman/CosyVoice/cosyvoice/cli/cosyvoice.py", line 24, in <module> from cosyvoice.utils.class_utils import get_model_type File "/home/q/qitjwang/TujiaProjects/AiDigitalHuman/CosyVoice/cosyvoice/utils/class_utils.py", line 35, in <module> from cosyvoice.llm.llm import TransformerLM, Qwen2LM File "/home/q/qitjwang/TujiaProjects/AiDigitalHuman/CosyVoice/cosyvoice/llm/llm.py", line 18, in <module> from transformers import Qwen2ForCausalLM File "/home/q/qitjwang/.conda/envs/latentsync/lib/python3.10/site-packages/transformers/__init__.py", line 26, in <module> from . import dependency_versions_check File "/home/q/qitjwang/.conda/envs/latentsync/lib/python3.10/site-packages/transformers/dependency_versions_check.py", line 16, in <module> from .utils.versions import require_version, require_version_core File "/home/q/qitjwang/.conda/envs/latentsync/lib/python3.10/site-packages/transformers/utils/__init__.py", line 22, in <module> from huggingface_hub.constants import HF_HUB_DISABLE_TELEMETRY as DISABLE_TELEMETRY # for backward compatibility ImportError: cannot import name 'HF_HUB_DISABLE_TELEMETRY' from 'huggingface_hub.constants' (/home/q/qitjwang/.conda/envs/latentsync/lib/python3.10/site-packages/huggingface_hub/constants.py)

(changwenben) ubuntu@ubuntu-Lenovo-Product:~/llama.cpp$ python convert_hf_to_gguf.py /home/ubuntu/QwenLong-L1-32B --outfile QwenLong-L1-32B.gguf Traceback (most recent call last): File "/home/ubuntu/llama.cpp/convert_hf_to_gguf.py", line 19, in <module> from transformers import AutoConfig File "/home/ubuntu/changwenben/lib/python3.12/site-packages/transformers/utils/import_utils.py", line 2045, in __getattr__ module = self._get_module(self._class_to_module[name]) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/ubuntu/changwenben/lib/python3.12/site-packages/transformers/utils/import_utils.py", line 2075, in _get_module raise e File "/home/ubuntu/changwenben/lib/python3.12/site-packages/transformers/utils/import_utils.py", line 2073, in _get_module return importlib.import_module("." + module_name, self.__name__) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/lib/python3.12/importlib/__init__.py", line 90, in import_module return _bootstrap._gcd_import(name[level:], package, level) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/ubuntu/changwenben/lib/python3.12/site-packages/transformers/models/auto/configuration_auto.py", line 24, in <module> from ...configuration_utils import PretrainedConfig File "/home/ubuntu/changwenben/lib/python3.12/site-packages/transformers/configuration_utils.py", line 27, in <module> from .modeling_gguf_pytorch_utils import load_gguf_checkpoint File "/home/ubuntu/changwenben/lib/python3.12/site-packages/transformers/modeling_gguf_pytorch_utils.py", line 22, in <module> from .integrations import ( ImportError: cannot import name 'GGUF_CONFIG_MAPPING' from 'transformers.integrations' (/home/ubuntu/changwenben/lib/python3.12/site-packages/transformers/integrations/__init__.py). Did you mean: 'GGUF_TOKENIZER_MAPPING'?

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#

(vllm) zhzx@zhzx-S2600WF-LS:/media/zhzx/ssd2/Qwen3-32B$ vllm serve "/media/zhzx/ssd2/Qwen3-32B" --host 0.0.0.0 --port 8060 --dtype bfloat16 --tensor-parallel-size 2 --cpu-offload-gb 20 --gpu-memory-utilization 0.8 --max-model-len 8126 --api-key token-abc123 --enable-prefix-caching --trust-remote-code \ > INFO 05-10 20:06:33 [__init__.py:239] Automatically detected platform cuda. INFO 05-10 20:06:36 [api_server.py:1043] vLLM API server version 0.8.5.post1 INFO 05-10 20:06:36 [api_server.py:1044] args: Namespace(subparser='serve', model_tag='/media/zhzx/ssd2/Qwen3-32B', config='', host='0.0.0.0', port=8060, uvicorn_log_level='info', disable_uvicorn_access_log=False, allow_credentials=False, allowed_origins=['*'], allowed_methods=['*'], allowed_headers=['*'], api_key='token-abc123', lora_modules=None, prompt_adapters=None, chat_template=None, chat_template_content_format='auto', response_role='assistant', ssl_keyfile=None, ssl_certfile=None, ssl_ca_certs=None, enable_ssl_refresh=False, ssl_cert_reqs=0, root_path=None, middleware=[], return_tokens_as_token_ids=False, disable_frontend_multiprocessing=False, enable_request_id_headers=False, enable_auto_tool_choice=False, tool_call_parser=None, tool_parser_plugin='', model='/media/zhzx/ssd2/Qwen3-32B', task='auto', tokenizer=None, hf_config_path=None, skip_tokenizer_init=False, revision=None, code_revision=None, tokenizer_revision=None, tokenizer_mode='auto', trust_remote_code=True, allowed_local_media_path=None, load_format='auto', download_dir=None, model_loader_extra_config={}, use_tqdm_on_load=True, config_format=<ConfigFormat.AUTO: 'auto'>, dtype='bfloat16', max_model_len=8126, guided_decoding_backend='auto', reasoning_parser=None, logits_processor_pattern=None, model_impl='auto', distributed_executor_backend=None, pipeline_parallel_size=1, tensor_parallel_size=2, data_parallel_size=1, enable_expert_parallel=False, max_parallel_loading_workers=None, ray_workers_use_nsight=False, disable_custom_all_reduce=False, block_size=None, gpu_memory_utilization=0.8, swap_space=4, kv_cache_dtype='auto', num_gpu_blocks_override=None, enable_prefix_caching=True, prefix_caching_hash_algo='builtin', cpu_offload_gb=20.0, calculate_kv_scales=False, disable_sliding_window=False, use_v2_block_manager=True, seed=None, max_logprobs=20, disable_log_stats=False, quantization=None, rope_scaling=None, rope_theta=None, hf_token=None, hf_overrides=None, enforce_eager=False, max_seq_len_to_capture=8192, tokenizer_pool_size=0, tokenizer_pool_type='ray', tokenizer_pool_extra_config={}, limit_mm_per_prompt={}, mm_processor_kwargs=None, disable_mm_preprocessor_cache=False, enable_lora=None, enable_lora_bias=False, max_loras=1, max_lora_rank=16, lora_extra_vocab_size=256, lora_dtype='auto', long_lora_scaling_factors=None, max_cpu_loras=None, fully_sharded_loras=False, enable_prompt_adapter=None, max_prompt_adapters=1, max_prompt_adapter_token=0, device='auto', speculative_config=None, ignore_patterns=[], served_model_name=None, qlora_adapter_name_or_path=None, show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None, disable_async_output_proc=False, max_num_batched_tokens=None, max_num_seqs=None, max_num_partial_prefills=1, max_long_partial_prefills=1, long_prefill_token_threshold=0, num_lookahead_slots=0, scheduler_delay_factor=0.0, preemption_mode=None, num_scheduler_steps=1, multi_step_stream_outputs=True, scheduling_policy='fcfs', enable_chunked_prefill=None, disable_chunked_mm_input=False, scheduler_cls='vllm.core.scheduler.Scheduler', override_neuron_config=None, override_pooler_config=None, compilation_config=None, kv_transfer_config=None, worker_cls='auto', worker_extension_cls='', generation_config='auto', override_generation_config=None, enable_sleep_mode=False, additional_config=None, enable_reasoning=False, disable_cascade_attn=False, disable_log_requests=False, max_log_len=None, disable_fastapi_docs=False, enable_prompt_tokens_details=False, enable_server_load_tracking=False, dispatch_function=<function ServeSubcommand.cmd at 0x7f625a071bc0>) WARNING 05-10 20:06:36 [config.py:2972] Casting torch.float16 to torch.bfloat16. INFO 05-10 20:06:42 [config.py:717] This model supports multiple tasks: {'reward', 'embed', 'generate', 'classify', 'score'}. Defaulting to 'generate'. WARNING 05-10 20:06:42 [arg_utils.py:1658] Compute Capability < 8.0 is not supported by the V1 Engine. Falling back to V0. INFO 05-10 20:06:42 [config.py:1770] Defaulting to use mp for distributed inference INFO 05-10 20:06:42 [api_server.py:246] Started engine process with PID 73230 INFO 05-10 20:06:45 [__init__.py:239] Automatically detected platform cuda. INFO 05-10 20:06:47 [llm_engine.py:240] Initializing a V0 LLM engine (v0.8.5.post1) with config: model='/media/zhzx/ssd2/Qwen3-32B', speculative_config=None, tokenizer='/media/zhzx/ssd2/Qwen3-32B', skip_tokenizer_init=False, tokenizer_mode=auto, revision=None, override_neuron_config=None, tokenizer_revision=None, trust_remote_code=True, dtype=torch.bfloat16, max_seq_len=8126, download_dir=None, load_format=LoadFormat.AUTO, tensor_parallel_size=2, pipeline_parallel_size=1, disable_custom_all_reduce=False, quantization=None, enforce_eager=False, kv_cache_dtype=auto, device_config=cuda, decoding_config=DecodingConfig(guided_decoding_backend='auto', reasoning_backend=None), observability_config=ObservabilityConfig(show_hidden_metrics=False, otlp_traces_endpoint=None, collect_model_forward_time=False, collect_model_execute_time=False), seed=None, served_model_name=/media/zhzx/ssd2/Qwen3-32B, num_scheduler_steps=1, multi_step_stream_outputs=True, enable_prefix_caching=True, chunked_prefill_enabled=False, use_async_output_proc=True, disable_mm_preprocessor_cache=False, mm_processor_kwargs=None, pooler_config=None, compilation_config={"splitting_ops":[],"compile_sizes":[],"cudagraph_capture_sizes":[256,248,240,232,224,216,208,200,192,184,176,168,160,152,144,136,128,120,112,104,96,88,80,72,64,56,48,40,32,24,16,8,4,2,1],"max_capture_size":256}, use_cached_outputs=True, WARNING 05-10 20:06:48 [multiproc_worker_utils.py:306] Reducing Torch parallelism from 16 threads to 1 to avoid unnecessary CPU contention. Set OMP_NUM_THREADS in the external environment to tune this value as needed. INFO 05-10 20:06:48 [cuda.py:240] Cannot use FlashAttention-2 backend for Volta and Turing GPUs. INFO 05-10 20:06:48 [cuda.py:289] Using XFormers backend. INFO 05-10 20:06:50 [__init__.py:239] Automatically detected platform cuda. (VllmWorkerProcess pid=73270) INFO 05-10 20:06:53 [multiproc_worker_utils.py:225] Worker ready; awaiting tasks (VllmWorkerProcess pid=73270) INFO 05-10 20:06:53 [cuda.py:240] Cannot use FlashAttention-2 backend for Volta and Turing GPUs. (VllmWorkerProcess pid=73270) INFO 05-10 20:06:53 [cuda.py:289] Using XFormers backend. ERROR 05-10 20:06:53 [engine.py:448] Bfloat16 is only supported on GPUs with compute capability of at least 8.0. Your Quadro RTX 6000 GPU has compute capability 7.5. You can use float16 instead by explicitly setting the dtype flag in CLI, for example: --dtype=half. ERROR 05-10 20:06:53 [engine.py:448] Traceback (most recent call last): ERROR 05-10 20:06:53 [engine.py:448] File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 436, in run_mp_engine ERROR 05-10 20:06:53 [engine.py:448] engine = MQLLMEngine.from_vllm_config( ERROR 05-10 20:06:53 [engine.py:448] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 05-10 20:06:53 [engine.py:448] File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 128, in from_vllm_config ERROR 05-10 20:06:53 [engine.py:448] return cls( ERROR 05-10 20:06:53 [engine.py:448] ^^^^ ERROR 05-10 20:06:53 [engine.py:448] File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 82, in __init__ ERROR 05-10 20:06:53 [engine.py:448] self.engine = LLMEngine(*args, **kwargs) ERROR 05-10 20:06:53 [engine.py:448] ^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 05-10 20:06:53 [engine.py:448] File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/engine/llm_engine.py", line 275, in __init__ ERROR 05-10 20:06:53 [engine.py:448] self.model_executor = executor_class(vllm_config=vllm_config) ERROR 05-10 20:06:53 [engine.py:448] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 05-10 20:06:53 [engine.py:448] File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/executor/executor_base.py", line 286, in __init__ ERROR 05-10 20:06:53 [engine.py:448] super().__init__(*args, **kwargs) ERROR 05-10 20:06:53 [engine.py:448] File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/executor/executor_base.py", line 52, in __init__ ERROR 05-10 20:06:53 [engine.py:448] self._init_executor() ERROR 05-10 20:06:53 [engine.py:448] File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/executor/mp_distributed_executor.py", line 124, in _init_executor ERROR 05-10 20:06:53 [engine.py:448] self._run_workers("init_device") ERROR 05-10 20:06:53 [engine.py:448] File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/executor/mp_distributed_executor.py", line 185, in _run_workers ERROR 05-10 20:06:53 [engine.py:448] driver_worker_output = run_method(self.driver_worker, sent_method, ERROR 05-10 20:06:53 [engine.py:448] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 05-10 20:06:53 [engine.py:448] File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/utils.py", line 2456, in run_method ERROR 05-10 20:06:53 [engine.py:448] return func(*args, **kwargs) ERROR 05-10 20:06:53 [engine.py:448] ^^^^^^^^^^^^^^^^^^^^^ ERROR 05-10 20:06:53 [engine.py:448] File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/worker/worker_base.py", line 604, in init_device ERROR 05-10 20:06:53 [engine.py:448] self.worker.init_device() # type: ignore ERROR 05-10 20:06:53 [engine.py:448] ^^^^^^^^^^^^^^^^^^^^^^^^^ ERROR 05-10 20:06:53 [engine.py:448] File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/worker/worker.py", line 177, in init_device ERROR 05-10 20:06:53 [engine.py:448] _check_if_gpu_supports_dtype(self.model_config.dtype) ERROR 05-10 20:06:53 [engine.py:448] File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/worker/worker.py", line 546, in _check_if_gpu_supports_dtype ERROR 05-10 20:06:53 [engine.py:448] raise ValueError( ERROR 05-10 20:06:53 [engine.py:448] ValueError: Bfloat16 is only supported on GPUs with compute capability of at least 8.0. Your Quadro RTX 6000 GPU has compute capability 7.5. You can use float16 instead by explicitly setting the dtype flag in CLI, for example: --dtype=half. Process SpawnProcess-1: ERROR 05-10 20:06:53 [multiproc_worker_utils.py:120] Worker VllmWorkerProcess pid 73270 died, exit code: -15 INFO 05-10 20:06:53 [multiproc_worker_utils.py:124] Killing local vLLM worker processes Traceback (most recent call last): File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 450, in run_mp_engine raise e File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 436, in run_mp_engine engine = MQLLMEngine.from_vllm_config( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 128, in from_vllm_config return cls( ^^^^ File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/engine/multiprocessing/engine.py", line 82, in __init__ self.engine = LLMEngine(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/engine/llm_engine.py", line 275, in __init__ self.model_executor = executor_class(vllm_config=vllm_config) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/executor/executor_base.py", line 286, in __init__ super().__init__(*args, **kwargs) File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/executor/executor_base.py", line 52, in __init__ self._init_executor() File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/executor/mp_distributed_executor.py", line 124, in _init_executor self._run_workers("init_device") File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/executor/mp_distributed_executor.py", line 185, in _run_workers driver_worker_output = run_method(self.driver_worker, sent_method, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/utils.py", line 2456, in run_method return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/worker/worker_base.py", line 604, in init_device self.worker.init_device() # type: ignore ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/worker/worker.py", line 177, in init_device _check_if_gpu_supports_dtype(self.model_config.dtype) File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/worker/worker.py", line 546, in _check_if_gpu_supports_dtype raise ValueError( ValueError: Bfloat16 is only supported on GPUs with compute capability of at least 8.0. Your Quadro RTX 6000 GPU has compute capability 7.5. You can use float16 instead by explicitly setting the dtype flag in CLI, for example: --dtype=half. Traceback (most recent call last): File "/home/zhzx/miniconda3/envs/vllm/bin/vllm", line 8, in <module> sys.exit(main()) ^^^^^^ File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/entrypoints/cli/main.py", line 53, in main args.dispatch_function(args) File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/entrypoints/cli/serve.py", line 27, in cmd uvloop.run(run_server(args)) File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/uvloop/__init__.py", line 109, in run return __asyncio.run( ^^^^^^^^^^^^^^ File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/asyncio/runners.py", line 195, in run return runner.run(main) ^^^^^^^^^^^^^^^^ File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/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 "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/uvloop/__init__.py", line 61, in wrapper return await main ^^^^^^^^^^ File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 1078, in run_server async with build_async_engine_client(args) as engine_client: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/contextlib.py", line 210, in __aenter__ return await anext(self.gen) ^^^^^^^^^^^^^^^^^^^^^ File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 146, in build_async_engine_client async with build_async_engine_client_from_engine_args( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/contextlib.py", line 210, in __aenter__ return await anext(self.gen) ^^^^^^^^^^^^^^^^^^^^^ File "/home/zhzx/miniconda3/envs/vllm/lib/python3.12/site-packages/vllm/entrypoints/openai/api_server.py", line 269, in build_async_engine_client_from_engine_args raise RuntimeError( RuntimeError: Engine process failed to start. See stack trace for the root cause.

/home/wiseatc/.local/lib/python3.11/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81. import pkg_resources W0703 16:30:36.069853 3914856 torch/distributed/run.py:766] W0703 16:30:36.069853 3914856 torch/distributed/run.py:766] ***************************************** W0703 16:30:36.069853 3914856 torch/distributed/run.py:766] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. W0703 16:30:36.069853 3914856 torch/distributed/run.py:766] ***************************************** /home/wiseatc/.local/lib/python3.11/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81. import pkg_resources [INFO|tokenization_utils_base.py:2048] 2025-07-03 16:30:43,321 >> loading file tokenizer.model [INFO|tokenization_utils_base.py:2048] 2025-07-03 16:30:43,322 >> loading file tokenizer.json [INFO|tokenization_utils_base.py:2048] 2025-07-03 16:30:43,322 >> loading file added_tokens.json [INFO|tokenization_utils_base.py:2048] 2025-07-03 16:30:43,322 >> loading file special_tokens_map.json [INFO|tokenization_utils_base.py:2048] 2025-07-03 16:30:43,322 >> loading file tokenizer_config.json [INFO|tokenization_utils_base.py:2048] 2025-07-03 16:30:43,322 >> loading file chat_template.jinja /home/wiseatc/.local/lib/python3.11/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81. import pkg_resources /home/wiseatc/.local/lib/python3.11/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81. import pkg_resources /home/wiseatc/.local/lib/python3.11/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81. import pkg_resources [INFO|tokenization_utils_base.py:2313] 2025-07-03 16:30:43,904 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. [INFO|configuration_utils.py:697] 2025-07-03 16:30:43,913 >> loading configuration file /mnt/data1/models/1.5B/config.json [INFO|configuration_utils.py:771] 2025-07-03 16:30:43,919 >> Model config Qwen2Config { "_name_or_path": "/mnt/data1/models/1.5B", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 1536, "initializer_range": 0.02, "intermediate_size": 8960, "max_position_embeddings": 131072, "max_window_layers": 21, "model_type": "qwen2", "num_attention_heads": 12, "num_hidden_layers": 28, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.49.0", "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 151936 } [INFO|tokenization_utils_base.py:2048] 2025-07-03 16:30:43,920 >> loading file tokenizer.model [INFO|tokenization_utils_base.py:2048] 2025-07-03 16:30:43,920 >> loading file tokenizer.json [INFO|tokenization_utils_base.py:2048] 2025-07-03 16:30:43,920 >> loading file added_tokens.json [INFO|tokenization_utils_base.py:2048] 2025-07-03 16:30:43,920 >> loading file special_tokens_map.json [INFO|tokenization_utils_base.py:2048] 2025-07-03 16:30:43,920 >> loading file tokenizer_config.json [INFO|tokenization_utils_base.py:2048] 2025-07-03 16:30:43,920 >> loading file chat_template.jinja [INFO|tokenization_utils_base.py:2313] 2025-07-03 16:30:44,493 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. /usr/local/lib/python3.11/dist-packages/torch/distributed/distributed_c10d.py:4631: UserWarning: No device id is provided via init_process_group or barrier . Using the current device set by the user. warnings.warn( # warn only once [rank1]:[W703 16:30:45.102845887 ProcessGroupNCCL.cpp:4718] [PG ID 0 PG GUID 0 Rank 1] using GPU 1 as device used by this process is currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. You can pecify device_id in init_process_group() to force use of a particular device. /usr/local/lib/python3.11/dist-packages/torch/distributed/distributed_c10d.py:4631: UserWarning: No device id is provided via init_process_group or barrier . Using the current device set by the user. warnings.warn( # warn only once [rank2]:[W703 16:30:45.126706430 ProcessGroupNCCL.cpp:4718] [PG ID 0 PG GUID 0 Rank 2] using GPU 2 as device used by this process is currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. You can pecify device_id in init_process_group() to force use of a particular device. /usr/local/lib/python3.11/dist-packages/torch/distributed/distributed_c10d.py:4631: UserWarning: No device id is provided via init_process_group or barrier . Using the current device set by the user. warnings.warn( # warn only once [rank3]:[W703 16:30:45.136836682 ProcessGroupNCCL.cpp:4718] [PG ID 0 PG GUID 0 Rank 3] using GPU 3 as device used by this process is currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. You can pecify device_id in init_process_group() to force use of a particular device. Setting num_proc from 16 back to 1 for the train split to disable multiprocessing as it only contains one shard. Generating train split: 0 examples [00:00, ? examples/s] Generating train split: 120 examples [00:00, 6525.39 examples/s] Converting format of dataset (num_proc=16): 0%| | 0/120 [00:00<?, ? examples/s] Converting format of dataset (num_proc=16): 0%| | 0/120 [00:00<?, ? examples/s] Converting format of dataset (num_proc=16): 0%| | 0/120 [00:00<?, ? examples/s] /usr/local/lib/python3.11/dist-packages/torch/distributed/distributed_c10d.py:4631: UserWarning: No device id is provided via init_process_group or barrier . Using the current device set by the user. warnings.warn( # warn only once [rank0]:[W703 16:31:05.679961201 ProcessGroupNCCL.cpp:4718] [PG ID 0 PG GUID 0 Rank 0] using GPU 0 as device used by this process is currently unknown. This can potentially cause a hang if this rank to GPU mapping is incorrect. You can pecify device_id in init_process_group() to force use of a particular device. [rank0]: multiprocess.pool.RemoteTraceback: [rank0]: """ [rank0]: Traceback (most recent call last): [rank0]: File "/home/wiseatc/.local/lib/python3.11/site-packages/multiprocess/pool.py", line 125, in worker [rank0]: result = (True, func(*args, **kwds)) [rank0]: ^^^^^^^^^^^^^^^^^^^ [rank0]: File "/home/wiseatc/.local/lib/python3.11/site-packages/datasets/utils/py_utils.py", line 688, in _write_generator_to_queue [rank0]: for i, result in enumerate(func(**kwargs)): [rank0]: File "/home/wiseatc/.local/lib/python3.11/site-packages/datasets/arrow_dataset.py", line 3501, in _map_single [rank0]: for i, example in iter_outputs(shard_iterable): [rank0]: File "/home/wiseatc/.local/lib/python3.11/site-packages/datasets/arrow_dataset.py", line 3475, in iter_outputs [rank0]: yield i, apply_function(example, i, offset=offset) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/home/wiseatc/.local/lib/python3.11/site-packages/datasets/arrow_dataset.py", line 3398, in apply_function [rank0]: processed_inputs = function(*fn_args, *additional_args, **fn_kwargs) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/home/wiseatc/LLaMA-Factory/src/llamafactory/data/converter.py", line 94, in __call__ [rank0]: if self.dataset_attr.prompt and example[self.dataset_attr.prompt]: [rank0]: ~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/home/wiseatc/.local/lib/python3.11/site-packages/datasets/formatting/formatting.py", line 278, in __getitem__ [rank0]: value = self.data[key] [rank0]: ~~~~~~~~~^^^^^ [rank0]: KeyError: 'instruction' [rank0]: """ [rank0]: The above exception was the direct cause of the following exception: [rank0]: Traceback (most recent call last): [rank0]: File "/home/wiseatc/LLaMA-Factory/src/llamafactory/launcher.py", line 23, in <module> [rank0]: launch() [rank0]: File "/home/wiseatc/LLaMA-Factory/src/llamafactory/launcher.py", line 19, in launch [rank0]: run_exp() [rank0]: File "/home/wiseatc/LLaMA-Factory/src/llamafactory/train/tuner.py", line 110, in run_exp [rank0]: _training_function(config={"args": args, "callbacks": callbacks}) [rank0]: File "/home/wiseatc/LLaMA-Factory/src/llamafactory/train/tuner.py", line 72, in _training_function [rank0]: run_sft(model_args, data_args, training_args, finetuning_args, generating_args, callbacks) [rank0]: File "/home/wiseatc/LLaMA-Factory/src/llamafactory/train/sft/workflow.py", line 51, in run_sft [rank0]: dataset_module = get_dataset(template, model_args, data_args, training_args, stage="sft", **tokenizer_module) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/home/wiseatc/LLaMA-Factory/src/llamafactory/data/loader.py", line 304, in get_dataset [rank0]: dataset = _get_merged_dataset(data_args.dataset, model_args, data_args, training_args, stage) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/home/wiseatc/LLaMA-Factory/src/llamafactory/data/loader.py", line 182, in _get_merged_dataset [rank0]: datasets[dataset_name] = _load_single_dataset(dataset_attr, model_args, data_args, training_args) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/home/wiseatc/LLaMA-Factory/src/llamafactory/data/loader.py", line 162, in _load_single_dataset [rank0]: return align_dataset(dataset, dataset_attr, data_args, training_args) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/home/wiseatc/LLaMA-Factory/src/llamafactory/data/converter.py", line 279, in align_dataset [rank0]: return dataset.map( [rank0]: ^^^^^^^^^^^^ [rank0]: File "/home/wiseatc/.local/lib/python3.11/site-packages/datasets/arrow_dataset.py", line 557, in wrapper [rank0]: out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs) [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/home/wiseatc/.local/lib/python3.11/site-packages/datasets/arrow_dataset.py", line 3171, in map [rank0]: for rank, done, content in iflatmap_unordered( [rank0]: File "/home/wiseatc/.local/lib/python3.11/site-packages/datasets/utils/py_utils.py", line 728, in iflatmap_unordered [rank0]: [async_result.get(timeout=0.05) for async_result in async_results] [rank0]: File "/home/wiseatc/.local/lib/python3.11/site-packages/datasets/utils/py_utils.py", line 728, in [rank0]: [async_result.get(timeout=0.05) for async_result in async_results] [rank0]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ [rank0]: File "/home/wiseatc/.local/lib/python3.11/site-packages/multiprocess/pool.py", line 774, in get [rank0]: raise self._value [rank0]: KeyError: 'instruction' [rank0]:[W703 16:31:06.912491219 ProcessGroupNCCL.cpp:1479] Warning: WARNING: destroy_process_group() was not called before program exit, which can leak resources. For more info, please see https://pytorch.org/docs/stable/distributed.html#shutdown (function operator()) W0703 16:31:07.960560 3914856 torch/distributed/elastic/multiprocessing/api.py:900] Sending process 3914916 closing signal SIGTERM W0703 16:31:07.961188 3914856 torch/distributed/elastic/multiprocessing/api.py:900] Sending process 3914917 closing signal SIGTERM W0703 16:31:07.961536 3914856 torch/distributed/elastic/multiprocessing/api.py:900] Sending process 3914918 closing signal SIGTERM E0703 16:31:08.371267 3914856 torch/distributed/elastic/multiprocessing/api.py:874] failed (exitcode: 1) local_rank: 0 (pid: 3914915) of binary: /usr/bin/python3.11 Traceback (most recent call last): File "/usr/local/bin/torchrun", line 8, in <module> sys.exit(main()) ^^^^^^ File "/usr/local/lib/python3.11/dist-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper return f(*args, **kwargs) ^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/dist-packages/torch/distributed/run.py", line 892, in main run(args) File "/usr/local/lib/python3.11/dist-packages/torch/distributed/run.py", line 883, in run elastic_launch( File "/usr/local/lib/python3.11/dist-packages/torch/distributed/launcher/api.py", line 139, in __call__ return launch_agent(self._config, self._entrypoint, list(args)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.11/dist-packages/torch/distributed/launcher/api.py", line 270, in launch_agent raise ChildFailedError( torch.distributed.elastic.multiprocessing.errors.ChildFailedError: ============================================================ /home/wiseatc/LLaMA-Factory/src/llamafactory/launcher.py FAILED ------------------------------------------------------------ Failures: <NO_OTHER_FAILURES> ------------------------------------------------------------ Root Cause (first observed failure): [0]: time : 2025-07-03_16:31:07 host : wiseatc-Super-Server rank : 0 (local_rank: 0) exitcode : 1 (pid: 3914915) error_file: <N/A> traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html ============================================================ Traceback (most recent call last): File "/home/wiseatc/.local/bin/llamafactory-cli", line 8, in <module> sys.exit(main()) ^^^^^^ File "/home/wiseatc/LLaMA-Factory/src/llamafactory/cli.py", line 130, in main process = subprocess.run( ^^^^^^^^^^^^^^^ File "/usr/lib/python3.11/subprocess.py", line 569, in run raise CalledProcessError(retcode, process.args, subprocess.CalledProcessError: Command '['torchrun', '--nnodes', '1', '--node_rank', '0', '--nproc_per_node', '4', '--master_addr', '127.0.0.1', '--master_port', '41919', '/home/wiseatc/LLaMA-Factory/src/llamafactory/launcher.py', 'saves/DeepSeek-R1-1.5B-Distill/lora/train_2025-07-03-16-29-46/training_args.yaml']' returned non-zero exit status 1.

root@autodl-container-9d8d46936f-63e215ba:~/autodl-tmp/Qwen/Qwen2.5-VL# python test.py You are using a model of type qwen2_5_vl to instantiate a model of type qwen2_vl. This is not supported for all configurations of models and can yield errors. Loading checkpoint shards: 0%| | 0/5 [00:00<?, ?it/s] Traceback (most recent call last): File "/root/autodl-tmp/Qwen/Qwen2.5-VL/test.py", line 5, in <module> model = Qwen2VLForConditionalGeneration.from_pretrained( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/lib/python3.12/site-packages/transformers/modeling_utils.py", line 300, in _wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/lib/python3.12/site-packages/transformers/modeling_utils.py", line 4567, in from_pretrained ) = cls._load_pretrained_model( ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/lib/python3.12/site-packages/transformers/modeling_utils.py", line 5020, in _load_pretrained_model disk_offload_index, cpu_offload_index = _load_state_dict_into_meta_model( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/root/miniconda3/lib/python3.12/site-packages/transformers/modeling_utils.py", line 833, in _load_state_dict_into_meta_model _load_parameter_into_model(model, param_name, param.to(param_device)) File "/root/miniconda3/lib/python3.12/site-packages/transformers/modeling_utils.py", line 721, in _load_parameter_into_model module.load_state_dict({param_type: tensor}, strict=False, assign=True) File "/root/miniconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 2189, in load_state_dict raise RuntimeError('Error(s) in loading s

[INFO|tokenization_utils_base.py:2058] 2025-07-08 19:31:37,761 >> loading file vocab.json [INFO|tokenization_utils_base.py:2058] 2025-07-08 19:31:37,762 >> loading file merges.txt [INFO|tokenization_utils_base.py:2058] 2025-07-08 19:31:37,762 >> loading file tokenizer.json [INFO|tokenization_utils_base.py:2058] 2025-07-08 19:31:37,762 >> loading file added_tokens.json [INFO|tokenization_utils_base.py:2058] 2025-07-08 19:31:37,762 >> loading file special_tokens_map.json [INFO|tokenization_utils_base.py:2058] 2025-07-08 19:31:37,762 >> loading file tokenizer_config.json [INFO|tokenization_utils_base.py:2058] 2025-07-08 19:31:37,762 >> loading file chat_template.jinja [INFO|tokenization_utils_base.py:2323] 2025-07-08 19:31:38,047 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. [INFO|configuration_utils.py:691] 2025-07-08 19:31:38,051 >> loading configuration file D:\llamafactory\LLaMA-Factory\Qwen2.5-0.5B-Instruct\config.json [INFO|configuration_utils.py:765] 2025-07-08 19:31:38,054 >> Model config Qwen2Config { "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 896, "initializer_range": 0.02, "intermediate_size": 4864, "max_position_embeddings": 32768, "max_window_layers": 21, "model_type": "qwen2", "num_attention_heads": 14, "num_hidden_layers": 24, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": 32768, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.51.0", "use_cache": true, "use_sliding_window": false, "vocab_size": 151936 } [INFO|tokenization_utils_base.py:2058] 2025-07-08 19:31:38,060 >> loading file vocab.json [INFO|tokenization_utils_base.py:2058] 2025-07-08 19:31:38,060 >> loading file merges.txt [INFO|tokenization_utils_base.py:2058] 2025-07-08 19:31:38,060 >> loading file tokenizer.json [INFO|tokenization_utils_base.py:2058] 2025-07-08 19:31:38,060 >> loading file added_tokens.json [INFO|tokenization_utils_base.py:2058] 2025-07-08 19:31:38,060 >> loading file special_tokens_map.json [INFO|tokenization_utils_base.py:2058] 2025-07-08 19:31:38,060 >> loading file tokenizer_config.json [INFO|tokenization_utils_base.py:2058] 2025-07-08 19:31:38,060 >> loading file chat_template.jinja [INFO|tokenization_utils_base.py:2323] 2025-07-08 19:31:38,343 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. Setting num_proc from 16 back to 1 for the train split to disable multiprocessing as it only contains one shard. Generating train split: 0 examples [00:00, ? examples/s] Generating train split: 513 examples [00:00, 4879.25 examples/s] Generating train split: 513 examples [00:00, 4852.62 examples/s] Converting format of dataset (num_proc=16): 0%| | 0/513 [00:00<?, ? examples/s] Converting format of dataset (num_proc=16): 0%| | 0/513 [00:25<?, ? examples/s] Converting format of dataset (num_proc=16): 0%| | 0/513 [00:26<?, ? examples/s] Converting format of dataset (num_proc=16): 0%| | 0/513 [00:26<?, ? examples/s] Converting format of dataset (num_proc=16): 0%| | 0/513 [00:26<?, ? examples/s] Converting format of dataset (num_proc=16): 0%| | 0/513 [00:27<?, ? examples/s] Converting format of dataset (num_proc=16): 0%| | 0/513 [00:27<?, ? examples/s] Converting format of dataset (num_proc=16): 0%| | 0/513 [00:27<?, ? examples/s] Converting format of dataset (num_proc=16): 0%| | 0/513 [00:27<?, ? examples/s] multiprocess.pool.RemoteTraceback: """ Traceback (most recent call last): File "C:\Users\李俊聪\AppData\Roaming\Python\Python313\site-packages\multiprocess\pool.py", line 125, in worker result = (True, func(*args, **kwds)) ~~~~^^^^^^^^^^^^^^^ File "C:\Users\李俊聪\AppData\Roaming\Python\Python313\site-packages\datasets\utils\py_utils.py", line 688, in _write_generator_to_queue for i, result in enumerate(func(**kwargs)): ~~~~~~~~~^^^^^^^^^^^^^^^^ File "C:\Users\李俊聪\AppData\Roaming\Python\Python313\site-packages\datasets\arrow_dataset.py", line 3501, in _map_single for i, example in iter_outputs(shard_iterable): ~~~~~~~~~~~~^^^^^^^^^^^^^^^^ File "C:\Users\李俊聪\AppData\Roaming\Python\Python313\site-packages\datasets\arrow_dataset.py", line 3475, in iter_outputs yield i, apply_function(example, i, offset=offset) ~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\李俊聪\AppData\Roaming\Python\Python313\site-packages\datasets\arrow_dataset.py", line 3398, in apply_function processed_inputs = function(*fn_args, *additional_args, **fn_kwargs) File "D:\llamafactory\LLaMA-Factory\src\llamafactory\data\converter.py", line 94, in __call__ if self.dataset_attr.prompt and example[self.dataset_attr.prompt]: ~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\李俊聪\AppData\Roaming\Python\Python313\site-packages\datasets\formatting\formatting.py", line 278, in __getitem__ value = self.data[key] ~~~~~~~~~^^^^^ KeyError: 'instruction' """ The above exception was the direct cause of the following exception: Traceback (most recent call last): File "<frozen runpy>", line 198, in _run_module_as_main File "<frozen runpy>", line 88, in _run_code File "C:\Users\李俊聪\AppData\Roaming\Python\Python313\Scripts\llamafactory-cli.exe\__main__.py", line 7, in <module> sys.exit(main()) ~~~~^^ File "D:\llamafactory\LLaMA-Factory\src\llamafactory\cli.py", line 151, in main COMMAND_MAP[command]() ~~~~~~~~~~~~~~~~~~~~^^ File "D:\llamafactory\LLaMA-Factory\src\llamafactory\train\tuner.py", line 110, in run_exp _training_function(config={"args": args, "callbacks": callbacks}) ~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\llamafactory\LLaMA-Factory\src\llamafactory\train\tuner.py", line 72, in _training_function run_sft(model_args, data_args, training_args, finetuning_args, generating_args, callbacks) ~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\llamafactory\LLaMA-Factory\src\llamafactory\train\sft\workflow.py", line 51, in run_sft dataset_module = get_dataset(template, model_args, data_args, training_args, stage="sft", **tokenizer_module) File "D:\llamafactory\LLaMA-Factory\src\llamafactory\data\loader.py", line 304, in get_dataset dataset = _get_merged_dataset(data_args.dataset, model_args, data_args, training_args, stage) File "D:\llamafactory\LLaMA-Factory\src\llamafactory\data\loader.py", line 182, in _get_merged_dataset datasets[dataset_name] = _load_single_dataset(dataset_attr, model_args, data_args, training_args) ~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\llamafactory\LLaMA-Factory\src\llamafactory\data\loader.py", line 162, in _load_single_dataset return align_dataset(dataset, dataset_attr, data_args, training_args) File "D:\llamafactory\LLaMA-Factory\src\llamafactory\data\converter.py", line 279, in align_dataset return dataset.map( ~~~~~~~~~~~^ dataset_converter, ^^^^^^^^^^^^^^^^^^ ...<2 lines>... **kwargs, ^^^^^^^^^ ) ^ File "C:\Users\李俊聪\AppData\Roaming\Python\Python313\site-packages\datasets\arrow_dataset.py", line 557, in wrapper out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs) ~~~~^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\李俊聪\AppData\Roaming\Python\Python313\site-packages\datasets\arrow_dataset.py", line 3171, in map for rank, done, content in iflatmap_unordered( ~~~~~~~~~~~~~~~~~~^ pool, Dataset._map_single, kwargs_iterable=kwargs_per_job ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ): ^ File "C:\Users\李俊聪\AppData\Roaming\Python\Python313\site-packages\datasets\utils\py_utils.py", line 728, in iflatmap_unordered [async_result.get(timeout=0.05) for async_result in async_results] ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^ File "C:\Users\李俊聪\AppData\Roaming\Python\Python313\site-packages\multiprocess\pool.py", line 774, in get raise self._value KeyError: 'instruction'怎么解决

2025-03-19 10:18:51.988420: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: INVALID_ARGUMENT: Incompatible shapes: [16,4,1937,1937] vs. [16,16,1937,1937] [[{{function_node __inference_one_step_on_data_7270}}{{node gradient_tape/functional_1_1/multi_head_attention_1/softmax_1/add/BroadcastGradientArgs}}]] Traceback (most recent call last): File "c:\Users\86158\Desktop\3\5.LSTM.py", line 162, in <module> history = model.fit( ^^^^^^^^^^ File "C:\Users\86158\AppData\Local\Programs\Python\Python312\Lib\site-packages\keras\src\utils\traceback_utils.py", line 123, in error_handler raise e.with_traceback(filtered_tb) from None File "C:\Users\86158\AppData\Local\Programs\Python\Python312\Lib\site-packages\tensorflow\python\eager\execute.py", line 53, in quick_execute tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name, ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ tensorflow.python.framework.errors_impl.InvalidArgumentError: Graph execution error: Detected at node gradient_tape/functional_1_1/multi_head_attention_1/softmax_1/add/BroadcastGradientArgs defined at (most recent call last): File "c:\Users\86158\Desktop\3\5.LSTM.py", line 162, in <module> File "C:\Users\86158\AppData\Local\Programs\Python\Python312\Lib\site-packages\keras\src\utils\traceback_utils.py", line 118, in error_handler File "C:\Users\86158\AppData\Local\Programs\Python\Python312\Lib\site-packages\keras\src\backend\tensorflow\trainer.py", line 323, in fit File "C:\Users\86158\AppData\Local\Programs\Python\Python312\Lib\site-packages\keras\src\backend\tensorflow\trainer.py", line 117, in one_step_on_iterator File "C:\Users\86158\AppData\Local\Programs\Python\Python312\Lib\site-packages\keras\src\backend\tensorflow\trainer.py", line 105, in one_step_on_data File "C:\Users\86158\AppData\Local\Programs\Python\Python312\Lib\site-packages\keras\

大家在看

recommend-type

C语言流程图生成工具

AutoFlowChart 自动生成流程图 AutoFlowchart 是一个极佳的根据源码生成流程图的工具 它生成的流程图支持展开 合拢 并且可以预定义流程图块的大小和间隔 移动和缩放流程图也很方便 你还可以把它导出到WORD文档或BMP文件 它可以帮助程序员更好地理解程序 制作文档和可视化代码 支持C C++ VC++ Visual C++ NET Delphi Object Pascal 主要功能 根据源程序生成流程图 导出流程图到WORD文档中 展开 合拢流程图 自动生成一个 TreeView显示所有函数 过程 同步显示对应块的源程序和流程图 自定义流程图的配色方案 自定义流程图的大小和间距 根据格式自动排列程序 自由缩小 放大 移动流程图 显示程序行号 支持清除当前流程图 导出流程图到 bmp文件 发展前瞻 ① 支持各种语言 已经完成Pascal C 待完成:Java FoxPro Basic Fortan等; ② 支持反向操作 可以动态修改流程图 并可根据流程图生成相应的语言代码; ③ 结合Delphi专家 嵌入IDE直接运行 已经完成详见主页 操作说明 ① 打开一个或多个文件; ② 双击一个If For While Case Repeat Try begin的起始行 你就可以看到流程图; ③ 双击流程图中相应的框 可以同步显示程序块位置;">AutoFlowChart 自动生成流程图 AutoFlowchart 是一个极佳的根据源码生成流程图的工具 它生成的流程图支持展开 合拢 并且可以预定义流程图块的大小和间隔 移动和缩放流程图也很方便 你还可以把它导出到WORD文档或BMP文件 [更多]
recommend-type

GPRS网络信令实例详解

抓取了GPRS各个接口信令,很详细的各类问题抓包,值得喜欢分析的人下载做为原材料
recommend-type

The GNU Toolchain for ARM targets HOWTO.pdf

英文原版的介绍怎样制作交叉编译工具的资料
recommend-type

高频双调谐谐振放大电路设计3MHz+电压200倍放大.zip

高频双调谐谐振放大电路设计3MHz+电压200倍放大.zip
recommend-type

中国地级市地图shp

中国地级市地图shp文件,希望对大家科研有帮助。

最新推荐

recommend-type

Twitter平台完整数据压缩包文件下载

资源下载链接为: https://pan.quark.cn/s/22ca96b7bd39 小米手机安装 Twitter 时若出现闪退,多与缺失 OBB 扩展文件有关。Google Play 为突破 APK 体积上限,允许把游戏或大型应用的高清资源打包成 main.<包名>.obb,存于 /Android/obb/ 目录。小米系统因权限或优化策略,可能无法自动放置该文件,导致 Twitter 启动即崩溃。 解决思路: 改用整合 APK 与 OBB 的 XAPK 包,借助 XAPK 安装器一键解压到正确路径; 手动把 obb 文件移至 /Android/obb/com.twitter.android/,确认应用有读写存储权限; 若仍失败,关闭 MIUI 优化、检查剩余空间或更新系统与客户端。 下载 XAPK 时务必选择可信来源,避免恶意软件。
recommend-type

Web2.0新特征图解解析

Web2.0是互联网发展的一个阶段,相对于早期的Web1.0时代,Web2.0具有以下显著特征和知识点: ### Web2.0的定义与特点 1. **用户参与内容生产**: - Web2.0的一个核心特征是用户不再是被动接收信息的消费者,而是成为了内容的生产者。这标志着“读写网络”的开始,用户可以在网络上发布信息、评论、博客、视频等内容。 2. **信息个性化定制**: - Web2.0时代,用户可以根据自己的喜好对信息进行个性化定制,例如通过RSS阅读器订阅感兴趣的新闻源,或者通过社交网络筛选自己感兴趣的话题和内容。 3. **网页技术的革新**: - 随着技术的发展,如Ajax、XML、JSON等技术的出现和应用,使得网页可以更加动态地与用户交互,无需重新加载整个页面即可更新数据,提高了用户体验。 4. **长尾效应**: - 在Web2.0时代,即使是小型或专业化的内容提供者也有机会通过互联网获得关注,这体现了长尾理论,即在网络环境下,非主流的小众产品也有机会与主流产品并存。 5. **社交网络的兴起**: - Web2.0推动了社交网络的发展,如Facebook、Twitter、微博等平台兴起,促进了信息的快速传播和人际交流方式的变革。 6. **开放性和互操作性**: - Web2.0时代倡导开放API(应用程序编程接口),允许不同的网络服务和应用间能够相互通信和共享数据,提高了网络的互操作性。 ### Web2.0的关键技术和应用 1. **博客(Blog)**: - 博客是Web2.0的代表之一,它支持用户以日记形式定期更新内容,并允许其他用户进行评论。 2. **维基(Wiki)**: - 维基是另一种形式的集体协作项目,如维基百科,任何用户都可以编辑网页内容,共同构建一个百科全书。 3. **社交网络服务(Social Networking Services)**: - 社交网络服务如Facebook、Twitter、LinkedIn等,促进了个人和组织之间的社交关系构建和信息分享。 4. **内容聚合器(RSS feeds)**: - RSS技术让用户可以通过阅读器软件快速浏览多个网站更新的内容摘要。 5. **标签(Tags)**: - 用户可以为自己的内容添加标签,便于其他用户搜索和组织信息。 6. **视频分享(Video Sharing)**: - 视频分享网站如YouTube,用户可以上传、分享和评论视频内容。 ### Web2.0与网络营销 1. **内容营销**: - Web2.0为内容营销提供了良好的平台,企业可以通过撰写博客文章、发布视频等内容吸引和维护用户。 2. **社交媒体营销**: - 社交网络的广泛使用,使得企业可以通过社交媒体进行品牌传播、产品推广和客户服务。 3. **口碑营销**: - 用户生成内容、评论和分享在Web2.0时代更易扩散,为口碑营销提供了土壤。 4. **搜索引擎优化(SEO)**: - 随着内容的多样化和个性化,SEO策略也必须适应Web2.0特点,注重社交信号和用户体验。 ### 总结 Web2.0是对互联网发展的一次深刻变革,它不仅仅是一个技术变革,更是人们使用互联网的习惯和方式的变革。Web2.0的时代特征与Web1.0相比,更加注重用户体验、社交互动和信息的个性化定制。这些变化为网络营销提供了新的思路和平台,也对企业的市场策略提出了新的要求。通过理解Web2.0的特点和应用,企业可以更好地适应互联网的发展趋势,实现与用户的深度互动和品牌的有效传播。
recommend-type

【C++编程新手必看】:一步步带你制作出风靡全球的“别踩白块儿”游戏

# 摘要 本文全面介绍C++编程在游戏开发中的应用,涵盖了从基础概念到具体实现的多个方面。首先,文章提供了游戏开发环境的搭建指南,包括编译器配置和开发工具的选择。随后,重点介绍了游戏主循环和基本框架的构建,强调了事件处理和渲染技术。在游戏逻辑和交互设计方面,本文阐述了界面布局、事件响应和游戏状态管理的核心实现。为了提升游戏体验,本文还探讨了添加音效和背景音乐以及开发高级游戏特性的方法。最后,文章介绍了性能优化和跨平台发布的过程,包括游戏的打包和针对不同平台的发布策略。本文旨在为C++游戏开发者提供一个实用的开发指南,帮助他们从零开始构建出性能优化、跨平台兼容的游戏。 # 关键字 C++编程;
recommend-type

使用scikit-learn训练模型来预测鸢尾花种类

<think>我们使用scikit-learn库来训练一个分类模型预测鸢尾花种类。鸢尾花数据集是scikit-learn内置的经典数据集,包含三种鸢尾花的四个特征(花萼长度、花萼宽度、花瓣长度、花瓣宽度)和对应的类别标签。步骤:1.导入必要的库和数据集2.数据探索(可选,但建议了解数据)3.数据预处理(如划分训练集和测试集、标准化等)4.选择模型(例如KNN、随机森林等)5.训练模型6.模型评估7.使用模型进行预测下面以KNN(K近邻)算法为例,展示完整流程。</think>### 使用 scikit-learn 训练鸢尾花分类模型 以下是基于 scikit-learn 训练鸢尾花分类模型的
recommend-type

WWF工作流设计器C#源码解析及演示

### WWF工作流设计器控件C#源码知识点 #### 1. WWF(Windows Workflow Foundation)概述 WWF是微软公司推出的一个工作流框架,作为.NET Framework的一部分。它提供了一套丰富的API,用于设计、执行和管理工作流。工作流可以用于各种应用程序,包括Web应用、服务和桌面应用,使得开发者能够将复杂的业务逻辑以工作流的形式表现出来,简化业务流程自动化和管理。 #### 2. 工作流设计器控件(Workflow Designer Control) 工作流设计器控件是WWF中的一个组件,主要用于提供可视化设计工作流的能力。它允许用户通过拖放的方式在界面上添加、配置和连接工作流活动,从而构建出复杂的工作流应用。控件的使用大大降低了工作流设计的难度,并使得设计工作流变得直观和用户友好。 #### 3. C#源码分析 在提供的文件描述中提到了两个工程项目,它们均使用C#编写。下面分别对这两个工程进行介绍: - **WorkflowDesignerControl** - 该工程是工作流设计器控件的核心实现。它封装了设计工作流所需的用户界面和逻辑代码。开发者可以在自己的应用程序中嵌入这个控件,为最终用户提供一个设计工作流的界面。 - 重点分析:控件如何加载和显示不同的工作流活动、控件如何响应用户的交互、控件状态的保存和加载机制等。 - **WorkflowDesignerExample** - 这个工程是演示如何使用WorkflowDesignerControl的示例项目。它不仅展示了如何在用户界面中嵌入工作流设计器控件,还展示了如何处理用户的交互事件,比如如何在设计完工作流后进行保存、加载或执行等。 - 重点分析:实例程序如何响应工作流设计师的用户操作、示例程序中可能包含的事件处理逻辑、以及工作流的实例化和运行等。 #### 4. 使用Visual Studio 2008编译 文件描述中提到使用Visual Studio 2008进行编译通过。Visual Studio 2008是微软在2008年发布的集成开发环境,它支持.NET Framework 3.5,而WWF正是作为.NET 3.5的一部分。开发者需要使用Visual Studio 2008(或更新版本)来加载和编译这些代码,确保所有必要的项目引用、依赖和.NET 3.5的特性均得到支持。 #### 5. 关键技术点 - **工作流活动(Workflow Activities)**:WWF中的工作流由一系列的活动组成,每个活动代表了一个可以执行的工作单元。在工作流设计器控件中,需要能够显示和操作这些活动。 - **活动编辑(Activity Editing)**:能够编辑活动的属性是工作流设计器控件的重要功能,这对于构建复杂的工作流逻辑至关重要。 - **状态管理(State Management)**:工作流设计过程中可能涉及保存和加载状态,例如保存当前的工作流设计、加载已保存的工作流设计等。 - **事件处理(Event Handling)**:处理用户交互事件,例如拖放活动到设计面板、双击活动编辑属性等。 #### 6. 文件名称列表解释 - **WorkflowDesignerControl.sln**:解决方案文件,包含了WorkflowDesignerControl和WorkflowDesignerExample两个项目。 - **WorkflowDesignerControl.suo**:Visual Studio解决方案用户选项文件,该文件包含了开发者特有的个性化设置,比如窗口布局、断点位置等。 - **Thumbs.db**:缩略图缓存文件,由Windows自动生成,用于存储文件夹中的图片缩略图,与WWF工作流设计器控件功能无关。 - **WorkflowDesignerExample**:可能是一个文件夹,包含了示例工程相关的所有文件,或者是示例工程的可执行文件。 - **EULA.txt**:最终用户许可协议文本文件,通常说明了软件的版权和使用许可条件。 综上所述,该文件集包含了WWF工作流设计器控件的完整C#源码以及相应的Visual Studio项目文件,开发者可以利用这些资源深入理解WWF工作流设计器控件的工作机制,并将其应用于实际的项目开发中,实现工作流的设计和管理功能。
recommend-type

CAD数据在ANSA中:完美修复几何数据的策略与方法

# 摘要 CAD数据的准确性和几何完整性对于产品设计和工程分析至关重要。本文首先强调了CAD数据和几何修复的重要性,随后介绍了ANSA软件在处理CAD数据中的角色。通过详细的分析,本文探讨了几何数据的常见问题,以及有效的手动和自动修复技术。文中还提供了几何修复在实际应用中的案例分析,并讨论了行业未来对几何修复技术的需求和新兴技术趋势。文章旨在为CAD数据几何修复提供全面的理论知识、诊断方法和修复策略,并
recommend-type

编写verilog代码实现以上的规格化功能

<think>我们有一个16位的二进制数,其格式如下:-a15:尾数符号位(1位)-a14-a5:尾数数值位(10位)-a4:指数符号位(1位)-a3-a0:指数数值位(4位)规格化的目标:确保尾数数值位的最高位a14为1(即尾数的绝对值在[0.5,1)范围内)。步骤:1.提取输入信号的各个部分:尾数符号位、尾数数值位、指数符号位、指数数值位。2.将尾数数值位(10位)视为无符号整数M(范围0到1023),我们需要通过左移操作使得M的最高位为1(即M>=512)。同时记录左移的位数(shift_count)。3.调整指数:新的指数=原指数-shift_count(因为尾数左移相当于乘以2^sh
recommend-type

探索ARM9 2410开发板与wince5.0系统的高级实验

标题中的“周立功ARM (magicarm2410) 高级实验”指明了文档内容涉及周立功品牌下的ARM9 2410开发板的高级使用实验。ARM9 2410是基于ARM920T内核的处理器,广泛应用于嵌入式系统开发。周立功是一家在电子与嵌入式系统领域内具有影响力的公司,提供嵌入式教学和开发解决方案。MagicARM2410是该公司的某型号开发板,可能专为教学和实验设计,携带了特定的实验内容,例如本例中的“eva例程”。 描述提供了额外的背景信息,说明周立功ARM9 2410开发板上预装有Windows CE 5.0操作系统,以及该开发板附带的EVA例程。EVA可能是用于实验教学的示例程序或演示程序。文档中还提到,虽然书店出售的《周立功 ARM9开发实践》书籍中没有包含EVA的源码,但该源码实际上是随开发板提供的。这意味着,EVA例程的源码并不在书籍中公开,而是需要直接从开发板上获取。这对于那些希望深入研究和修改EVA例程的学生和开发者来说十分重要。 标签中的“magicarm2410”和“周立功ARM”是对文档和开发板的分类标识。这些标签有助于在文档管理系统或资料库中对相关文件进行整理和检索。 至于“压缩包子文件的文件名称列表:新建文件夹”,这表明相关文件已经被打包压缩,但具体的文件内容和名称没有在描述中列出。我们仅知道压缩包内至少存在一个“新建文件夹”,这可能意味着用户需要进一步操作来查看或解压出文件夹中的内容。 综合以上信息,知识点主要包括: 1. ARM9 2410开发板:一款基于ARM920T内核的处理器的嵌入式开发板,适用于教学和项目实验。 2. Windows CE 5.0系统:这是微软推出的专为嵌入式应用设计的操作系统,提供了一个可定制、可伸缩的、实时的操作环境。 3. EVA例程:一个嵌入式系统开发的教学或实验示例程序。它可能被设计用于演示特定功能或技术,如显示、控制或通信。 4. 开发实践书籍与源码提供:《周立功 ARM9开发实践》一书可能详细介绍了ARM9 2410开发板的使用方法,但书中的内容不包含EVA例程的源码,源码需要通过其他途径获得。 5. 文件打包压缩:文档可能以压缩包的形式存在,包含了需要的内容,但具体内容未知,需要解压缩之后才能查看。 了解这些知识点后,对于从事嵌入式系统开发的工程师或者学生来说,可以更好地利用周立功 ARM9 2410开发板进行学习和实验,尤其是可以进行更深入的研究和实验设计,通过EVA例程的源码来理解嵌入式系统的运行机制和程序结构。同时,也能够使用Windows CE 5.0系统环境来开发相应的应用程序。
recommend-type

【ANSA网格生成手册】:创建高效高质量网格的6个技巧

# 摘要 ANSA软件作为一款强大的前处理工具,在工程仿真领域扮演着重要角色。本文首先概述了ANSA软件的基本功能以及网格生成技术的基础知识。接着深入探讨了不同网格类型的选择及其优缺点,同时强调了网格密度与质量控制的重要性。文中详细介绍了高级网格生成技巧,包括自适应网格技术和多重网格以及混合网格技术的应用。此外,本文还提供了网格生成在实际应用中的前处理
recommend-type

能否简单一点

<think>我们简化问题:统计从列表第一个字典开始,连续多少个字典的money字段为正数。注意:我们只关心从第一个开始的连续正数,一旦遇到非正数(包括0和负数)或者缺失money字段,就停止计数。简单实现思路:1.遍历列表中的每个字典(从第一个开始)2.对于每个字典,检查是否有'money'键,且其值大于0。3.如果满足条件,计数器加1;否则立即停止遍历并返回当前计数。代码实现:</think>### 简化版:统计连续正数 `money` 字段 #### 解决方案代码 ```python def count_positive_money(dict_list): count = 0