昇腾 No stack trace in paddle, may be caused by external reasons. #76780
Description
bug描述 Describe the Bug
昇腾910B paddle-custom-npu =3.0.0 paddleocr=3.3.2 paddlepaddle=3.2.2 paddlex=3.3.10 运行PPStructureV3报错：
(pd2) root@autodl-container-9a3c4989ed-36c91baf:~/paddle# python task_1.py
[INFO] 初始化 PP-StructureV3 管线 ...
/root/miniconda3/envs/pd2/lib/python3.9/site-packages/paddle/utils/cpp_extension/extension_utils.py:718: UserWarning: No ccache found. Please be aware that recompiling all source files may be required. You can download and install ccache from: https://github.com/ccache/ccache/blob/master/doc/INSTALL.md
warnings.warn(warning_message)
WARNING: OMP_NUM_THREADS set to 24, not 1. The computation speed will not be optimized if you use data parallel. It will fail if this PaddlePaddle binary is compiled with OpenBlas since OpenBlas does not support multi-threads.
PLEASE USE OMP_NUM_THREADS WISELY.
I1204 20:11:48.821022 246282 init.cc:238] ENV [CUSTOM_DEVICE_ROOT]=/root/miniconda3/envs/pd2/lib/python3.9/site-packages/paddle_custom_device
I1204 20:11:48.821079 246282 init.cc:146] Try loading custom device libs from: [/root/miniconda3/envs/pd2/lib/python3.9/site-packages/paddle_custom_device]
I1204 20:11:49.773571 246282 custom_device_load.cc:51] Succeed in loading custom runtime in lib: /root/miniconda3/envs/pd2/lib/python3.9/site-packages/paddle_custom_device/libpaddle-custom-npu.so
I1204 20:11:49.773648 246282 custom_device_load.cc:58] Skipped lib [/root/miniconda3/envs/pd2/lib/python3.9/site-packages/paddle_custom_device/libpaddle-custom-npu.so]: no custom engine Plugin symbol in this lib.
I1204 20:11:49.773660 246282 custom_kernel.cc:44] No custom kernel info found in loaded lib(s).
I1204 20:11:49.773669 246282 init.cc:158] Finished in LoadCustomDevice with libs_path: [/root/miniconda3/envs/pd2/lib/python3.9/site-packages/paddle_custom_device]
I1204 20:11:49.773690 246282 init.cc:244] CustomDevice: npu, visible devices count: 1
Creating model: ('PP-DocBlockLayout', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: /root/.paddlex/official_models/PP-DocBlockLayout.
Creating model: ('PP-DocLayout_plus-L', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: /root/.paddlex/official_models/PP-DocLayout_plus-L.
Creating model: ('PP-LCNet_x1_0_textline_ori', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: /root/.paddlex/official_models/PP-LCNet_x1_0_textline_ori.
Creating model: ('PP-OCRv5_server_det', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: /root/.paddlex/official_models/PP-OCRv5_server_det.
Creating model: ('PP-OCRv5_server_rec', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: /root/.paddlex/official_models/PP-OCRv5_server_rec.
Creating model: ('PP-LCNet_x1_0_table_cls', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: /root/.paddlex/official_models/PP-LCNet_x1_0_table_cls.
Creating model: ('SLANeXt_wired', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: /root/.paddlex/official_models/SLANeXt_wired.
Creating model: ('SLANet_plus', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: /root/.paddlex/official_models/SLANet_plus.
Creating model: ('RT-DETR-L_wired_table_cell_det', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: /root/.paddlex/official_models/RT-DETR-L_wired_table_cell_det.
Creating model: ('RT-DETR-L_wireless_table_cell_det', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: /root/.paddlex/official_models/RT-DETR-L_wireless_table_cell_det.
Creating model: ('PP-FormulaNet_plus-L', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: /root/.paddlex/official_models/PP-FormulaNet_plus-L.
Creating model: ('PP-Chart2Table', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: /root/.paddlex/official_models/PP-Chart2Table.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Loading configuration file /root/.paddlex/official_models/PP-Chart2Table/config.json
Loading weights file /root/.paddlex/official_models/PP-Chart2Table/model_state.pdparams
Loaded weights file from disk, setting weights to model.
All model checkpoint weights were used when initializing PPChart2TableInference.
All the weights of PPChart2TableInference were initialized from the model checkpoint at /root/.paddlex/official_models/PP-Chart2Table.
If your task is similar to the task the model of the checkpoint was trained on, you can already use PPChart2TableInference for predictions without further training.
Loading configuration file /root/.paddlex/official_models/PP-Chart2Table/generation_config.json
[INFO] 将处理 PDF 数量：8
===== [1/8] 处理文档: 文件.pdf =====
[INFO] 调用 PP-StructureV3 解析 PDF: /root/paddle/data/文件.pdf
Creating model: ('PP-LCNet_x1_0_doc_ori', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: /root/.paddlex/official_models/PP-LCNet_x1_0_doc_ori.
Creating model: ('PP-LCNet_x1_0_textline_ori', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: /root/.paddlex/official_models/PP-LCNet_x1_0_textline_ori.
Creating model: ('PP-OCRv5_server_det', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: /root/.paddlex/official_models/PP-OCRv5_server_det.
Creating model: ('PP-OCRv5_server_rec', None)
Model files already exist. Using cached files. To redownload, please delete the directory manually: /root/.paddlex/official_models/PP-OCRv5_server_rec.
C++ Traceback (most recent call last):
No stack trace in paddle, may be caused by external reasons.
Error Message Summary:
FatalError: Segmentation fault is detected by the operating system.
[TimeInfo: *** Aborted at 1764851009 (unix time) try "date -d @1764851009" if you are using GNU date ***]
[SignalInfo: *** SIGSEGV (@0x3c20a) received by PID 246282 (TID 0xfffd9860f120) from PID 246282 ***]
Segmentation fault (core dumped)
其他补充信息 Additional Supplementary Information
No response