[Question]: PaddleNLP 报错OSError: (External) CUBLAS error(1).

[bella-cc]

请提出你的问题

cuda 11.7；cudnn 8.4.1；python 3.11
paddlepaddle-gpu 2.5.2 post117 （显示成功安装）

paddlenlp 2.5.2
输入代码：
from pprint import pprint
from paddlenlp import Taskflow
schema = ['时间', '选手', '赛事名称']
ie = Taskflow('information_extraction', schema=schema)
pprint(ie("2月8日北京冬奥会自由式滑雪女子大跳台决赛中中国选手谷爱凌以188.25分获得金牌！"))

报错如下：
[2024-06-25 14:38:44,992] [ INFO] - We are using <class 'paddlenlp.transformers.ernie.tokenizer.ErnieTokenizer'> to load 'C:\Users\ADMIN.paddlenlp\taskflow\information_extraction\uie-base'.
Error: C:\home\workspace\Paddle\paddle\phi\kernels\gpu\embedding_kernel.cu:45 Assertion id < N failed. Id should smaller than 40000 but received an id value: 6875154315333164900.
Error: C:\home\workspace\Paddle\paddle\phi\kernels\gpu\embedding_kernel.cu:45 Assertion id < N failed. Id should smaller than 40000 but received an id value: 6875154315333164900.
......
Traceback (most recent call last):
File "D:\pythonproject\pythonProject1\check.py", line 10, in
pprint(ie("2月8日北京冬奥会自由式滑雪女子大跳台决赛中中国选手谷爱凌以188.25分获得金牌！"))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\ADMIN\AppData\Local\Programs\Python\Python311\Lib\site-packages\paddlenlp\taskflow\taskflow.py", line 850, in call
results = self.task_instance(inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\ADMIN\AppData\Local\Programs\Python\Python311\Lib\site-packages\paddlenlp\taskflow\task.py", line 516, in call
outputs = self._run_model(inputs)
^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\ADMIN\AppData\Local\Programs\Python\Python311\Lib\site-packages\paddlenlp\taskflow\information_extraction.py", line 1066, in _run_model
results = self._multi_stage_predict(_inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\ADMIN\AppData\Local\Programs\Python\Python311\Lib\site-packages\paddlenlp\taskflow\information_extraction.py", line 1164, in _multi_stage_predict
result_list = self._single_stage_predict(examples)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\ADMIN\AppData\Local\Programs\Python\Python311\Lib\site-packages\paddlenlp\taskflow\information_extraction.py", line 977, in _single_stage_predict
self.predictor.run()

OSError: (External) CUBLAS error(1).
[Hint: 'CUBLAS_STATUS_NOT_INITIALIZED'. The cuBLAS library was not initialized. This is usually caused by the lack of a prior cublasCreate() call, an error in the CUDA Runtime API called by the cuBLAS routine, or an error in the hardware setup. To correct: call cublasCreate() prior to the function call; and check that the hardware, an appropriate version of the driver, and the cuBLAS library are correctly installed. ] (at ..\paddle\phi\backends\gpu\gpu_resources.cc:214)
[operator < multihead_matmul > error]

Process finished with exit code -1073740791 (0xC0000409)

[zhanghengjiayou]

我也是这个错误，请问你解决了嘛

[qinhuangdaoStation]

同样的问题，请问有解决的吗？

[zhanghengjiayou]

重建虚拟环境，重新安装