使用paddlex3.0.0.b2的时候，在cuda版本为12.2的版本中遇到了问题

[Stefan3Zz]

当我paddlex部署在了cuda12.2的版本上时候，运行模型进行预测，连续调用的时候就会报错
File "/mnt/afs/poc/leadigital_inference_service/services/paddlex_service.py", line 37, in predict for res in output: File "/mnt/afs/miniconda3/envs/paddlex/lib/python3.10/site-packages/paddlex/inference/pipelines/ocr.py", line 69, in predict for det_res in self.text_det_model(input): File "/mnt/afs/miniconda3/envs/paddlex/lib/python3.10/site-packages/paddlex/inference/models/base/basic_predictor.py", line 74, in __call__ yield from super().__call__(input) File "/mnt/afs/miniconda3/envs/paddlex/lib/python3.10/site-packages/paddlex/inference/models/base/base_predictor.py", line 48, in __call__ for res in super().__call__(input): File "/mnt/afs/miniconda3/envs/paddlex/lib/python3.10/site-packages/paddlex/inference/components/base.py", line 63, in __call__ for each_output in output: File "/mnt/afs/miniconda3/envs/paddlex/lib/python3.10/site-packages/paddlex/inference/models/base/basic_predictor.py", line 78, in apply yield from self._generate_res(self.engine(input)) File "/mnt/afs/miniconda3/envs/paddlex/lib/python3.10/site-packages/paddlex/inference/utils/process_hook.py", line 46, in _wrapper for ele in input_: File "/mnt/afs/miniconda3/envs/paddlex/lib/python3.10/site-packages/paddlex/inference/components/base.py", line 290, in __call__ yield from self.__call__(data, i + 1) File "/mnt/afs/miniconda3/envs/paddlex/lib/python3.10/site-packages/paddlex/inference/components/base.py", line 290, in __call__ yield from self.__call__(data, i + 1) File "/mnt/afs/miniconda3/envs/paddlex/lib/python3.10/site-packages/paddlex/inference/components/base.py", line 290, in __call__ yield from self.__call__(data, i + 1) [Previous line repeated 1 more time] File "/mnt/afs/miniconda3/envs/paddlex/lib/python3.10/site-packages/paddlex/inference/components/base.py", line 289, in __call__ for data in data_gen: File "/mnt/afs/miniconda3/envs/paddlex/lib/python3.10/site-packages/paddlex/inference/components/base.py", line 49, in __call__ output = self.apply(**args) File "/mnt/afs/miniconda3/envs/paddlex/lib/python3.10/site-packages/paddlex/inference/components/paddle_predictor/predictor.py", line 219, in apply self.infer.apply() File "/mnt/afs/miniconda3/envs/paddlex/lib/python3.10/site-packages/paddlex/inference/components/paddle_predictor/predictor.py", line 59, in apply self.predictor.run() RuntimeError: std::exception
请问这是目前paddlex和cuda12.2版本不兼容的原因吗

[TingquanGao]

哪个模型呢，是特定的样本才会报错吗？这个问题可以稳定复现么。