C++推理中，换一台设备后GPU显存利用率为0，用不起来GPU然后报错

[ainndejj11]

paddle_inference版本是2.2.2 在PaddleOCR项目中，C++推理时，本地两台机器上代码运行正常，使用GPU和tensorrt均正常。但是用另一部机器（也是Paddle支持的显卡），在这上运行时，设备GPU的利用率就为0，GPU用不起来，然后程序就会报错。代码和环境都一致，请问这是什么原因呢？？

报错信息如下： WARNING: Logging before InitGoogleLogging() is written to STDERR I1028 14:30:40.557919 22346 analysis_config.cc:1044] In CollectShapeInfo mode, we will disable optimizations and collect the shape information of all intermediate tensors in the compute graph and calculate the min_shape, max_shape and opt_shape. terminate called after throwing an instance of 'phi::enforce::EnforceNotMet' what():

---

C++ Traceback (most recent call last):

0 paddle_infer::CreatePredictor(paddle::AnalysisConfig const&) 1 paddle_infer::Predictor::Predictor(paddle::AnalysisConfig const&) 2 paddle::AnalysisPredictor::~AnalysisPredictor() 3 paddle::AnalysisPredictor::~AnalysisPredictor() 4 paddle::memory::allocation::AllocatorFacade::Release(phi::Place const&) 5 paddle::memory::allocation::AllocatorFacadePrivate::GetAllocator(phi::Place const&, unsigned long)

---

Error Message Summary:

NotFoundError: No allocator found for the place, Place(undefined:0) [Hint: Expected iter != allocators.end(), but received iter == allocators.end().] (at /paddle/paddle/fluid/memory/allocation/allocator_facade.cc:343)

Aborted

[huangjun12]

paddle.utils.run_check()检查下这台机器能成功执行吗

[ainndejj11]

paddle.utils.run_check()检查下这台机器能成功执行吗

是C++代码的推理流程

[github-actions[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions.