PaddlePaddle
libascendcl.so: 运行华为华为昇腾推理报错
参考： https://github.com/PaddlePaddle/FastDeploy/tree/develop/examples/vision/detection/yolov5/cpp 运行命令： ./infer_paddle_demo yolov5s_infer 000000014439.jpg 4 报错关键信息： [I 4/12 22:16:54.127 ...le-Lite/lite/core/optimizer/optimizer.cc:119 ApplyPasses] == Finished running: argument_type_display_pass [I 4/12 22:16:54.127 ...le-Lite/lite/core/optimizer/optimizer.cc:99 ApplyPasses] == Running pass: variable_place_inference_pass [I 4/12 22:16:54.132 ...le-Lite/lite/core/optimizer/optimizer.cc:119 ApplyPasses] == Finished running: variable_place_inference_pass [I 4/12 22:16:54.132 ...le-Lite/lite/core/optimizer/optimizer.cc:99 ApplyPasses] == Running pass: control_flow_op_shared_inputs_and_outputs_place_sync_pass [I 4/12 22:16:54.132 ...le-Lite/lite/core/optimizer/optimizer.cc:107 ApplyPasses] - Skip control_flow_op_shared_inputs_and_outputs_place_sync_pass because the target or kernel does not match. [I 4/12 22:16:54.132 ...le-Lite/lite/core/optimizer/optimizer.cc:99 ApplyPasses] == Running pass: argument_type_display_pass [I 4/12 22:16:54.132 ...le-Lite/lite/core/optimizer/optimizer.cc:119 ApplyPasses] == Finished running: argument_type_display_pass [I 4/12 22:16:54.132 ...le-Lite/lite/core/optimizer/optimizer.cc:99 ApplyPasses] == Running pass: runtime_context_assign_pass [I 4/12 22:16:54.132 ...le-Lite/lite/core/optimizer/optimizer.cc:119 ApplyPasses] == Finished running: runtime_context_assign_pass [I 4/12 22:16:54.132 ...le-Lite/lite/core/optimizer/optimizer.cc:99 ApplyPasses] == Running pass: argument_type_display_pass [I 4/12 22:16:54.133 ...le-Lite/lite/core/optimizer/optimizer.cc:119 ApplyPasses] == Finished running: argument_type_display_pass [I 4/12 22:16:54.133 ...le-Lite/lite/core/optimizer/optimizer.cc:99 ApplyPasses] == Running pass: lite_inplace_fuse_pass [I 4/12 22:16:54.133 ...le-Lite/lite/core/optimizer/optimizer.cc:119 ApplyPasses] == Finished running: lite_inplace_fuse_pass [I 4/12 22:16:54.133 ...le-Lite/lite/core/optimizer/optimizer.cc:99 ApplyPasses] == Running pass: memory_optimize_pass [I 4/12 22:16:54.133 ...le-Lite/lite/core/optimizer/optimizer.cc:107 ApplyPasses] - Skip memory_optimize_pass because the target or kernel does not match. [I 4/12 22:16:54.133 ...le-Lite/lite/core/optimizer/optimizer.cc:99 ApplyPasses] == Running pass: xpu_memory_optimize_pass [I 4/12 22:16:54.133 ...le-Lite/lite/core/optimizer/optimizer.cc:107 ApplyPasses] - Skip xpu_memory_optimize_pass because the target or kernel does not match. [I 4/12 22:16:54.137 ...re/optimizer/mir/generate_program_pass.h:41 GenProgram] insts.size: 1 [INFO] fastdeploy/runtime/runtime.cc(321)::CreateLiteBackend Runtime initialized with Backend::PDLITE in Device::ASCEND. [F 4/12 22:16:54.161 ...nadapter/nnadapter/src/runtime/device.cc:529 Find] Failed to load the nnadapter device HAL library for 'huawei_ascend_npu' from libhuawei_ascend_npu.so, libascendcl.so: cannot open shared object file: No such file or directory terminate called after throwing an instance of 'nnadapter::logging::Exception' what(): NNAdapter C++ Exception: [F 4/12 22:16:54.161 ...nadapter/nnadapter/src/runtime/device.cc:529 Find] Failed to load the nnadapter device HAL library for 'huawei_ascend_npu' from libhuawei_ascend_npu.so, libascendcl.so: cannot open shared object file: No such file or directory
Aborted (core dumped)
上面的库在哪里可以找到，如何解决？
华为昇腾的部署可以参考这个文档哈：
- https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/build_and_install/huawei_ascend.md
@DefTruth 我就是对着这个编译的，我的硬件Atlas 300I没有pro应该也没关系吧，我按这个步骤编译成功了，到了yolov5编译cpp的时候也没问题，就是在运行的时候报了这个库找不到，我在系统里面找了也没找到这个库，这个怎么解决的
看下是不是没有设置环境变量，可以参考文档：
- https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/faq/use_sdk_on_ascend.md
根据文档配置后遇到下面问题，这是toolkit版本问题还是驱动问题？
[I 4/14 7:53:44.944 ...le-Lite/lite/core/optimizer/optimizer.cc:99 ApplyPasses] == Running pass: xpu_memory_optimize_pass [I 4/14 7:53:44.944 ...le-Lite/lite/core/optimizer/optimizer.cc:107 ApplyPasses] - Skip xpu_memory_optimize_pass because the target or kernel does not match. [I 4/14 7:53:44.948 ...re/optimizer/mir/generate_program_pass.h:41 GenProgram] insts.size: 1 [INFO] fastdeploy/runtime/runtime.cc(321)::CreateLiteBackend Runtime initialized with Backend::PDLITE in Device::ASCEND. [F 4/14 7:53:44.971 ...nadapter/nnadapter/src/runtime/device.cc:529 Find] Failed to load the nnadapter device HAL library for 'huawei_ascend_npu' from libhuawei_ascend_npu.so, libmsprofiler.so: cannot open shared object file: No such file or directory terminate called after throwing an instance of 'nnadapter::logging::Exception' what(): NNAdapter C++ Exception: [F 4/14 7:53:44.971 ...nadapter/nnadapter/src/runtime/device.cc:529 Find] Failed to load the nnadapter device HAL library for 'huawei_ascend_npu' from libhuawei_ascend_npu.so, libmsprofiler.so: cannot open shared object file: No such file or directory
Aborted (core dumped)
@DefTruth
为什么我用的昆仑芯用XPU却是可以抛出结果的（问题来源），我的硬件环境是atlas 300I 加速卡的NPU啊?
运行./infer_paddle_model_demo yolov7_infer 000000014439.jpg 3 就出上面错误
