PaddlePaddle / PaddlePaddle/FastDeploy

libascendcl.so: 运行华为华为昇腾推理报错

Open
#1,808 7 comments 0 reactions 2 assignees View on GitHub

@yunyaoXYY is already working on this.

Since Apr 13, 2023.

Dominant language
Python
Stars
3.7k
Forks
756
Avg merge
19h 28m
Merged PRs (30d)
4

Description

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?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.