You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
When we try to run a loop to initializing, model inferring and finalizing on QNN 2.25.0 engine (with onnxruntime 1.18.1) every 3~5 sec, and there is an error coming out in initial stage.
It will come out an error as below in a few seconds:
[onnxruntime] [] sequential_executor.cc:516 onnxruntime::ExecuteKernel: Non-zero status code returned while running QNN_13825321319279089785_0 node. Name:'QNNExecutionProvider_QNN_13825321319279089785_0_0' Status Message: QNN graph execute error. Error code: 1100
run failed : Non-zero status code returned while running QNN_13825321319279089785_0 node. Name:'QNNExecutionProvider_QNN_13825321319279089785_0_0' Status Message: QNN graph execute error. Error code: 1100
or
[onnxruntime] [] sequential_executor.cc:514 onnxruntime::ExecuteKernel: Non-zero status code returned while running QNN_8567928183500563082_0 node. Name:'QNNExecutionProvider_QNN_8567928183500563082_0_0' Status Message: QNN graph execute error. Error code: 6001
run failed : Non-zero status code returned while running QNN_8567928183500563082_0 node. Name:'QNNExecutionProvider_QNN_8567928183500563082_0_0' Status Message: QNN graph execute error. Error code: 6001
Test case 2
We have passed the loop test.
Just want to confirm that this issue has been fixed in onnxruntime v1.19.0
Urgency
It's a production issue for our customer, will pending the release plan and impact shipping date.
Platform
Windows
OS Version
Windows 11
ONNX Runtime Installation
Released Package
ONNX Runtime Version or Commit ID
1.19.0 and 1.18.1
ONNX Runtime API
C++
Architecture
ARM64
Execution Provider
Other / Unknown
Execution Provider Library Version
QNN 2.25.0 HTP backend
The text was updated successfully, but these errors were encountered:
just wanted to confirm that you are bringing your own version of QNN.
ORT.QNN 1.18.1 (nuget and pypi) packages shipped with QNN 2.22.10
were these tests working on a previous version of ORT.QNN? if so, which version(s) of ORT and QNN?
Describe the issue
When we try to run a loop to initializing, model inferring and finalizing on QNN 2.25.0 engine (with onnxruntime 1.18.1) every 3~5 sec, and there is an error coming out in initial stage.
To reproduce
[Test case 1]
QNN : 2.25
Onnxruntime: 1.18.1
[Test case 2]
QNN : 2.25
Onnxruntime: 1.19.0
referred to onnxruntime-inference-examples/c_cxx/QNN_EP/mobilenetv2_classification at main · microsoft/onnxruntime-inference-examples · GitHub
We only change to do “run_ort_qnn_ep” for 10000 times to simulate particular use case.
It will come out an error as below in a few seconds:
or
We have passed the loop test.
Just want to confirm that this issue has been fixed in onnxruntime v1.19.0
Urgency
It's a production issue for our customer, will pending the release plan and impact shipping date.
Platform
Windows
OS Version
Windows 11
ONNX Runtime Installation
Released Package
ONNX Runtime Version or Commit ID
1.19.0 and 1.18.1
ONNX Runtime API
C++
Architecture
ARM64
Execution Provider
Other / Unknown
Execution Provider Library Version
QNN 2.25.0 HTP backend
The text was updated successfully, but these errors were encountered: