-
Notifications
You must be signed in to change notification settings - Fork 724
Closed
Labels
partner: qualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, QualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm
Description
I export a model with
python export_example.py -m mul -g
and hardcoded to SM8450 model. When trying in runtime, it errors out with the message as following
[ERROR] [Qnn ExecuTorch]: <E> DspTransport.openSession qnn_open failed, 0x80000406
[ERROR] [Qnn ExecuTorch]: <E> IDspTransport: Unable to load lib 0x80000406
[ERROR] [Qnn ExecuTorch]: <E> DspTransport failed,cannot open session, error 0x00000009
[ERROR] [Qnn ExecuTorch]: <E> Unable to load Skel Library. transportStatus: 9
[ERROR] [Qnn ExecuTorch]: <E> Failed to retrieve skel build id: err: 1008
[ERROR] [Qnn ExecuTorch]: <E> Failed to create transport for device, error: 1008
[ERROR] [Qnn ExecuTorch]: <E> Failed to load skel, error: 1008
[ERROR] [Qnn ExecuTorch]: <E> Transport layer setup failed: 1008
[ERROR] [Qnn ExecuTorch]: <E> Failed to parse default platform info: 1008
[ERROR] [Qnn ExecuTorch]: <E> Failed to load default platform info: 1008
[ERROR] [Qnn ExecuTorch]: <E> Failed to parse platform config: 1008
[ERROR] [Qnn ExecuTorch]: Failed to create device_handle for Backend ID 6, error=1008
E 00:00:00.188565 executorch:QnnManager.cpp:154] Fail to configure Qnn device
E 00:00:00.188596 executorch:QnnExecuTorchBackend.cpp:54] Fail to initialize Qnn Manager
E 00:00:00.188605 executorch:method.cpp:106] Init failed for backend QnnBackend: 0x1
F 00:00:00.188620 executorch:qnn_executor_runner.cpp:215] In function main(), assert failed (method.ok()): Loading of method forward failed with status 0x1
Is it only for SM8450?
Metadata
Metadata
Assignees
Labels
partner: qualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, QualcommFor backend delegation, kernels, demo, etc. from the 3rd-party partner, Qualcomm