I'm trying to reproduce Qwen1.5-1.8B-Chat NPU+CPU inference on a Xiaomi 14 phone. My environment is as follows:
- Ubuntu: 22.04.5
- QNN SDK: 2.41.0.251128
- Hexagon NPU Runtime: 6.4.0.1
First, I used the example from the main branch:
🔗 examples/qwen_npu/main.cpp
However, the program was killed by the system. I added some debug logs to the code for troubleshooting, as shown below:


Then, I tried the example from the v1-backup branch:
🔗 examples/demo_qwen_npu.cpp
But I encountered the following issue:


Is it an issue with with the above QNN/Hexagon versions? Or could there be other possible causes?
Thanks for your help.
I'm trying to reproduce Qwen1.5-1.8B-Chat NPU+CPU inference on a Xiaomi 14 phone. My environment is as follows:
First, I used the example from the
mainbranch:🔗 examples/qwen_npu/main.cpp
However, the program was killed by the system. I added some debug logs to the code for troubleshooting, as shown below:


Then, I tried the example from the


v1-backupbranch:🔗 examples/demo_qwen_npu.cpp
But I encountered the following issue:
Is it an issue with with the above QNN/Hexagon versions? Or could there be other possible causes?
Thanks for your help.