-
Notifications
You must be signed in to change notification settings - Fork 2.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Bug]: NPU compile: L0 zeFenceHostSynchronize result: ZE_RESULT_ERROR_UNKNOWN #27099
Comments
@Zctoylm0927 thanks for reaching out, do you observe the same behavior on the latest 2024.4 release or nightly release? If you can please share minimal sample reproducer and IR model. Also provide the NPU driver version you are using. |
Thanks for reply. I have tried 2024.4 release,
Btw, I don't know how to check the npu driver version information. How can I check it? |
@Zctoylm0927 sorry for missing your update, thanks for providing the entire model. It seems the issue you reported has been addressed, as of OpenVINO 2024.5/2024.6 and the latest NPU driver (v1.10.0) the issue does not reproduce. Please have a try in upgrading to the latest OpenVINO release and NPU driver on your end and see if the issue is resolved. If the issue persists perhaps it could be a coding issue in your application, as the benchmark_app executes the model and inference without issue.
|
Closing this as it seems issue has been addressed. Feel free to reopen and ask additional questions related to this topic. |
OpenVINO Version
2024.3
Operating System
Ubuntu 20.04 (LTS)
Device used for inference
NPU
Framework
PyTorch
Model used
torch.nn.MultiheadAttention
Issue description
I have handwritten a Transformer model that includes three parts: self-attention, cross-attention, and MLP. It can run on the NPU, but when I run only the cross-attention part, the following problem occurs.
RuntimeError: Exception from src/inference/src/cpp/infer_request.cpp:223:
Exception from src/plugins/intel_npu/src/backend/include/zero_utils.hpp:21:
L0 zeFenceHostSynchronize result: ZE_RESULT_ERROR_UNKNOWN, code 0x7ffffffe - an action is required to complete the desired operation
Step-by-step reproduction
my cross_attention code is here:
And followed by my convert code:
When I try to use the ov cross block, the problem occurs:
t = compiled_model(example_input)
But I use the original model, there is no such problem. And here is my cross block xml.
cross.xml.txt
Relevant log output
Issue submission checklist
The text was updated successfully, but these errors were encountered: