-
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
Segmentation fault when running test_get_runtime_model test #20163
Conversation
|
|
||
core = Core() | ||
user_stream = compiled_model.export_model() | ||
core.import_model(user_stream, device) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
it's totally unclear why do we need to export / import model to resolve a segfault
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@siddhant-0707 mentioned that it is unclear why. However, my best bet would be creating actual core = Core()
that is somehow affecting internals. Would you be able to test it out?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
compiled_model
(returned by generate_relu_compiled_model
) is expected to hold some internal to prolong its live time and ensure correct destruction.
But if it's 100% reproducible, it can be debugged with dbg. @siddhant-0707 could you please try to collect debugger logs?
This PR will be closed in a week because of 2 weeks of no activity. |
This PR was closed because it has been stalled for 2 week with no activity. |
Details:
3.8.10
Tickets:
test_get_runtime_model
test #18388It appears that the segfault is fixed when
core.import_model()
is called beforeget_runtime_model()