Skip to content
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

[EISW-140760] Device memory refactor fix #466

Merged
merged 1 commit into from
Oct 3, 2024

Conversation

javier-intel
Copy link

Description

Fix ORT crash caused when running with OVEP without device memory. The crash was root caused to be due to outputs_ array only set when device memory is used. Fixed by populating outputs_ array in both cases, with and without device memory.

Motivation and Context

Fix P1 issue from https://jira.devtools.intel.com/browse/EISW-140760

@saurabhkale17
Copy link

saurabhkale17 commented Oct 3, 2024

LGTM. Model passes functionality with default CPU allocator.
Internal CI: http://ai-frameworks-integration.mlops.iotg.sclab.intel.com:8080/view/ONNXRT/job/internal_ci/182/
all tests are passing

FYI:
Model PSS failing with device_memory_name|OpenVINO_RT_NPU ..Only when ORT optimizations are disabled.
Model PSS passing with device_memory_name|OpenVINO_RT_NPU ..Only when ORT optimizations are enabled.

More details in the ticket: https://jira.devtools.intel.com/browse/EISW-140760

@saurabhkale17 saurabhkale17 merged commit dd49e37 into ovep-develop-lnl-1.2 Oct 3, 2024
11 of 16 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants