[fix] Keep global copy of opened backends.#17
Merged
again4you merged 1 commit intonnstreamer:mainfrom Jan 22, 2026
Merged
Conversation
- Maintaining a global copy of opened backends in GHashTable to mitigate memory fragmentation in iterations of [hal_ml_create - hal_ml_destroy] which load and unload backend libraries. - This extra reference prevents the underlying library from being unloaded when the user calls hal_ml_destroy. - Adding a destructor function to release pinned backends. This would resolve [this issue](https://github.sec.samsung.net/OASIS/ML-Service-API-DA-Examples/issues/12) Signed-off-by: Yongjoo Ahn <yongjoo1.ahn@samsung.com>
anyj0527
force-pushed
the
pin-current-backend
branch
from
7ccde0b to
bd94678
Compare
|
LGTM . Pipeline mode seems to be fixed with this commit for amlogic , |
songgot
approved these changes
Jan 22, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This would resolve this issue