Add support for configurable inference device for the model #5478
Conversation
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
github-actions
bot
added
TEST
Contributor
There was a problem hiding this comment.
Pull request overview
Adds support for selecting an inference device and ensures the model reloads when the device changes.
Changes:
- Extend model activation / loaded model state to include an inference
device. - Trigger model reload on
INFERENCE_DEVICE_CHANGEDevents (including new unit coverage). - Reload the inference model when the configured device differs from the currently loaded one.
Reviewed changes
Copilot reviewed 7 out of 7 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
| application/backend/app/models/model_activation.py | Adds device to persisted activation state. |
| application/backend/app/services/active_model_service.py | Loads device from active pipeline and reloads model when device changes. |
| application/backend/app/services/event/event_bus.py | Emits model-reload signal on inference device change. |
| application/backend/app/workers/dispatching.py | Subscribes dispatching worker to inference device change event. |
| application/backend/app/repositories/active_model_repo.py | Adds DB query for active pipeline’s configured device. |
| application/backend/tests/unit/services/test_active_model_service.py | Asserts LoadedModel.device matches activation state. |
| application/backend/tests/unit/services/event/test_event_bus.py | Adds test ensuring device-change triggers model reload. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
📊 Test coverage report
|
Docker Image SizesCPU
GPU
XPU
|
leoll2
approved these changes
Feb 10, 2026
Contributor
leoll2
left a comment
leoll2
left a comment
There was a problem hiding this comment.
LGTM, preferably ask for an additional review since I pushed some changes myself.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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.
Summary
The emitted event is now handled, and the model is reloaded with the desired inference device.
How to test
Start an inference pipeline, check the logs:
Change the device:
Check the logs again:
Checklist