Skip to content

Added support for Intel dGPU for inference#6879

Merged
itallix merged 3 commits into
developfrom
aurelien/add-intel-dpgu-inference
Jun 23, 2026
Merged

Added support for Intel dGPU for inference#6879
itallix merged 3 commits into
developfrom
aurelien/add-intel-dpgu-inference

Conversation

@A-Artemis

@A-Artemis A-Artemis commented Jun 19, 2026

Copy link
Copy Markdown
Contributor

Summary

Accepts Intel dGPU for inference device.

How to test

Checklist

  • The PR title and description are clear and descriptive
  • I have manually tested the changes
  • All changes are covered by automated tests
  • All related issues are linked to this PR (if applicable)
  • Documentation has been updated (if applicable)

@A-Artemis A-Artemis self-assigned this Jun 19, 2026
@A-Artemis A-Artemis marked this pull request as ready for review June 19, 2026 17:17
@A-Artemis A-Artemis requested a review from a team as a code owner June 19, 2026 17:17
Copilot AI review requested due to automatic review settings June 19, 2026 17:17
@github-actions github-actions Bot added TEST Any changes in tests Geti Backend Issues related to the Geti application server labels Jun 19, 2026

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds Intel discrete GPU (dGPU) support to the backend’s OpenVINO-based inference device enumeration, aligning available inference devices with newer Intel GPU hardware while continuing to exclude unsupported/non-Intel GPUs.

Changes:

  • Expanded SystemService.get_inference_devices() filtering to allow Intel-branded discrete GPUs in addition to iGPUs.
  • Updated unit tests to cover inclusion of Intel dGPU and exclusion of a non-Intel discrete GPU in the OpenVINO device list.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File Description
application/backend/app/services/system_service.py Updates OpenVINO inference device discovery to include Intel-branded dGPUs and adjusts filtering logic.
application/backend/tests/unit/services/test_system_service.py Updates unit test expectations to validate Intel dGPU inclusion and non-Intel dGPU exclusion.

Comment thread application/backend/app/services/system_service.py Outdated
@github-actions

github-actions Bot commented Jun 19, 2026

Copy link
Copy Markdown

🐳 Docker image sizes

Device Size
xpu 10791.8 MB (10.54 GB)
cuda 10208.6 MB (9.97 GB)
cpu 4003.2 MB (3.91 GB)

@github-actions

Copy link
Copy Markdown

📊 Test coverage report

Metric Coverage
Lines 57.0%
Functions 53.9%
Branches 48.6%
Statements 56.6%

A-Artemis and others added 3 commits June 23, 2026 10:11
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
@itallix itallix force-pushed the aurelien/add-intel-dpgu-inference branch from 3d5323b to be40776 Compare June 23, 2026 08:11
@itallix itallix added this pull request to the merge queue Jun 23, 2026
Merged via the queue into develop with commit 659cf9a Jun 23, 2026
36 checks passed
@itallix itallix deleted the aurelien/add-intel-dpgu-inference branch June 23, 2026 08:53
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Geti Backend Issues related to the Geti application server TEST Any changes in tests

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants