Fix NPU hardware accelerator detection for custom models loaded from AITK converted genai_config.json#525
Merged
Merged
Conversation
Copilot
AI
changed the title
[WIP] Fix NPU hardware accelerator detection for custom models
Fix NPU hardware accelerator detection for custom models loaded from AITK converted genai_config.json
Dec 4, 2025
weiyuanyue
approved these changes
Dec 4, 2025
weiyuanyue
marked this pull request as ready for review
December 4, 2025 02:54
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
AITK-converted NPU models were incorrectly tagged as CPU because the detection logic couldn't parse diverse execution provider configurations from
genai_config.json.Changes
Enhanced GenAI Config Parsing (
GenAIConfig.cs)Dml/Cudaclasses with flexibleJsonExtensionDataparsing to support diverse execution providers (QNN, OpenVINO, VitisAI, DML, CUDA, etc.)SessionOptionssupport—AITK configs specify EPs at both decoder and pipeline levelsHasProvider()andGetProviderOptions()for dynamic provider detectionHardware Detection (
DeviceUtils.cs,ExecutionProviderNames.cs)HasNPU()using ONNX Runtime's EP device detectionGetAvailableExecutionProviders()with certified EP registration and cachingExecutionProviderNamesconstants class to eliminate hardcoded EP stringsModel Classification (
UserAddedModelUtil.cs)GetHardwareAcceleratorFromConfig()to:ValidateExecutionProviders()to check EP availability before model loadCompatibility Checks (
ModelCompatibility.cs)Code Quality
ExecutionProviderNamesconstantsBefore/After
Before: NPU model shows CPU tag

After: NPU model correctly tagged

Warning dialog for unavailable EPs:

💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.