fix: resolve_device/resolve_eps uses get_registered_ep_devices#712
Merged
Conversation
added 3 commits
May 22, 2026 15:22
timenick
reviewed
May 25, 2026
Collaborator
timenick
left a comment
timenick
left a comment
There was a problem hiding this comment.
One concern: the new _get_device_ep_map_from_ort() and the existing _get_available_eps() now use different ORT APIs, and your error messages mix the two so users can see contradictory output.
DingmaomaoBJTU
requested changes
May 25, 2026
Collaborator
DingmaomaoBJTU
left a comment
DingmaomaoBJTU
left a comment
There was a problem hiding this comment.
Overall the direction is right — using get_registered_ep_devices() (the authoritative ORT API) instead of WMI hardware probes eliminates the DML-GPU false positive that caused the original crash. Nice simplification of the test mocking too — single mock point via _patch_device_ep_map is much cleaner.
A few issues to address before merging (1 bug, 2 robustness, 2 nits).
timenick
approved these changes
May 25, 2026
DingmaomaoBJTU
approved these changes
May 25, 2026
This was referenced May 25, 2026
xieofxie
added a commit
that referenced
this pull request
May 26, 2026
- remove class WinML as it is confusing - also incidentally fixes a bug introduced by #712 — the two independent singletons (WinML and WinMLEPRegistry) both call ort.register_execution_provider_library(...) but dedup separately, so after #712 winml perf --device npu emits a library is already registered under QNNExecutionProvider traceback (benign but alarming, swallowed by except Exception) --------- Co-authored-by: hualxie <hualxie@microsoft.com>
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
3 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.
For a device without openvino gpu but have openvino cpu, the follow command will crash before
winml compile -m "resnet-cpu\model.onnx" -v --ep openvinoBecause it will be resolved to gpu device since dml has gpu device