Add infrastructure for auto EP selection #24430
Merged
Conversation
This file contains 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]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
skottmckay
commented
Apr 15, 2025
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
skottmckay
commented
Apr 15, 2025
skottmckay
commented
Apr 15, 2025
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
|
bunch of build failures. missing some dxcore header ? |
yuslepukhin
reviewed
Apr 15, 2025
skottmckay
commented
Apr 15, 2025
skottmckay
commented
Apr 15, 2025
fs-eire
reviewed
Apr 15, 2025
…EpInfrastructure_PR
Address PR comment
Disable EP registration/auto selection testing on non-Windows platforms. There's no device discovery so it can't be used.
…thub.com/microsoft/onnxruntime into skottmckay/AutoSelectEpInfrastructure_PR
Add ORT_API_CALL fixes Co-authored-by: Adrian Lizarraga <[email protected]>
…EpInfrastructure_PR
…cies a lot simpler, and in the future we need to provide that to an EP author so it is reasonable for it to be implemented in onnxruntime_session. Address PR comments. Add onnxruntime_session to the CUDA EP dependencies.
Co-authored-by: Adrian Lizarraga <[email protected]>
…thub.com/microsoft/onnxruntime into skottmckay/AutoSelectEpInfrastructure_PR
- move provider bridge support to the EP side - change SessionOptionsAppendExecutionProvider_V2 to take OrtEpDevices as input - better device discovery (pending final implementation)
Avoid double lock for Provider Get when it calls Load.
Co-authored-by: Adrian Lizarraga <[email protected]>
Disable setting device_id for DML. Need to investigate why we get an invalid bus number in device discovery. The device discovery code is temporary and most likely has an issue.
…thub.com/microsoft/onnxruntime into skottmckay/AutoSelectEpInfrastructure_PR
jywu-msft
approved these changes
Apr 20, 2025
|
Will follow up any comments in separate PR |
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.
Description
Add infrastructure to enable auto EP selection.
Device discovery for CPU/GPU/NPU on Windows.
Supports internal (CPU/DML/WebGPU) and provider bridge (CUDA) EPs currently.
Infrastructure will be used with plugin EPs next.
Selection policy implementation will be added next, so in the interim there's a temporary function with manually specified selection so unit tests can cover the end-to-end.
Motivation and Context