Add CUDA opset 20 ReduceMax int8 tests - #31836
Open
Zupeng Wang (zupengwang) wants to merge 1 commit into
Open
Conversation
|
Azure Pipelines: There may be pipelines that require an authorized user to comment /azp run to run. |
Zupeng Wang (zupengwang)
marked this pull request as ready for review
August 10, 2026 05:06
|
Azure Pipelines: There may be pipelines that require an authorized user to comment /azp run to run. |
Author
|
@microsoft-github-policy-service agree |
Zupeng Wang (zupengwang)
marked this pull request as draft
August 10, 2026 05:12
Zupeng Wang (zupengwang)
marked this pull request as ready for review
August 10, 2026 05:12
|
Azure Pipelines: There may be pipelines that require an authorized user to comment /azp run to run. |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 CUDA EP opset 20
ReduceMaxcoverage forint8_tanduint8_t. The tests use negative signed inputs and high unsigned values, and explicitly run withDefaultCudaExecutionProvider().Validation:
onnxruntime_provider_testtarget with CUDA 13.0 and cuDNN 9.24 for SM86.ReduceMaxCUDA tests successfully.lintrunneron the changed file with no issues.Motivation and Context
Complete the remaining test TODO in #27729 after the opset 20 CUDA registrations added by #27755. This is test-only and does not change kernels or public APIs.