Update CUDA TopK kernel registration to opset 24 with BFloat16 support#27735
Merged
Update CUDA TopK kernel registration to opset 24 with BFloat16 support#27735
Conversation
Co-authored-by: tianleiwu <30328909+tianleiwu@users.noreply.github.com>
Copilot created this pull request from a session on behalf of
tianleiwu
March 18, 2026 17:52
View session
Contributor
|
/azp run Windows GPU Doc Gen CI Pipeline |
|
Azure Pipelines successfully started running 1 pipeline(s). |
… + 24+) Co-authored-by: tianleiwu <30328909+tianleiwu@users.noreply.github.com>
tianleiwu
approved these changes
Mar 20, 2026
Contributor
|
@copilot, TopK-24 supports bfloat16 according to https://github.com/onnx/onnx/blob/main/docs/Operators.md#TopK |
Co-authored-by: tianleiwu <30328909+tianleiwu@users.noreply.github.com> Agent-Logs-Url: https://github.com/microsoft/onnxruntime/sessions/cd70afdc-35b3-4472-a3d3-262dbb68f2b5
Contributor
Author
Added BFloat16 support for CUDA TopK opset 24 in commit
|
Copilot
AI
changed the title
Update CUDA TopK kernel registration to opset 24
Update CUDA TopK kernel registration to opset 24 with BFloat16 support
Mar 20, 2026
Contributor
|
@copilot, could you add a test case for bfloat16 TopK-24? |
Co-authored-by: tianleiwu <30328909+tianleiwu@users.noreply.github.com> Agent-Logs-Url: https://github.com/microsoft/onnxruntime/sessions/9eab8ca4-7d1f-4b1e-bcb9-b65c411b4256
Contributor
Author
Added three BFloat16 test cases in commit
All tests use the |
… operations Co-authored-by: tianleiwu <30328909+tianleiwu@users.noreply.github.com> Agent-Logs-Url: https://github.com/microsoft/onnxruntime/sessions/d0c34466-e21b-4457-a2cf-df7af450f1a1
Contributor
|
/azp run Linux QNN CI Pipeline, Win_TRT_Minimal_CUDA_Test_CI, Windows ARM64 QNN CI Pipeline, Windows GPU Doc Gen CI Pipeline |
|
Azure Pipelines successfully started running 4 pipeline(s). |
tianleiwu
approved these changes
Mar 24, 2026
kunal-vaishnavi
approved these changes
Mar 24, 2026
titaiwangms
approved these changes
Mar 24, 2026
tianleiwu
added a commit
that referenced
this pull request
May 5, 2026
### Description Extends CUDA ReduceMax and ReduceMin kernel registrations from opset 18 to opset 20. - **`reduction_ops.cc`**: Added `REGISTER_KERNEL_VERSIONED_RANGE_AXES_INPUT_TYPED` macro for versioned ranges requiring `InputMemoryType(OrtMemTypeCPUInput, 1)`. Split both operators from 2-way (1–17, 18+) to 3-way (1–17, 18–19, 20+). - **`cuda_execution_provider.cc`**: Capped opset 18 forward declarations and `BuildKernelCreateInfo` entries to versioned 18–19. Added opset 20 non-versioned entries for both operators. Type coverage maintained as-is: ReduceMax (float, double, MLFloat16, int32_t, int64_t), ReduceMin adds int8_t, uint8_t. ### Motivation and Context ReduceMax and ReduceMin CUDA registrations stopped at opset 18; ONNX latest is opset 20. Models exported with opset 19–20 could fail to find a matching CUDA kernel for these ops. Follows the same pattern used in #27735 (TopK) and other opset gap PRs tracked in #27729. --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: tianleiwu <30328909+tianleiwu@users.noreply.github.com> Co-authored-by: Tianlei Wu <tlwu@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
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.
💬 Send tasks to Copilot coding agent from Slack and Teams to turn conversations into code. Copilot posts an update in your thread when it's finished.