Fix CUDA EP: add opset 24 kernel registrations for Reshape and Cast#28368
Closed
justinchuby wants to merge 1 commit intomainfrom
Closed
Fix CUDA EP: add opset 24 kernel registrations for Reshape and Cast#28368justinchuby wants to merge 1 commit intomainfrom
justinchuby wants to merge 1 commit intomainfrom
Conversation
ONNX opset 24 bumped Reshape and Cast (added float8e8m0 type support). ORT CUDA EP only had opset 23 registrations, so these ops fell to CPUExecutionProvider on opset 24 models, producing ~280 MemcpyFromHost/MemcpyToHost nodes. Version existing opset 23 registrations to (23, 23) and add new non-versioned opset 24 registrations. Same kernel implementations. Result: 282 memcpy → 4 memcpy for opset 24 models on CUDA EP. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Signed-off-by: Justin Chu <justinchu@microsoft.com>
Contributor
Contributor
Author
|
Will close. LMK when they can be merged? |
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
ONNX opset 24 bumped Reshape and Cast (added
float8e8m0type). ORT CUDA EP only had opset 23 registrations, causing these ops to fall to CPUExecutionProvider on opset 24 models — producing ~280 memcpy nodes.Fix: Version opset 23 registrations to (23, 23) and add non-versioned opset 24 registrations. Same kernel code.
Result: 282 memcpy → 4 memcpy for opset 24 models.
Tested with Gemma4 E2B-it (2B, opset 24) on H200.