Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[CUDA EP] Fix BeamSearch on T5 with sequence_as_input_ids (#20667) #20668

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

amancini-N
Copy link

Description

Change the implementation of BeamSearch op when using CUDA EP: in case of T5 model, and in case the decoder input_ids are sequences, copy the sequences device-to-device instead of host-to-device

Motivation and Context

@tianleiwu
Copy link
Contributor

/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows CPU CI Pipeline,Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline,ONNX Runtime Web CI Pipeline,Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline

@tianleiwu
Copy link
Contributor

/azp run Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,orttraining-amd-gpu-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,onnxruntime-binary-size-checks-ci-pipeline,Big Models,Android CI Pipeline

@tianleiwu
Copy link
Contributor

/azp run iOS CI Pipeline,ONNX Runtime React Native CI Pipeline

Copy link

Azure Pipelines successfully started running 2 pipeline(s).

Copy link

Azure Pipelines successfully started running 10 pipeline(s).

1 similar comment
Copy link

Azure Pipelines successfully started running 10 pipeline(s).

@tianleiwu
Copy link
Contributor

@amancini-N, could you take a look at those build and test errors in CI pipeline. Let me know if you need help to resolve them.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

BeamSearch op returning wrong results on CUDA execution provider when sequence is used as input_ids
2 participants