Skip to content

Conversation

chunghow-qti
Copy link

Description

  • QNN EP supports batch multiplier during inference, while InferenceSession::checkShapes validates the input_output_shape against the expected_shape.
  • This check is relaxed when all nodes are assigned to QNN EP and running batch size is divisible by the original batch size.
  • A separate PR will be submitted for the implementation of batch multiplier support in QNN EP.

Motivation and Context

@microsoft-github-policy-service agree company="Qualcomm"

Description
* QNN EP supports batch multiplier during inference,
while InferenceSession::checkShapes validates the input_output_shape against
the expected_shape.
* This check is relaxed when all nodes are assigned to QNN EP and
  running batch size is divisible by the original batch size.
* A separate PR will be submitted for the implementation of batch
multiplier support in QNN EP.

Motivation and Context
* This change supports batch multiplier in QNN API to ORT as described
  in this page:
  https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-10/function_QnnGraph_8h_1a3ea05f42a9295f9a74a2e3a0cdd64228.html
@chunghow-qti
Copy link
Author

@microsoft-github-policy-service agree company="Qualcomm"

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.

1 participant