Skip to content

[QNN EP] Support Qnn MatMul with 2 dynamic inputs which are uint16 quantized#18469

Merged
HectorSVC merged 4 commits intomainfrom
qnn_matmul_a16w16
Nov 16, 2023
Merged

[QNN EP] Support Qnn MatMul with 2 dynamic inputs which are uint16 quantized#18469
HectorSVC merged 4 commits intomainfrom
qnn_matmul_a16w16

Conversation

@HectorSVC
Copy link
Contributor

Description

QNN can't run MatMul if both inputs are dynamic inputs with uint16 quantized on v68. Make it run by inserting Convert op to convert 1 input to int8

@HectorSVC HectorSVC merged commit 6a4e448 into main Nov 16, 2023
@HectorSVC HectorSVC deleted the qnn_matmul_a16w16 branch November 16, 2023 21:44
kleiti pushed a commit to kleiti/onnxruntime that referenced this pull request Mar 22, 2024
…antized (microsoft#18469)

### Description
QNN can't run MatMul if both inputs are dynamic inputs with uint16 quantized on v68. Make it run by inserting Convert op to convert 1 input to int8
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.

2 participants