Skip to content

Conversation

@yufenglee
Copy link
Member

Description: Describe your changes.

  1. add a session option to control quantization QDQ format
  2. skip constant folding dequant for qdq format.

@yufenglee yufenglee requested a review from a team as a code owner February 10, 2021 21:05
// "0": disable. ORT doesn't do fusion logic for QDQ format.
// "1": enable. ORT does fusion logic for QDQ format.
// Its default value is "1"
static const char* const kOrtSessionOptionsEnableQuantQDQ = "session.enable_quant_qdq";
Copy link
Contributor

@guoyu-wang guoyu-wang Feb 11, 2021

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

If the qdq is by default enabled, is it better to make this "session.disable_quant_qdq"?

@yufenglee yufenglee merged commit 1c3168c into master Feb 11, 2021
@yufenglee yufenglee deleted the yufeng/qdq_const_fold branch February 11, 2021 22:06
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.

3 participants