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

[cherry pick #43088 #40664] Add float16 to fake quantize/dequantize OP #43689

Merged
merged 2 commits into from
Jun 21, 2022

Conversation

yghstill
Copy link
Contributor

PR types

Function optimization

PR changes

APIs

Describe

cherry pick #43088 #40664: Add float16 to fake quantize/dequantize OP

  • Support float16 fake qdq OPs to do QAT + AMP training with static graph.
  • Simplify the code of fake quantize op unit test.

@paddle-bot-old
Copy link

你的PR提交成功,感谢你对开源项目的贡献!
请关注后续CI自动化测试结果,详情请参考Paddle-CI手册
Your PR has been submitted. Thanks for your contribution!
Please wait for the result of CI firstly. See Paddle CI Manual for details.

Copy link
Contributor

@Xreki Xreki left a comment

Choose a reason for hiding this comment

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

LGTM for the change of atol

Copy link
Contributor

@XiaoguangHu01 XiaoguangHu01 left a comment

Choose a reason for hiding this comment

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

LGTM

@XiaoguangHu01 XiaoguangHu01 merged commit 9783e88 into PaddlePaddle:release/2.3 Jun 21, 2022
@yghstill yghstill deleted the cp_quant_fp16 branch June 21, 2022 09:09
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.

None yet

5 participants