Skip to content

Fp8 ptq kernel function #65441

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

Merged
merged 14 commits into from
Jul 3, 2024
Merged

Fp8 ptq kernel function #65441

merged 14 commits into from
Jul 3, 2024

Conversation

YZW-explorer
Copy link
Contributor

@YZW-explorer YZW-explorer commented Jun 25, 2024

PR Category

Inference

PR Types

New features

Description

quantize_linear and dequantize_linear now support fp8 ptq function

Copy link

paddle-bot bot commented Jun 25, 2024

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.

@paddle-bot paddle-bot bot added the contributor External developers label Jun 25, 2024
ceci3
ceci3 previously approved these changes Jun 25, 2024
@@ -78,18 +78,44 @@ def __init__(
self._zero_point.set_value(zero_point)
self._quant_axis = -1 if quant_axis is None else quant_axis
self._bit_length = bit_length
self._group_size = group_size
if isinstance(self._bit_length, tuple):
Copy link
Contributor

Choose a reason for hiding this comment

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

看起来接口文档里bit_length也得增加下注释,这里使用方式变了

@ceci3 ceci3 merged commit 6a21a78 into PaddlePaddle:develop Jul 3, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
contributor External developers
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants