-
Notifications
You must be signed in to change notification settings - Fork 5.7k
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
【Hackathon 6th No.53】move fake_channel_wise_quantize_abs_max/fake_channel_wise_quantize_dequantize_abs_max op to phi - part #64266
Conversation
…e_dequantize_abs_max to phi
你的PR提交成功,感谢你对开源项目的贡献! |
) = _C_ops.fake_channel_wise_quantize_dequantize_abs_max( | ||
input, | ||
self._quant_bits, | ||
1, | ||
self._quant_axis, | ||
quant_out, | ||
out_scale, | ||
) | ||
return out | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这里这样改一下:
(
out,
scale,
) = _C_ops.fake_channel_wise_quantize_dequantize_abs_max(
input,
self._quant_bits,
1,
self._quant_axis
)
_C_ops.assign_out_(out, quant_out)
_C_ops.assign_out_(scale, out_scale)
return quant_out
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
已修改
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
…nnel_wise_quantize_dequantize_abs_max op to phi - part (PaddlePaddle#64266) * move fake_channel_wise_quantize_abs_max and fake_channel_wise_quantize_dequantize_abs_max to phi * fix opps yaml * fix ops yaml * fix accuracy
…nnel_wise_quantize_dequantize_abs_max op to phi - part (PaddlePaddle#64266) * move fake_channel_wise_quantize_abs_max and fake_channel_wise_quantize_dequantize_abs_max to phi * fix opps yaml * fix ops yaml * fix accuracy
PR Category
Others
PR Types
Others
Description
combine #63991 with #64255