-
Notifications
You must be signed in to change notification settings - Fork 5.6k
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
【Hackathon4 No.61】remainder 算子FP16/BF16单测完善 #52920
【Hackathon4 No.61】remainder 算子FP16/BF16单测完善 #52920
Conversation
你的PR提交成功,感谢你对开源项目的贡献! |
Sorry to inform you that 566cec1's CIs have passed for more than 7 days. To prevent PR conflicts, you need to re-run all CIs manually. |
checker=self.verify_output, place=place | ||
) | ||
|
||
def verify_output(self, outs): |
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.
为什么需要自定义一个计算函数
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.
不管是用np.mod还是np.fmod,rtol都到了300以上
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.
由于数据类型所限,使用fp32计算和使用bf16的结果差距太大,这里可以对输入做一些处理,初始化为FP32->convert为bf16->convert为fp32,即convert_uint16_to_float(convert_float_to_uint16(x))
然后再计算参考结果,这样应该是可以通过的,无需使用自定义函数
…e/Paddle into hackathon4-No61-remainder
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
PR types
Others
PR changes
Others
Description
remainder