Correctly changing precision in DLRM

[rishucoding]

Hello,

I would like to change the precision used in DLRM inference. I observed that the default datatype used in the original code is "float32", in the create_emb() method. Is changing the dtype to any of the supported values enough to correctly change the precision?

I believe that the generated embedding table would be directly used in the apply_emb() function.

Thanks for the help.
Rishabh Jain

[hrwleo]

已收到邮件  阿里阿豆故咋一马斯！如未及时回复，请致电15868848097  QQ：812737452