未验证 提交 478ea78b 编写于 作者: C ceci3 提交者: GitHub

add layernorm (#33610)

上级 1e4e6a36
......@@ -81,6 +81,7 @@ _out_scale_op_list = [
"transpose",
"pad2d",
"reshape",
"layer_norm",
]
# list op real input and output names, to avoid processing input such as AxisTensor.
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册