[Paddle C++ API] Remapping input and output tensors after XPU op has fallen back to CPU op (#50625)
* fix accurary diff issue when XPU op batch_norm is added to XPU blacklist * remap op output tensor to input tensor when the op has fallen back to CPU * rename function name and fix bug causing by InplaceCounter
Showing
想要评论请 注册 或 登录