Function at::_fused_adamw(at::TensorList, at::TensorList, at::TensorList, at::TensorList, at::TensorList, at::TensorList, const at::Tensor&, double, double, double, double, bool, bool, const ::std::optional<at::Tensor>&, const ::std::optional<at::Tensor>&)¶

Function Documentation¶

inline ::std::tuple<::std::vector<at::Tensor>, ::std::vector<at::Tensor>, ::std::vector<at::Tensor>, ::std::vector<at::Tensor>, ::std::vector<at::Tensor>> at::_fused_adamw(at::TensorList self, at::TensorList grads, at::TensorList exp_avgs, at::TensorList exp_avg_sqs, at::TensorList max_exp_avg_sqs, at::TensorList state_steps, const at::Tensor &lr, double beta1, double beta2, double weight_decay, double eps, bool amsgrad, bool maximize, const ::std::optional<at::Tensor> &grad_scale = {}, const ::std::optional<at::Tensor> &found_inf = {})¶