from typing import List, Optional, Tuple, Union
import torch
import torch_npu
from torch import Tensor
from torch.optim.optimizer import Optimizer
from torch.optim.adamw import AdamW as TorchAdamW


def adamw(params: List[Tensor],
          grads: List[Tensor],
          exp_avgs: List[Tensor],
          exp_avg_sqs: List[Tensor],
          max_exp_avg_sqs: List[Tensor],
          step_tensor: Tensor,
          *,
          amsgrad: bool,
          beta1: float,
          beta2: float,
          lr: float,
          weight_decay: float,
          eps: float,
          maximize: bool):
    r"""Functional API that performs AdamW algorithm computation.
    See :class:`~torch.optim.AdamW` for details.
    """
    for i, param in enumerate(params):
        grad = grads[i]
        exp_avg = exp_avgs[i]
        exp_avg_sq = exp_avg_sqs[i]
        max_exp_avg_sq = max_exp_avg_sqs[i] if amsgrad else None

        torch._fused_adamw_(
            [param],
            [grad],
            [exp_avg],
            [exp_avg_sq],
            [max_exp_avg_sq] if amsgrad else [],
            [step_tensor],
            amsgrad=amsgrad,
            lr=lr,
            beta1=beta1,
            beta2=beta2,
            weight_decay=weight_decay,
            eps=eps,
            maximize=maximize
        )


class AdamW(Optimizer):
    def __init__(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8,
                 weight_decay=1e-2, amsgrad=False, *, maximize: bool = False):
        if not 0.0 <= lr:
            raise ValueError("Invalid learning rate: {}".format(lr))
        if not 0.0 <= eps:
            raise ValueError("Invalid epsilon value: {}".format(eps))
        if not 0.0 <= betas[0] < 1.0:
            raise ValueError("Invalid beta parameter at index 0: {}".format(betas[0]))
        if not 0.0 <= betas[1] < 1.0:
            raise ValueError("Invalid beta parameter at index 1: {}".format(betas[1]))
        if not 0.0 <= weight_decay:
            raise ValueError("Invalid weight_decay value: {}".format(weight_decay))
        defaults = dict(lr=lr, betas=betas, eps=eps,
                        weight_decay=weight_decay, amsgrad=amsgrad, maximize=maximize)
        super(AdamW, self).__init__(params, defaults)

    def __setstate__(self, state):
        super(AdamW, self).__setstate__(state)
        for group in self.param_groups:
            group.setdefault('amsgrad', False)
            group.setdefault('maximize', False)

    @torch.no_grad()
    def step(self, closure=None):
        loss = None
        if closure is not None:
            with torch.enable_grad():
                loss = closure()

        for group in self.param_groups:
            params_with_grad = []
            grads = []
            exp_avgs = []
            exp_avg_sqs = []
            state_sums = []
            max_exp_avg_sqs = []
            state_steps = []
            amsgrad = group['amsgrad']
            beta1, beta2 = group['betas']

            if 'step' in group:
                group['step'] += 1
                if group['step'].is_cpu:
                    group['step'] = group['step'].cuda()
            else:
                group['step'] = torch.tensor(1, dtype=torch.int64, device=torch.cuda.current_device())

            for p in group['params']:
                if p.grad is None:
                    continue
                params_with_grad.append(p)
                if p.grad.is_sparse:
                    raise RuntimeError('AdamW does not support sparse gradients')
                grads.append(p.grad)

                state = self.state[p]

                # State initialization
                if len(state) == 0:
                    # Exponential moving average of gradient values
                    state['exp_avg'] = torch.zeros_like(p, memory_format=torch.preserve_format)
                    # Exponential moving average of squared gradient values
                    state['exp_avg_sq'] = torch.zeros_like(p, memory_format=torch.preserve_format)
                    if amsgrad:
                        # Maintains max of all exp. moving avg. of sq. grad. values
                        state['max_exp_avg_sq'] = torch.zeros_like(p, memory_format=torch.preserve_format)

                exp_avgs.append(state['exp_avg'])
                exp_avg_sqs.append(state['exp_avg_sq'])

                if amsgrad:
                    max_exp_avg_sqs.append(state['max_exp_avg_sq'])

            adamw(params_with_grad,
                  grads,
                  exp_avgs,
                  exp_avg_sqs,
                  max_exp_avg_sqs,
                  group['step'],
                  amsgrad=amsgrad,
                  beta1=beta1,
                  beta2=beta2,
                  lr=group['lr'],
                  weight_decay=group['weight_decay'],
                  eps=group['eps'],
                  maximize=group['maximize'])

        return loss