# Copyright (c) OpenMMLab. All rights reserved.
from typing import Optional, Tuple

import torch
import torch.nn.functional as F


def rotate_half(x):
    """Rotates half the hidden dims of the input."""
    x1 = x[..., :x.shape[-1] // 2]
    x2 = x[..., x.shape[-1] // 2:]
    return torch.cat((-x2, x1), dim=-1)


def apply_rotary_pos_emb(q, k, cos, sin, position_ids):
    # The first two dimensions of cos and sin are always 1,
    # so we can `squeeze` them.
    cos = cos.squeeze(1).squeeze(0)  # [seq_len, dim]
    sin = sin.squeeze(1).squeeze(0)  # [seq_len, dim]
    cos = cos[position_ids].unsqueeze(1)  # [bs, 1, seq_len, dim]
    sin = sin[position_ids].unsqueeze(1)  # [bs, 1, seq_len, dim]
    q_embed = (q * cos) + (rotate_half(q) * sin)
    k_embed = (k * cos) + (rotate_half(k) * sin)
    return q_embed, k_embed


def repeat_kv(hidden_states: torch.Tensor, n_rep: int) -> torch.Tensor:
    """This is the equivalent of torch.repeat_interleave(x, dim=1,
    repeats=n_rep).

    The hidden states go from (batch, num_key_value_heads, seqlen, head_dim) to
    (batch, num_attention_heads, seqlen, head_dim)
    """
    batch, num_key_value_heads, slen, head_dim = hidden_states.shape
    if n_rep == 1:
        return hidden_states
    hidden_states = hidden_states[:, :,
                                  None, :, :].expand(batch,
                                                     num_key_value_heads,
                                                     n_rep, slen, head_dim)
    return hidden_states.reshape(batch, num_key_value_heads * n_rep, slen,
                                 head_dim)


def yi_attn_forward(
    self,
    hidden_states: torch.Tensor,
    attention_mask: Optional[torch.Tensor] = None,
    position_ids: Optional[torch.LongTensor] = None,
    past_key_value: Optional[Tuple[torch.Tensor]] = None,
    output_attentions: bool = False,
    use_cache: bool = False,
    **kwargs,
) -> Tuple[torch.Tensor, Optional[torch.Tensor],
           Optional[Tuple[torch.Tensor]]]:
    bsz, q_len, _ = hidden_states.size()

    query_states = self.q_proj(hidden_states)
    key_states = self.k_proj(hidden_states)
    value_states = self.v_proj(hidden_states)

    query_states = query_states.view(bsz, q_len, self.num_heads,
                                     self.head_dim).transpose(1, 2)
    key_states = key_states.view(bsz, q_len, self.num_key_value_heads,
                                 self.head_dim).transpose(1, 2)
    value_states = value_states.view(bsz, q_len, self.num_key_value_heads,
                                     self.head_dim).transpose(1, 2)

    kv_seq_len = key_states.shape[-2]
    if past_key_value is not None:
        kv_seq_len += past_key_value[0].shape[-2]
    cos, sin = self.rotary_emb(value_states, seq_len=kv_seq_len)
    query_states, key_states = apply_rotary_pos_emb(query_states, key_states,
                                                    cos, sin, position_ids)

    if past_key_value is not None:
        # reuse k, v, self_attention
        key_states = torch.cat([past_key_value[0], key_states], dim=2)
        value_states = torch.cat([past_key_value[1], value_states], dim=2)

    past_key_value = (key_states, value_states) if use_cache else None

    # repeat k/v heads if n_kv_heads < n_heads
    key_states = repeat_kv(key_states, self.num_key_value_groups)
    value_states = repeat_kv(value_states, self.num_key_value_groups)

    # use flash attention implemented by pytorch
    attn_output = F.scaled_dot_product_attention(
        query_states, key_states, value_states, attn_mask=attention_mask)

    attn_output = attn_output.transpose(1, 2).contiguous()
    attn_output = attn_output.reshape(bsz, q_len, self.hidden_size)

    attn_output = self.o_proj(attn_output)

    # Due to the implementation of the PyTorch version of flash attention,
    # even when the output_attentions flag is set to True, it is not possible
    # to return the attn_weights.
    return attn_output, None, past_key_value