# Copyright (c) 2025 ByteDance Ltd. and/or its affiliates
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

# Modified from: https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/vision_transformer.py#L103-L110 # noqa

from typing import Callable, Optional, Union
import torch
import torch.nn.functional as F
from torch import Tensor, nn


class Attention(nn.Module):
    def __init__(
        self,
        dim: int,
        num_heads: int = 8,
        qkv_bias: bool = True,
        proj_bias: bool = True,
        attn_drop: float = 0.0,
        proj_drop: float = 0.0,
        norm_layer: nn.Module = nn.LayerNorm,
        qk_norm: bool = False,
        rope=None,
    ) -> None:
        super().__init__()
        assert dim % num_heads == 0, "dim should be divisible by num_heads"
        self.num_heads = num_heads
        self.head_dim = dim // num_heads
        self.scale = self.head_dim**-0.5
        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
        self.q_norm = norm_layer(self.head_dim) if qk_norm else nn.Identity()
        self.k_norm = norm_layer(self.head_dim) if qk_norm else nn.Identity()
        self.attn_drop = nn.Dropout(attn_drop)
        self.proj = nn.Linear(dim, dim, bias=proj_bias)
        self.proj_drop = nn.Dropout(proj_drop)
        self.rope = rope

    def forward(self, x: Tensor, pos=None, attn_mask=None) -> Tensor:
        # Debug breakpoint removed for production
        B, N, C = x.shape
        qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, self.head_dim).permute(2, 0, 3, 1, 4)
        q, k, v = qkv.unbind(0)
        q, k = self.q_norm(q), self.k_norm(k)
        q = self.rope(q, pos) if self.rope is not None else q
        k = self.rope(k, pos) if self.rope is not None else k
        x = F.scaled_dot_product_attention(
            q,
            k,
            v,
            dropout_p=self.attn_drop.p if self.training else 0.0,
            attn_mask=attn_mask,
        )
        x = x.transpose(1, 2).reshape(B, N, C)
        x = self.proj(x)
        x = self.proj_drop(x)
        return x


class LayerScale(nn.Module):
    def __init__(
        self,
        dim: int,
        init_values: Union[float, Tensor] = 1e-5,
        inplace: bool = False,
    ) -> None:
        super().__init__()
        self.inplace = inplace
        self.gamma = nn.Parameter(init_values * torch.ones(dim))

    def forward(self, x: Tensor) -> Tensor:
        return x.mul_(self.gamma) if self.inplace else x * self.gamma


class Mlp(nn.Module):
    def __init__(
        self,
        in_features: int,
        hidden_features: Optional[int] = None,
        out_features: Optional[int] = None,
        act_layer: Callable[..., nn.Module] = nn.GELU,
        drop: float = 0.0,
        bias: bool = True,
    ) -> None:
        super().__init__()
        out_features = out_features or in_features
        hidden_features = hidden_features or in_features
        self.fc1 = nn.Linear(in_features, hidden_features, bias=bias)
        self.act = act_layer()
        self.fc2 = nn.Linear(hidden_features, out_features, bias=bias)
        self.drop = nn.Dropout(drop)

    def forward(self, x: Tensor) -> Tensor:
        x = self.fc1(x)
        x = self.act(x)
        x = self.drop(x)
        x = self.fc2(x)
        x = self.drop(x)
        return x