# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project

import torch
import torch.nn as nn

from vllm_omni.diffusion.attention.backends.abstract import (
    AttentionMetadata,
)
from vllm_omni.diffusion.attention.selector import get_attn_backend


class Attention(nn.Module):
    def __init__(
        self,
        num_heads: int,
        head_size: int,
        causal: bool,
        softmax_scale: float,
        num_kv_heads: int | None = None,
        prefix: str = "",
    ):
        super().__init__()
        self.attn_backend = get_attn_backend(-1)
        self.attn_impl_cls = self.attn_backend.get_impl_cls()
        self.attention = self.attn_impl_cls(
            num_heads=num_heads,
            head_size=head_size,
            softmax_scale=softmax_scale,
            causal=causal,
            num_kv_heads=num_kv_heads,
        )

    def forward(
        self,
        query: torch.Tensor,
        key: torch.Tensor,
        value: torch.Tensor,
        attn_metadata: AttentionMetadata = None,
    ) -> torch.Tensor:
        # shape: (batch_size, seq_len, num_heads, head_size)
        attn_output = self.attention.forward(query, key, value, attn_metadata)
        return attn_output