ppd/models/attention.py

import torch
import torch.nn as nn
import torch.nn.functional as F

class Attention(nn.Module):

    def __init__(
            self,
            dim: int,
            num_heads: int = 8,
            qkv_bias: bool = False,
            qk_norm: bool = False,
            rope=None,
            fused_attn: bool = True,  # use F.scaled_dot_product_attention or not
            attn_drop: float = 0.,
            proj_drop: float = 0.,
            norm_layer: nn.Module = nn.LayerNorm,
    ) -> 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.fused_attn = fused_attn

        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)
        self.proj_drop = nn.Dropout(proj_drop)
        self.rope = rope

    def forward(self, x: torch.Tensor, pos=None) -> torch.Tensor:
        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)

        if self.rope is not None:
            q = self.rope(q, pos)
            k = self.rope(k, pos)

        if self.fused_attn:
            x = F.scaled_dot_product_attention(
                q, k, v,
                dropout_p=self.attn_drop.p if self.training else 0.,
            )
        else:
            q = q * self.scale
            attn = q @ k.transpose(-2, -1)
            attn = attn.softmax(dim=-1)
            attn = self.attn_drop(attn)
            x = attn @ v

        x = x.transpose(1, 2).reshape(B, N, C)
        x = self.proj(x)
        x = self.proj_drop(x)
        return x