layernorm.py

"""Custom normalization layers."""
from typing import Optional, Tuple, Union

import torch
import torch.nn as nn

from vllm import layernorm_ops


class RMSNorm(nn.Module):
    """Root mean square normalization.

    Computes x -> w * x / sqrt(E[x^2] + eps) where w is the learned weight.
    Refer to https://arxiv.org/abs/1910.07467
    """

    def __init__(
        self,
        hidden_size: int,
        eps: float = 1e-6,
    ) -> None:
        super().__init__()
        self.weight = nn.Parameter(torch.ones(hidden_size))
        self.variance_epsilon = eps

    def forward(
        self,
        x: torch.Tensor,
        residual: Optional[torch.Tensor] = None,
    ) -> Union[torch.Tensor, Tuple[torch.Tensor, torch.Tensor]]:
        if residual is not None:
            layernorm_ops.fused_add_rms_norm(
                x,
                residual,
                self.weight.data,
                self.variance_epsilon,
            )
            return x, residual
        out = torch.empty_like(x)
        layernorm_ops.rms_norm(
            out,
            x,
            self.weight.data,
            self.variance_epsilon,
        )
        return out