layernorm.py

# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import torch
from torch import Tensor

from ..op import register_op


@register_op
def rms_norm(
    x: Tensor, weight: Tensor | None, epsilon: float, variance_size: int | None = None
) -> Tensor:
    """Weighted root-mean-square layer normalization"""
    orig_dtype = x.dtype
    x = x.to(torch.float32)
    x_var = x if variance_size is None else x[..., :variance_size]
    variance = x_var.pow(2).mean(dim=-1, keepdim=True)
    x = x * torch.rsqrt(variance + epsilon)
    if weight is not None:
        x = x.to(weight.dtype) * weight
    return x.to(orig_dtype)