当前Qwen、Llama等系列RMSNorm实现源码均一致。具体现实如下：

class RMSNorm(nn.Module):def __init__(self, hidden_size, eps=1e-6):super().__init__()self.weight = nn.Parameter(torch.ones(hidden_size))self.variance_epsilon = epsdef forward(self, hidden_states):input_dtype = hidden_states.dtypehidden_states = hidden_states.to(torch.float32)variance = hidden_states.pow(2).mean(-1, keepdim=True)hidden_states = hidden_states * torch.rsqrt(variance + self.variance_epsilon)return self.weight * hidden_states.to(input_dtype)

源码链接