Apply learned per-feature RMSNorm gains

Read the equation

After RMS scaling, multiply each component by its learned gain and restore the earlier input dtype. The gain allows the model to choose different output scales by feature; it does not add a learned bias in this expression.

Terms & definitions

The recovered passage does not supply a separate symbol table. Read the source context for the notation used in this version; familiar letters may carry different meanings in other builds.

How it works

Read the definition from its right-hand expression to the quantity on the left. Its surrounding source records the intended input, state, or parameter context. Where the source leaves an operation unspecified, this page preserves that gap.

Assumptions & limits

Source recovery establishes that the expression appears in this record. Its mathematical validity, implementation behavior, and interpretation must be assessed separately. See the linked source and research notes for the checks available for this version.

Original context

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)


ALL_LAYERNORM_LAYERS.append(DeepseekV3RMSNorm)

return self.weight * hidden_states.to(input_dtype)

Related builds