Skip to main content

Python module

identity

Identity layer that passes through input unchanged.

Identity

class max.nn.identity.Identity

Identity layer that passes through input unchanged.

This layer is useful for skipping certain operations (like normalization) in specific architectures such as EAGLE speculative decoding, where the draft model receives already-normalized hidden states from the target model.

Example:

>>> from max.nn import Identity
>>> identity = Identity()
>>> # In graph construction:
>>> output = identity(input_tensor)  # output == input_tensor

Was this page helpful?