nki.language.softplus — AWS Neuron Documentation (original) (raw)

This document is relevant for: Inf2, Trn1, Trn2

nki.language.softplus#

nki.language.softplus(x, *, dtype=None, mask=None, **kwargs)[source]#

Softplus activation function on the input, element-wise.

Softplus is a smooth approximation to the ReLU activation, defined as:

softplus(x) = log(1 + exp(x))

Parameters:

• x – a tile.
• dtype – (optional) data type to cast the output type to (see Supported Data Types for more information); if not specified, it will default to be the same as the data type of the input tile.
• mask – (optional) a compile-time constant predicate that controls whether/how this instruction is executed (see NKI API Masking for details)

Returns:

a tile that has softplus of x.

This document is relevant for: Inf2, Trn1, Trn2