AdditiveAttention

Additive attention layer, a.k.a. Bahdanau-style attention.

Abstract Signature:

AdditiveAttention(use_scale: bool = True, dropout: float = 0.0)

PyTorchJAX (Core)KerasTensorFlowApple MLXFlax NNXPaxML / Praxis

PyTorch

API: —

Strategy: Custom / Partial

JAX (Core)

API: —

Strategy: Custom / Partial

Keras

API: keras.layers.AdditiveAttention

Strategy: Direct Mapping

Official Docs ↗

TensorFlow

API: tf.keras.layers.AdditiveAttention

Strategy: Direct Mapping

Official Docs ↗

Apple MLX

API: —

Strategy: Custom / Partial

Flax NNX

API: flax.linen.attention.dot_product_attention

Strategy: Direct Mapping

Official Docs ↗

PaxML / Praxis

API: —

Strategy: Custom / Partial