AttentionProjection =================== Layer that computes multi-head projection for dot-product attention. **Abstract Signature:** ``AttentionProjection(input_dim: int, num_heads: int, dim_per_head: int, is_output: bool = False)`` .. raw:: html

PyTorch

API: torch.nn.Linear
Strategy: Direct Mapping

Flax NNX

API: flax.nnx.Linear
Strategy: Direct Mapping

PaxML / Praxis

API: praxis.layers.AttentionProjection
Strategy: Direct Mapping