DecoderAttention

 Graphs in : cluster, ONNX model architecture.

query – T : object, 3D input tensor with shape (sequence_length, batch_size, hidden_size), hidden_size = num_heads * head_size.
key – T : object, 3D input tensor with shape (total_sequence_length, batch_size, hidden_size).
q_weight – T : object, 2D input tensor with shape (hidden_size, hidden_size).
kv_weight – T : object, 2D input tensor with shape (hidden_size, 2 * hidden_size).
bias – T : object, 2D input tensor with shape (hidden_size, 2 * hidden_size).
key_padding_mask (optional) – B : object, 2D input tensor with shape (batch_size, total_sequence_length).
key_cache (optional) – T : object, input tensor with shape (batch_size, num_heads, sequence_length or total_sequence_length, head_size).
value_cache (optional) – T : object, input tensor with shape (batch_size, num_heads, sequence_length or total_sequence_length, head_size).
static_kv – B : object, if static_kv = true, cross-attention; else self-attention.
use_past – B : object, if use_past = true, use cache; else no cache.
has_layer_state – B : object, if has_layer_state = true, layer_state = {} or [a,b]; else layer_state = None.
has_key_padding_mask – B : object, has_key_padding_mask or not.

 Parameters : cluster,

mask_filter_value : float, the value to be filled in the attention mask. 
Default value “-10000”.
num_heads : integer, number of attention heads.
Default value “0”.
 training? : boolean, whether the layer is in training mode (can store data for backward).
Default value “True”.
 lda coeff : float, defines the coefficient by which the loss derivative will be multiplied before being sent to the previous layer (since during the backward run we go backwards).
Default value “1”.

 name (optional) : string, name of the node.

 Graphs out : cluster, ONNX model architecture.

output – T : object, 3D output tensor with shape (sequence_length, batch_size, hidden_size).
new_key_cache (optional) – T : object, output tensor with shape (batch_size, num_heads, new sequence_length, head_size).
new_value_cache (optional) – T : object, output tensor with shape (batch_size, num_heads, new sequence_length, head_size).