fairseq/modules/masked_multihead_attention.py [58:171]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - if incremental_state is not None: saved_state = self._get_input_buffer(incremental_state) if 'prev_key' in saved_state: # previous time steps are cached - no need to recompute # key and value if they are static if static_kv: assert self.encoder_decoder_attention and not self.self_attention key = value = None else: saved_state = None if self.self_attention: # self-attention q, k, v = self.in_proj_qkv(query) #elif masked_attn is not None: # q = self.in_proj_q(query) # k, v = self.in_proj_kv(key) elif self.encoder_decoder_attention: # encoder-decoder attention q = self.in_proj_q(query) if key is None: assert value is None k = v = None else: k = self.in_proj_k(key) v = self.in_proj_v(key) else: q = self.in_proj_q(query) k = self.in_proj_k(key) v = self.in_proj_v(value) q *= self.scaling if self.bias_k is not None: assert self.bias_v is not None k = torch.cat([k, self.bias_k.repeat(1, bsz, 1)]) v = torch.cat([v, self.bias_v.repeat(1, bsz, 1)]) if attn_mask is not None: attn_mask = torch.cat([attn_mask, attn_mask.new_zeros(attn_mask.size(0), 1)], dim=1) if key_padding_mask is not None: key_padding_mask = torch.cat( [key_padding_mask, key_padding_mask.new_zeros(key_padding_mask.size(0), 1)], dim=1) q = q.contiguous().view(tgt_len, bsz * self.num_heads, self.head_dim).transpose(0, 1) if k is not None: k = k.contiguous().view(-1, bsz * self.num_heads, self.head_dim).transpose(0, 1) if v is not None: v = v.contiguous().view(-1, bsz * self.num_heads, self.head_dim).transpose(0, 1) if saved_state is not None: # saved states are stored with shape (bsz, num_heads, seq_len, head_dim) if 'prev_key' in saved_state: prev_key = saved_state['prev_key'].view(bsz * self.num_heads, -1, self.head_dim) if static_kv: k = prev_key else: k = torch.cat((prev_key, k), dim=1) if 'prev_value' in saved_state: prev_value = saved_state['prev_value'].view(bsz * self.num_heads, -1, self.head_dim) if static_kv: v = prev_value else: v = torch.cat((prev_value, v), dim=1) saved_state['prev_key'] = k.view(bsz, self.num_heads, -1, self.head_dim) saved_state['prev_value'] = v.view(bsz, self.num_heads, -1, self.head_dim) self._set_input_buffer(incremental_state, saved_state) src_len = k.size(1) # This is part of a workaround to get around fork/join parallelism # not supporting Optional types. if key_padding_mask is not None and key_padding_mask.shape == torch.Size([]): key_padding_mask = None if key_padding_mask is not None: assert key_padding_mask.size(0) == bsz assert key_padding_mask.size(1) == src_len if self.add_zero_attn: src_len += 1 k = torch.cat([k, k.new_zeros((k.size(0), 1) + k.size()[2:])], dim=1) v = torch.cat([v, v.new_zeros((v.size(0), 1) + v.size()[2:])], dim=1) if attn_mask is not None: attn_mask = torch.cat([attn_mask, attn_mask.new_zeros(attn_mask.size(0), 1)], dim=1) if key_padding_mask is not None: key_padding_mask = torch.cat( [key_padding_mask, torch.zeros(key_padding_mask.size(0), 1).type_as(key_padding_mask)], dim=1) attn_weights = torch.bmm(q, k.transpose(1, 2)) attn_weights = self.apply_sparse_mask(attn_weights, tgt_len, src_len, bsz) assert list(attn_weights.size()) == [bsz * self.num_heads, tgt_len, src_len] if attn_mask is not None: attn_mask = attn_mask.unsqueeze(0) if self.onnx_trace: attn_mask = attn_mask.repeat(attn_weights.size(0), 1, 1) attn_weights += attn_mask if key_padding_mask is not None: # don't attend to padding symbols attn_weights = attn_weights.view(bsz, self.num_heads, tgt_len, src_len) if self.onnx_trace: attn_weights = torch.where( key_padding_mask.unsqueeze(1).unsqueeze(2), torch.Tensor([float("-Inf")]), attn_weights.float() ).type_as(attn_weights) else: attn_weights = attn_weights.masked_fill( key_padding_mask.unsqueeze(1).unsqueeze(2), float('-inf'), ) attn_weights = attn_weights.view(bsz * self.num_heads, tgt_len, src_len) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - fairseq/modules/multihead_attention.py [131:242]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - if incremental_state is not None: saved_state = self._get_input_buffer(incremental_state) if 'prev_key' in saved_state: # previous time steps are cached - no need to recompute # key and value if they are static if static_kv: assert self.encoder_decoder_attention and not self.self_attention key = value = None else: saved_state = None if self.self_attention: # self-attention q, k, v = self.in_proj_qkv(query) elif self.encoder_decoder_attention: # encoder-decoder attention q = self.in_proj_q(query) if key is None: assert value is None k = v = None else: k = self.in_proj_k(key) v = self.in_proj_v(key) else: q = self.in_proj_q(query) k = self.in_proj_k(key) v = self.in_proj_v(value) q *= self.scaling if self.bias_k is not None: assert self.bias_v is not None k = torch.cat([k, self.bias_k.repeat(1, bsz, 1)]) v = torch.cat([v, self.bias_v.repeat(1, bsz, 1)]) if attn_mask is not None: attn_mask = torch.cat([attn_mask, attn_mask.new_zeros(attn_mask.size(0), 1)], dim=1) if key_padding_mask is not None: key_padding_mask = torch.cat( [key_padding_mask, key_padding_mask.new_zeros(key_padding_mask.size(0), 1)], dim=1) q = q.contiguous().view(tgt_len, bsz * self.num_heads, self.head_dim).transpose(0, 1) if k is not None: k = k.contiguous().view(-1, bsz * self.num_heads, self.head_dim).transpose(0, 1) if v is not None: v = v.contiguous().view(-1, bsz * self.num_heads, self.head_dim).transpose(0, 1) if saved_state is not None: # saved states are stored with shape (bsz, num_heads, seq_len, head_dim) if 'prev_key' in saved_state: prev_key = saved_state['prev_key'].view(bsz * self.num_heads, -1, self.head_dim) if static_kv: k = prev_key else: k = torch.cat((prev_key, k), dim=1) if 'prev_value' in saved_state: prev_value = saved_state['prev_value'].view(bsz * self.num_heads, -1, self.head_dim) if static_kv: v = prev_value else: v = torch.cat((prev_value, v), dim=1) saved_state['prev_key'] = k.view(bsz, self.num_heads, -1, self.head_dim) saved_state['prev_value'] = v.view(bsz, self.num_heads, -1, self.head_dim) self._set_input_buffer(incremental_state, saved_state) src_len = k.size(1) # This is part of a workaround to get around fork/join parallelism # not supporting Optional types. if key_padding_mask is not None and key_padding_mask.shape == torch.Size([]): key_padding_mask = None if key_padding_mask is not None: assert key_padding_mask.size(0) == bsz assert key_padding_mask.size(1) == src_len if self.add_zero_attn: src_len += 1 k = torch.cat([k, k.new_zeros((k.size(0), 1) + k.size()[2:])], dim=1) v = torch.cat([v, v.new_zeros((v.size(0), 1) + v.size()[2:])], dim=1) if attn_mask is not None: attn_mask = torch.cat([attn_mask, attn_mask.new_zeros(attn_mask.size(0), 1)], dim=1) if key_padding_mask is not None: key_padding_mask = torch.cat( [key_padding_mask, torch.zeros(key_padding_mask.size(0), 1).type_as(key_padding_mask)], dim=1) attn_weights = torch.bmm(q, k.transpose(1, 2)) attn_weights = self.apply_sparse_mask(attn_weights, tgt_len, src_len, bsz) assert list(attn_weights.size()) == [bsz * self.num_heads, tgt_len, src_len] if attn_mask is not None: attn_mask = attn_mask.unsqueeze(0) if self.onnx_trace: attn_mask = attn_mask.repeat(attn_weights.size(0), 1, 1) attn_weights += attn_mask if key_padding_mask is not None: # don't attend to padding symbols attn_weights = attn_weights.view(bsz, self.num_heads, tgt_len, src_len) if self.onnx_trace: attn_weights = torch.where( key_padding_mask.unsqueeze(1).unsqueeze(2), torch.Tensor([float("-Inf")]), attn_weights.float() ).type_as(attn_weights) else: attn_weights = attn_weights.masked_fill( key_padding_mask.unsqueeze(1).unsqueeze(2), float('-inf'), ) attn_weights = attn_weights.view(bsz * self.num_heads, tgt_len, src_len) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -