Function add_residual

vggt/layers/block.py:136–145

(x, brange, residual, residual_scale_factor, scaling_vector=None)

def add_residual(x, brange, residual, residual_scale_factor, scaling_vector=None):
    if scaling_vector is None:
        x_flat = x.flatten(1)
        residual = residual.flatten(1)
        x_plus_residual = torch.index_add(x_flat, 0, brange, residual.to(dtype=x.dtype), alpha=residual_scale_factor)
    else:
        x_plus_residual = scaled_index_add(
            x, brange, residual.to(dtype=x.dtype), scaling=scaling_vector, alpha=residual_scale_factor
        )
    return x_plus_residual


attn_bias_cache: Dict[Tuple, Any] = {}