point_e/models/perceiver.py [62:67]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        weight = torch.einsum(
            "bthc,bshc->bhts", q * scale, k * scale
        )  # More stable with f16 than dividing afterwards
        wdtype = weight.dtype
        weight = torch.softmax(weight.float(), dim=-1).type(wdtype)
        return torch.einsum("bhts,bshc->bthc", weight, v).reshape(bs, n_ctx, -1)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



point_e/models/transformer.py [79:84]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        weight = torch.einsum(
            "bthc,bshc->bhts", q * scale, k * scale
        )  # More stable with f16 than dividing afterwards
        wdtype = weight.dtype
        weight = torch.softmax(weight.float(), dim=-1).type(wdtype)
        return torch.einsum("bhts,bshc->bthc", weight, v).reshape(bs, n_ctx, -1)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -