flag_use_half_precision=True but uses float32

[TZYSJTU]

Hi，in the function warp_decode(), why is the value set to float32 when flag_use_half_precision=True?

            # float the dict
            if self.inference_cfg.flag_use_half_precision:
                for k, v in ret_dct.items():
                    if isinstance(v, torch.Tensor):
                        ret_dct[k] = v.float()