src/peft/tuners/lora/model.py [246:285]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def _replace_module(self, parent, child_name, new_module, child):
        setattr(parent, child_name, new_module)
        # It's not necessary to set requires_grad here, as that is handled by
        # _mark_only_adapters_as_trainable

        # child layer wraps the original module, unpack it
        if hasattr(child, "base_layer"):
            child = child.base_layer

        meta = torch.device("meta")
        # dispatch to correct device
        for name, module in new_module.named_modules():
            if (self.prefix in name) or ("ranknum" in name):
                if hasattr(child, "qweight"):
                    weight = child.qweight
                elif hasattr(child, "W_q"):
                    weight = child.W_q
                elif hasattr(child, "weight"):
                    weight = child.weight
                elif getattr(child, "in_proj_weight", None) is not None:  # MHA
                    weight = child.in_proj_weight
                else:
                    weight = next(child.parameters())
                if not any(p.device == meta for p in module.parameters()):
                    module.to(weight.device)

    def _mark_only_adapters_as_trainable(self, model: nn.Module) -> None:
        for n, p in model.named_parameters():
            if self.prefix not in n:
                p.requires_grad = False

        for active_adapter in self.active_adapters:
            bias = self.peft_config[active_adapter].bias
            if bias == "none":
                continue

            if bias == "all":
                for n, p in model.named_parameters():
                    if "bias" in n:
                        p.requires_grad = True
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/peft/tuners/oft/model.py [180:219]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def _replace_module(self, parent, child_name, new_module, child):
        setattr(parent, child_name, new_module)
        # It's not necessary to set requires_grad here, as that is handled by
        # _mark_only_adapters_as_trainable

        # child layer wraps the original module, unpack it
        if hasattr(child, "base_layer"):
            child = child.base_layer

        meta = torch.device("meta")
        # dispatch to correct device
        for name, module in new_module.named_modules():
            if (self.prefix in name) or ("ranknum" in name):
                if hasattr(child, "qweight"):
                    weight = child.qweight
                elif hasattr(child, "W_q"):
                    weight = child.W_q
                elif hasattr(child, "weight"):
                    weight = child.weight
                elif getattr(child, "in_proj_weight", None) is not None:  # MHA
                    weight = child.in_proj_weight
                else:
                    weight = next(child.parameters())
                if not any(p.device == meta for p in module.parameters()):
                    module.to(weight.device)

    def _mark_only_adapters_as_trainable(self, model: nn.Module) -> None:
        for n, p in model.named_parameters():
            if self.prefix not in n:
                p.requires_grad = False

        for active_adapter in self.active_adapters:
            bias = self.peft_config[active_adapter].bias
            if bias == "none":
                continue

            if bias == "all":
                for n, p in model.named_parameters():
                    if "bias" in n:
                        p.requires_grad = True
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -