Method apply

tensorrt_llm/_torch/modules/linear.py:307–309

(self, module: Linear, input: torch.Tensor,
              bias: Optional[torch.Tensor], *args, **kwargs)

    @abstractmethod
    def apply(self, module: Linear, input: torch.Tensor,
              bias: Optional[torch.Tensor], *args, **kwargs):
        raise NotImplementedError

    def apply_linear_allreduce(self, module: Linear, input: torch.Tensor,
                               bias: Optional[torch.Tensor], tp_rank: int,