## aten.slice, aten.select, aten.expand - **Function Schema**: - `torch.ops.aten.expand.default: ((torch.int64,), {})` - `torch.ops.aten.slice.Tensor: ((torch.float32,), {})` - `torch.ops.aten.slice.Tensor: ((torch.int32,), {})` - `torch.ops.aten.slice.Tensor: ((torch.float32,), {})` - `torch.ops.aten.slice.Tensor: ((torch.int32,), {})` - `torch.ops.aten.select.int: ((torch.float32,), {})` - **Original PyTorch API**: `torch.expand`, `torch.slice`, `torch.select` - **Relevant TensorRT Documentation**: [IGatherLayer](https://docs.nvidia.com/deeplearning/tensorrt/api/python_api/infer/Graph/Layers.html?highlight=igather#igatherlayer), [IShuffleLayer](https://docs.nvidia.com/deeplearning/tensorrt/api/python_api/infer/Graph/Layers.html?highlight=ishuffle#ishufflelayer) Add support for `slice`, `select`, and `expand` as [aten converters](https://github.com/pytorch/TensorRT/blob/main/py/torch_tensorrt/fx/converters/aten_ops_converters.py).