Issue description

EmbeddingBag raises a RuntimeError if its weights are on the GPU, but the input is on the CPU.

Code example

import torch
bow = torch.nn.EmbeddingBag(10, 10).cuda()
test = torch.tensor([[1, 2]], dtype=torch.long).cpu()
bow(test)

Result: RuntimeError: get_device is not implemented for type torch.LongTensor
Expected result: a more informative error about device mismatch

System Info

PyTorch version: 0.4.0
Is debug build: No
CUDA used to build PyTorch: 9.0.176

OS: Ubuntu 16.04.3 LTS
GCC version: (Ubuntu 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609
CMake version: version 3.5.1

Python version: 3.6
Is CUDA available: Yes
CUDA runtime version: Could not collect
GPU models and configuration:
GPU 0: Quadro GP100
GPU 1: Quadro GP100

Nvidia driver version: 384.81
cuDNN version: Could not collect

Versions of relevant libraries:
[pip] numpy (1.14.3)
[pip] torch (0.4.0)
[pip] torchvision (0.2.1)
[conda] cuda90 1.0 h6433d27_0 pytorch
[conda] pytorch 0.4.0 py36_cuda9.0.176_cudnn7.1.2_1 [cuda90] pytorch
[conda] torchvision 0.2.1 py36_1 pytorch