fix 0-dim tensor.fill_

[Flowingsun007]

fix了tensor.fill_(scalar)报错的问题，示例：

>>> import oneflow as flow
>>> x = flow.zeros(())
>>> x
tensor(0., dtype=oneflow.float32)
>>> x.fill_(1)
>>> x
tensor(1., dtype=oneflow.float32)

[github-actions]

Speed stats:

GPU Name: GeForce GTX 1080 

PyTorch resnet50 time: 140.3ms (= 7012.8ms / 50, input_shape=[16, 3, 224, 224], backward is enabled)
OneFlow resnet50 time: 127.9ms (= 6394.0ms / 50, input_shape=[16, 3, 224, 224], backward is enabled)
Relative speed: 1.10 (= 140.3ms / 127.9ms)

PyTorch resnet50 time: 84.4ms (= 4221.5ms / 50, input_shape=[8, 3, 224, 224], backward is enabled)
OneFlow resnet50 time: 74.3ms (= 3716.7ms / 50, input_shape=[8, 3, 224, 224], backward is enabled)
Relative speed: 1.14 (= 84.4ms / 74.3ms)

PyTorch resnet50 time: 57.0ms (= 2850.0ms / 50, input_shape=[4, 3, 224, 224], backward is enabled)
OneFlow resnet50 time: 47.5ms (= 2374.8ms / 50, input_shape=[4, 3, 224, 224], backward is enabled)
Relative speed: 1.20 (= 57.0ms / 47.5ms)

PyTorch resnet50 time: 49.0ms (= 2448.4ms / 50, input_shape=[2, 3, 224, 224], backward is enabled)
OneFlow resnet50 time: 39.8ms (= 1992.4ms / 50, input_shape=[2, 3, 224, 224], backward is enabled)
Relative speed: 1.23 (= 49.0ms / 39.8ms)

PyTorch resnet50 time: 43.6ms (= 2180.8ms / 50, input_shape=[1, 3, 224, 224], backward is enabled)
OneFlow resnet50 time: 40.1ms (= 2002.9ms / 50, input_shape=[1, 3, 224, 224], backward is enabled)
Relative speed: 1.09 (= 43.6ms / 40.1ms)

[github-actions]

Speed stats:

GPU Name: GeForce GTX 1080 

PyTorch resnet50 time: 142.5ms (= 7126.9ms / 50, input_shape=[16, 3, 224, 224], backward is enabled)
OneFlow resnet50 time: 128.5ms (= 6423.0ms / 50, input_shape=[16, 3, 224, 224], backward is enabled)
Relative speed: 1.11 (= 142.5ms / 128.5ms)

PyTorch resnet50 time: 82.6ms (= 4129.7ms / 50, input_shape=[8, 3, 224, 224], backward is enabled)
OneFlow resnet50 time: 74.5ms (= 3723.0ms / 50, input_shape=[8, 3, 224, 224], backward is enabled)
Relative speed: 1.11 (= 82.6ms / 74.5ms)

PyTorch resnet50 time: 57.9ms (= 2893.7ms / 50, input_shape=[4, 3, 224, 224], backward is enabled)
OneFlow resnet50 time: 47.8ms (= 2388.2ms / 50, input_shape=[4, 3, 224, 224], backward is enabled)
Relative speed: 1.21 (= 57.9ms / 47.8ms)

PyTorch resnet50 time: 47.6ms (= 2377.9ms / 50, input_shape=[2, 3, 224, 224], backward is enabled)
OneFlow resnet50 time: 46.2ms (= 2311.5ms / 50, input_shape=[2, 3, 224, 224], backward is enabled)
Relative speed: 1.03 (= 47.6ms / 46.2ms)

PyTorch resnet50 time: 44.3ms (= 2213.6ms / 50, input_shape=[1, 3, 224, 224], backward is enabled)
OneFlow resnet50 time: 40.7ms (= 2036.9ms / 50, input_shape=[1, 3, 224, 224], backward is enabled)
Relative speed: 1.09 (= 44.3ms / 40.7ms)