[BugFix] GPT inference error when pipeline_para_size > 1 and int8_mode != 0

[00why00]

The problem is caused by the empty tensor check in quant ops in

FasterTransformer/examples/pytorch/gpt/utils/gpt.py

Lines 46 to 47 in f8e42aa

	quant = torch.ops.fastertransformer.symmetric_quantize_last_axis_of_batched_matrix
	self.weight_transpose_calibrate_quantize = lambda x: quant(x, torch.int8)

When pipeline_para_size > 1, the current rank does not load the weights of all layers, resulting in quantization errors, and it is necessary to add is_load() check when traversing layers