inferentia neuron core usage is only 1 when 4 cores are available

Im using the following code to load a neuron compiled model for inference. However on my inf1.2xlarge instance, neuron-top shows for cores (NC0 to NC3). Only NC0 gets used in inference. How do I increase throughput by using all cores???

from transformers import BertTokenizer, BertModel
import torch
import torch_neuron
import os.path
import os

os.environ['NEURON_RT_NUM_CORES']=str(4)
fname = 'modelneuron.pt'
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
inputs = tokenizer("Hello, my dog is cute and big", return_tensors="pt")
if not os.path.isfile(fname):

    model = BertModel.from_pretrained('bert-base-uncased', return_dict=False)

    neuron_model = torch_neuron.trace(model,
                                    example_inputs = (inputs['input_ids'],inputs['attention_mask']))
    neuron_model.save("modelneuron.pt")
    print('saved neuron model')
else:
    neuron_model = torch.jit.load('modelneuron.pt')
    print('loaded neuron model')

for i in range(10000):
    outputs = neuron_model(*(inputs['input_ids'],inputs['attention_mask']))

print(outputs)