AttributeError: Module has no function 'tvm.graph_runtime.remote_create'

Questions
#1

I tried running the tvm example for Raspberry Pi (https://docs.tvm.ai/tutorials/frontend/deploy_model_on_rasp.html#tutorial-deploy-model-on-rasp). However I am getting the following error. Any help would be appreciated. I have pasted the output of the example below.

File /root/.tvm_test_data/data/cat.png exists, skip.
File /root/.tvm_test_data/data/imagenet1000_clsid_to_human.txt exists, skip.
Cannot find config for target=llvm -device=arm_cpu -model=llvm -target=arm-linux-gnueabihf, workload=('dense', (1, 512, 'float32'), (1000, 512, 'float32'), 0, 'float32'). A fallback configuration is used, which may bring great performance regression.
Traceback (most recent call last):

  File "RpiDemo.py", line 86, in <module>
    module = graph_runtime.create(graph, rlib, ctx)

  File "/usr/tvm/python/tvm/contrib/graph_runtime.py", line 55, in create
    fcreate = ctx[0]._rpc_sess.get_function("tvm.graph_runtime.remote_create")

  File "/usr/tvm/python/tvm/rpc/client.py", line 57, in get_function
    return self._sess.get_function(name)

  File "/usr/tvm/python/tvm/_ffi/function.py", line 122, in get_function
    "Module has no function '%s'" %  name)

AttributeError: Module has no function 'tvm.graph_runtime.remote_create'
#2

This error is due to incompatibility in remote device runtime and host machine tvm build, recently graph_runtime.remote_create() is removed. So try to have same code version both in host and device. I had solved this error in this way.