Retinaface + Webface_600K

Hello guys,
I am trying to get a FRS pipeline with Retinaface + Webface_600k from [here](https://github.com/deepinsight/insightface/tree/master/model_zoo#:~:text=GDrive-,WebFace600K,-90.566) . I am having trouble in running the Retinaface model along with Webface_600k. Is it possible to run them together in specicif mxnet versions. The errors am getting are related to the Retinaface model ,

`[11:16:09] ../src/nnvm/legacy_json_util.cc:208: Loading symbol saved by previous version v1.3.0. Attempting to upgrade...
[11:16:09] ../src/nnvm/legacy_json_util.cc:216: Symbol successfully upgraded!
[11:16:09] ../src/storage/storage.cc:196: Using Pooled (Naive) StorageManager for CPU
means [0. 0. 0.]
use_landmarks True
cascade 0
sym size: 9
Traceback (most recent call last):
File "/opt/mxnet/python/mxnet/symbol/symbol.py", line 1872, in simple_bind
check_call(executor(self.handle,
File "/opt/mxnet/python/mxnet/base.py", line 246, in check_call
raise get_last_ffi_error()
mxnet.base.MXNetError: Traceback (most recent call last):
File "../src/storage/././storage_manager_helpers.h", line 129
Error: cudaMemGetInfo fails the provided PTX was compiled with an unsupported toolchain.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "", line 1, in
File "/home/frsOnboarding/insightface/RetinaFace/retinaface.py", line 158, in __init__
self.model.bind(data_shapes=[('data', (1, 3, image_size[0], image_size[1]))], for_training=False)
File "/opt/mxnet/python/mxnet/module/module.py", line 411, in bind
self._exec_group = DataParallelExecutorGroup(self._symbol, self._context,
File "/opt/mxnet/python/mxnet/module/executor_group.py", line 280, in __init__
self.bind_exec(data_shapes, label_shapes, shared_group)
File "/opt/mxnet/python/mxnet/module/executor_group.py", line 383, in bind_exec
self.execs.append(self._bind_ith_exec(i, data_shapes_i, label_shapes_i,
File "/opt/mxnet/python/mxnet/module/executor_group.py", line 700, in _bind_ith_exec
executor = self.symbol.simple_bind(ctx=context, grad_req=self.grad_req,
File "/opt/mxnet/python/mxnet/symbol/symbol.py", line 1911, in simple_bind
raise RuntimeError(error_msg)
RuntimeError: simple_bind error. Arguments:
data: (1, 3, 640, 640)
Traceback (most recent call last):
File "../src/storage/././storage_manager_helpers.h", line 129
Error: cudaMemGetInfo fails the provided PTX was compiled with an unsupported toolchain.`

regards
akirs