diff --git a/.github/workflows/smoke_test_cross_device_mnn_server_win.yml b/.github/workflows/smoke_test_cross_device_mnn_server_win.yml
deleted file mode 100644
index b38a1831d5..0000000000
--- a/.github/workflows/smoke_test_cross_device_mnn_server_win.yml
+++ /dev/null
@@ -1,55 +0,0 @@
-# This is a basic workflow to help you get started with Actions
-
-name: CROSS-DEVICE-MNN-Windows
-
-# Controls when the workflow will run
-on:
-  # Triggers the workflow on push or pull request events but only for the master branch
-  schedule:
-    # Nightly build at 12:12 A.M.
-    - cron: "12 12 */1 * *"
-  push:
-    branches: [ master,  test/v0.7.0, dev/v0.7.0 ]
-  pull_request:
-    branches: [ master,  test/v0.7.0, dev/v0.7.0 ]
-
-  # Allows you to run this workflow manually from the Actions tab
-  workflow_dispatch:
-
-
-# A workflow run is made up of one or more jobs that can run sequentially or in parallel
-jobs:
-  cross-device-mnn-server:
-    defaults:
-      run:
-        shell: powershell
-        working-directory: fedml-devops\python
-    strategy:
-      fail-fast: false
-      matrix:
-        os: [ windows-2019 ]
-        arch: [X64]
-        python-version: ['3.8']
-#        exclude:
-#          - os: macos-latest
-#            python-version: '3.8'
-#          - os: windows-latest
-#            python-version: '3.6'
-    runs-on: [self-hosted, runner-windows, devops]
-    steps:
-      - uses: actions/setup-python@v4
-        with:
-          python-version: ${{ matrix.python-version }}
-      # https://github.com/actions/checkout/issues/116#issuecomment-644419389
-      - uses: actions/checkout@v3
-        with:
-          path: fedml-devops
-          clean: true
-      - name: pip install -e ./
-        run: |
-          pip install -e ./
-          pip install MNN==1.1.6
-      - name: test server of cross-device
-        run: |
-          cd quick_start/beehive
-          .\run_server.bat
diff --git a/doc/en/starter/installation.md b/doc/en/starter/installation.md
index ebf3b8dac6..737e2e5395 100644
--- a/doc/en/starter/installation.md
+++ b/doc/en/starter/installation.md
@@ -11,7 +11,16 @@ FedML supports Linux, MacOS, Windows, and Android.
 ```
 pip install fedml
 ```
-(Note: please use python 3.6, 3.7, 3.8, 3.9. We will support 3.10 systematically in the next iteration.)
+
+The default machine learning engine is `PyTorch`. FedML also supports `TensorFlow`, `Jax`, and `MXNet`.
+You can install related engine as follows:
+```
+pip install "fedml[tensorflow]"
+pip install "fedml[jax]"
+pip install "fedml[mxnet]"
+```
+Note that the commands above only install the CPU version. 
+If you need GPU/TPU version, please follow TensorFlow/Jax/MXNet official guidance.
 
 ## Installing FedML with Anaconda
 
diff --git a/python/fedml/model/model_hub.py b/python/fedml/model/model_hub.py
index 493e1cb5d4..67388d4db7 100644
--- a/python/fedml/model/model_hub.py
+++ b/python/fedml/model/model_hub.py
@@ -72,11 +72,14 @@ def create(args, output_dim):
         model = (gen, disc)
     elif model_name == "lenet" and hasattr(args, "deeplearning_backend") and args.deeplearning_backend == "mnn":
         from .mobile.mnn_lenet import create_mnn_lenet5_model
+        
         create_mnn_lenet5_model(args.global_model_file_path)
+        model = None  # for server MNN, the model is saved as computational graph and then send it to clients.
     elif model_name == "resnet20" and hasattr(args, "deeplearning_backend") and args.deeplearning_backend == "mnn":
         from .mobile.mnn_resnet import create_mnn_resnet20_model
 
         create_mnn_resnet20_model(args.global_model_file_path)
+        model = None  # for server MNN, the model is saved as computational graph and then send it to clients.
     else:
         raise Exception("no such model definition, please check the argument spelling or customize your own model")
     return model
diff --git a/python/quick_start/beehive/README.md b/python/quick_start/beehive/README.md
index b78daa7154..9762ea18c9 100644
--- a/python/quick_start/beehive/README.md
+++ b/python/quick_start/beehive/README.md
@@ -22,8 +22,8 @@ brew install android-platform-tools
 
 [https://github.com/FedML-AI/FedML/tree/master/python/quick_start/beehive](https://github.com/FedML-AI/FedML/tree/master/python/quick_start/beehive)
 
-5. For local debugging of cross-device server, please try 
-
+5. For local debugging of cross-device server, please try
+(Cross device server on Windows is not working because MNN lib can't work on Windows correctly, so you should run cross-device server on linux or other OS in which MNN lib can be working correctly)
 ```
 sh run_server.sh
 ```
diff --git a/python/quick_start/beehive/config/fedml_config.yaml b/python/quick_start/beehive/config/fedml_config.yaml
index c2d8a1b89f..58ad7dc828 100644
--- a/python/quick_start/beehive/config/fedml_config.yaml
+++ b/python/quick_start/beehive/config/fedml_config.yaml
@@ -9,7 +9,7 @@ environment_args:
 
 data_args:
   dataset: "mnist"
-  data_cache_dir: "../../../data/mnist"
+  data_cache_dir: ~/fedml_data
   partition_method: "hetero"
   partition_alpha: 0.5
   train_size: 10000
@@ -18,8 +18,8 @@ data_args:
 model_args:
   model: "lenet"
   deeplearning_backend: "mnn"
-  model_file_cache_folder: "./model_file_cache" # will be filled by the server automatically
-  global_model_file_path: "./model_file_cache/global_model.mnn"
+  model_file_cache_folder: "model_file_cache" # will be filled by the server automatically
+  global_model_file_path: "model_file_cache/global_model.mnn"
 
 train_args:
   federated_optimizer: "FedAvg"
diff --git a/python/quick_start/beehive/my_dataset.py b/python/quick_start/beehive/my_dataset.py
index 5f85221d4b..b527945b10 100644
--- a/python/quick_start/beehive/my_dataset.py
+++ b/python/quick_start/beehive/my_dataset.py
@@ -5,11 +5,11 @@
 
 
 class MnistDataset(MNN.data.Dataset):
-    def __init__(self, training_dataset=True):
+    def __init__(self, training_dataset=True, root_path="./data"):
         super(MnistDataset, self).__init__()
         self.is_training_dataset = training_dataset
-        trainset = MNIST(root="./data", train=True, download=True)
-        testset = MNIST(root="./data", train=False, download=True)
+        trainset = MNIST(root=root_path, train=True, download=True)
+        testset = MNIST(root=root_path, train=False, download=True)
         if self.is_training_dataset:
             self.data = trainset.data / 255.0
             self.labels = trainset.targets
diff --git a/python/quick_start/beehive/torch_server.py b/python/quick_start/beehive/torch_server.py
index 530256ecee..3c3a366d59 100644
--- a/python/quick_start/beehive/torch_server.py
+++ b/python/quick_start/beehive/torch_server.py
@@ -1,3 +1,6 @@
+import os
+from os.path import expanduser
+
 import MNN
 
 import fedml
@@ -12,8 +15,8 @@
     device = fedml.device.get_device(args)
 
     # load data
-    train_dataset = MnistDataset(True)
-    test_dataset = MnistDataset(False)
+    train_dataset = MnistDataset(True, root_path=args.data_cache_dir)
+    test_dataset = MnistDataset(False, root_path=args.data_cache_dir)
     train_dataloader = MNN.data.DataLoader(train_dataset, batch_size=64, shuffle=True)
     test_dataloader = MNN.data.DataLoader(
         test_dataset, batch_size=args.batch_size, shuffle=False
@@ -21,7 +24,7 @@
     class_num = 10
 
     # load model
-    model = fedml.model.create(args, output_dim=class_num)
+    fedml.model.create(args, output_dim=class_num)
 
     # start training
     server = ServerMNN(
diff --git a/python/setup.py b/python/setup.py
index d58e09adb2..4861ccd81c 100755
--- a/python/setup.py
+++ b/python/setup.py
@@ -54,7 +54,7 @@ def finalize_options(self):
 ]
 
 requirements_extra_jax = [
-    "jax[cuda]",
+    "jax[cpu]",
     "dm-haiku",
     "optax",
     "jaxlib"