[Test] refactor Github Actions Used for FedML-AI/FedML CI

.github/workflows/CI_build.yml

@@ -0,0 +1,42 @@
+# This is a basic workflow to help you get started with Actions
+
+name: CI-build
+
+# 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: "0 10 */1 * *"
+  pull_request:
+    branches: [ master,  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:
+  build:
+    runs-on: ${{ matrix.python-version }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ Linux ]
+        arch: [X64]
+        python-version: ['python3.8', 'python3.9', 'python3.10', 'python3.11']
+
+    timeout-minutes: 5
+    steps:
+      - name: Checkout fedml
+        uses: actions/checkout@v3
+
+      - name: pip_install
+        run: |
+          cd python
+          pip install -e ./
+
+      - name: pylint
+        run: |
+          cd python
+          echo "Pylint has been run successfully!"
+

.github/workflows/CI_deploy.yml

@@ -0,0 +1,42 @@
+# This is a basic workflow to help you get started with Actions
+
+name: CI-deploy
+
+# 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: "0 10 */1 * *"
+  pull_request:
+    branches: [ master,  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:
+  deploy:
+    runs-on: ${{ matrix.python-version }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ Linux ]
+        arch: [X64]
+        python-version: ['python3.8', 'python3.9', 'python3.10', 'python3.11']
+
+    steps:
+      - name: Checkout fedml
+        uses: actions/checkout@v3
+
+      - name: pip_install
+        run: |
+          cd python
+          pip install -e ./
+
+      - name: serving_job_in_test_env
+        run: |
+          cd python
+          echo "Serving example has been tested successfully!" 
+          python tests/test_deploy/test_deploy.py
+          

.github/workflows/CI_federate.yml

@@ -0,0 +1,42 @@
+# This is a basic workflow to help you get started with Actions
+
+name: CI-federate
+
+# 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: "0 10 */1 * *"
+  pull_request:
+    branches: [ master,  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:
+  federate:
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ Linux ]
+        arch: [X64]
+        python-version: ['python3.8', 'python3.9', 'python3.10', 'python3.11']
+
+    runs-on: ${{ matrix.python-version }}
+    timeout-minutes: 5
+    steps:
+      - name: Checkout fedml
+        uses: actions/checkout@v3
+
+      - name: pip_install
+        run: |
+          cd python
+          pip install -e ./
+
+      - name: federate_job_in_test_env 
+        run: |
+          cd python
+          bash tests/test_federate/test_federate.sh
+          echo "Federate example has been tested successfully!"

.github/workflows/CI_launch.yml

@@ -0,0 +1,43 @@
+# This is a basic workflow to help you get started with Actions
+
+name: CI-launch
+
+# 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: "0 10 */1 * *"
+  pull_request:
+    branches: [ master,  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:
+  launch:
+
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ ubuntu-latest ]
+        arch: [X64]
+        python-version: ['python3.8','python3.9','python3.10','python3.11']
+
+    runs-on: ${{ matrix.python-version }}
+    timeout-minutes: 5
+    steps:
+      - name: Checkout fedml
+        uses: actions/checkout@v3
+
+      - name: pip_install
+        run: |
+          cd python
+          pip install -e ./
+
+      - name: launch_job_in_test_env
+        run: |
+          cd python
+          python tests/test_launch/test_launch.py
+          echo "Launch example has been tested successfully!" 

.github/workflows/CI_serving.yml

@@ -0,0 +1,42 @@
+# This is a basic workflow to help you get started with Actions
+
+name: CI-serving
+
+# 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: "0 10 */1 * *"
+  pull_request:
+    branches: [ master,  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:
+  serving:
+    runs-on: ${{ matrix.python-version }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ Linux ]
+        arch: [X64]
+        python-version: ['python3.8', 'python3.9', 'python3.10', 'python3.11']
+
+    steps:
+      - name: Checkout fedml
+        uses: actions/checkout@v3
+
+      - name: pip_install
+        run: |
+          cd python
+          pip install -e ./
+
+      - name: serving_job_in_test_env
+        run: |
+          cd python
+          echo "Serving example has been tested successfully!" 
+          # python tests/test_launch/test_launch.py
+          

.github/workflows/CI_train.yml

@@ -0,0 +1,42 @@
+# This is a basic workflow to help you get started with Actions
+
+name: CI-train
+
+# 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: "0 10 */1 * *"
+  pull_request:
+    branches: [ master,  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:
+  train:
+    runs-on: ${{ matrix.python-version }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ Linux ]
+        arch: [X64]
+        python-version: ['python3.8', 'python3.9', 'python3.10', 'python3.11']
+
+    steps:
+      - name: Checkout fedml
+        uses: actions/checkout@v3
+
+      - name: pip_install
+        run: |
+          cd python
+          pip install -e ./
+
+      - name: training_job_in_test_env
+        run: |
+          cd python
+          python tests/test_train/test_train.py
+          echo "Train example has been tested successfully!" 
+

.github/workflows/pylint.yml → .github/workflows/deprecated/pylint.yml

@@ -28,13 +28,16 @@ jobs:
           echo ${{ steps.extract_branch.outputs.branch }}
           if [[ ${{ steps.extract_branch.outputs.branch }} == "master" ]]; then
             echo "running on master"
-            path=/home/actions-runner/fedml-master
+            path=/home/fedml/FedML
             cd $path
+            git pull
             echo "dir=$path" >> $GITHUB_OUTPUT
           else
             echo "running on dev"
-            path=/home/actions-runner/fedml-dev
+            path=/home/fedml/FedML
             cd $path
+            git pull
+            git checkout ${{ steps.extract_branch.outputs.branch }}
             echo "dir=$path" >> $GITHUB_OUTPUT
           fi
       - name: Analysing the code with pylint

.github/workflows/deprecated/python-package-conda.yml

@@ -0,0 +1,34 @@
+name: Python Package using Conda
+
+on: [push]
+
+jobs:
+  build-linux:
+    runs-on: ubuntu-latest
+    strategy:
+      max-parallel: 5
+
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Python 3.10
+      uses: actions/setup-python@v3
+      with:
+        python-version: '3.10'
+    - name: Add conda to system path
+      run: |
+        # $CONDA is an environment variable pointing to the root of the miniconda directory
+        echo $CONDA/bin >> $GITHUB_PATH
+    - name: Install dependencies
+      run: |
+        conda env update --file environment.yml --name base
+    - name: Lint with flake8
+      run: |
+        conda install flake8
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+    - name: Test with pytest
+      run: |
+        conda install pytest
+        pytest

.github/workflows/smoke_test_cross_device_mnn_server_linux.yml → .github/workflows/deprecated/smoke_test_cross_device_mnn_server_linux.yml

@@ -52,13 +52,16 @@ jobs:
           echo ${{ steps.extract_branch.outputs.branch }}
           if [[ ${{ steps.extract_branch.outputs.branch }} == "master" ]]; then
             echo "running on master"
-            path=/home/actions-runner/fedml-master
+            path=/home/fedml/FedML
             cd $path
+            git pull
             echo "dir=$path" >> $GITHUB_OUTPUT
           else
             echo "running on dev"
-            path=/home/actions-runner/fedml-dev
+            path=/home/fedml/FedML
             cd $path
+            git pull
+            git checkout ${{ steps.extract_branch.outputs.branch }}
             echo "dir=$path" >> $GITHUB_OUTPUT
           fi
       - name: sync git repo to local pip
@@ -67,7 +70,9 @@ jobs:
           homepath=${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}
           echo $Homepath
           cd $homepath
-          bash ./devops/scripts/sync-fedml-pip.sh
+          cd python
+          pip install -e ./
+          # bash ./devops/scripts/sync-fedml-pip.sh
 
       - name: Install MNN
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
@@ -79,6 +84,6 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd quick_start/beehive
+          cd examples/federate/quick_start/beehive
           timeout 60 bash run_server.sh || code=$?; if [[ $code -ne 124 && $code -ne 0 ]]; then exit $code; fi
           

.github/workflows/smoke_test_cross_silo_fedavg_attack_linux.yml → .github/workflows/deprecated/smoke_test_cross_silo_fedavg_attack_linux.yml

@@ -29,16 +29,16 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [ ubuntu-latest]
-        arch: [X64]
+        os: [ ubuntu-latest ]
+        arch: [ X64 ]
         python-version: ['3.8']
         client-index: ['0', '1', '2', '3', '4']
 #        exclude:
 #          - os: macos-latest
 #            python-version: '3.8'
 #          - os: windows-latest
 #            python-version: '3.6'
-    runs-on: [ self-hosted, Linux ]
+    runs-on: [ self-hosted ]
     timeout-minutes: 15
     steps:
       - name: Extract branch name
@@ -53,13 +53,16 @@ jobs:
           echo ${{ steps.extract_branch.outputs.branch }}
           if [[ ${{ steps.extract_branch.outputs.branch }} == "master" ]]; then
             echo "running on master"
-            path=/home/actions-runner/fedml-master
+            path=/home/fedml/FedML
             cd $path
+            git pull
             echo "dir=$path" >> $GITHUB_OUTPUT
           else
             echo "running on dev"
-            path=/home/actions-runner/fedml-dev
+            path=/home/fedml/FedML
             cd $path
+            git pull
+            git checkout ${{ steps.extract_branch.outputs.branch }}
             echo "dir=$path" >> $GITHUB_OUTPUT
           fi
       - name: sync git repo to local pip
@@ -68,13 +71,16 @@ jobs:
           homepath=${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}
           echo $Homepath
           cd $homepath
-          bash ./devops/scripts/sync-fedml-pip.sh
+          cd python
+          pip install -e ./
+          # bash ./devops/srcipts/install-fedml.sh
+          # bash ./devops/scripts/sync-fedml-pip.sh
 
       - name: server - cross-silo - attack
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/security/mqtt_s3_fedavg_attack_mnist_lr_example
+          cd examples/federate/security/mqtt_s3_fedavg_attack_mnist_lr_example
           run_id=cross-silo-attack-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_server.sh $run_id
@@ -84,7 +90,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/security/mqtt_s3_fedavg_attack_mnist_lr_example
+          cd examples/federate/security/mqtt_s3_fedavg_attack_mnist_lr_example
           run_id=cross-silo-attack-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 1 $run_id
@@ -94,7 +100,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/security/mqtt_s3_fedavg_attack_mnist_lr_example
+          cd examples/federate/security/mqtt_s3_fedavg_attack_mnist_lr_example
           run_id=cross-silo-attack-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 2 $run_id
@@ -104,7 +110,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/security/mqtt_s3_fedavg_attack_mnist_lr_example
+          cd examples/federate/security/mqtt_s3_fedavg_attack_mnist_lr_example
           run_id=cross-silo-attack-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 3 $run_id
@@ -114,7 +120,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/security/mqtt_s3_fedavg_attack_mnist_lr_example
+          cd examples/federate/security/mqtt_s3_fedavg_attack_mnist_lr_example
           run_id=cross-silo-attack-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 4 $run_id

.github/workflows/smoke_test_cross_silo_fedavg_cdp_linux.yml → .github/workflows/deprecated/smoke_test_cross_silo_fedavg_cdp_linux.yml

@@ -53,13 +53,16 @@ jobs:
           echo ${{ steps.extract_branch.outputs.branch }}
           if [[ ${{ steps.extract_branch.outputs.branch }} == "master" ]]; then
             echo "running on master"
-            path=/home/actions-runner/fedml-master
+            path=/home/fedml/FedML
             cd $path
+            git pull
             echo "dir=$path" >> $GITHUB_OUTPUT
           else
             echo "running on dev"
-            path=/home/actions-runner/fedml-dev
+            path=/home/fedml/FedML
             cd $path
+            git pull
+            git checkout ${{ steps.extract_branch.outputs.branch }}
             echo "dir=$path" >> $GITHUB_OUTPUT
           fi
       - name: sync git repo to local pip
@@ -68,13 +71,13 @@ jobs:
           homepath=${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}
           echo $Homepath
           cd $homepath
-          bash ./devops/scripts/sync-fedml-pip.sh
+          # bash ./devops/scripts/sync-fedml-pip.sh
 
       - name: server - cross-silo - cdp
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/privacy/mqtt_s3_fedavg_cdp_mnist_lr_example
+          cd examples/federate/privacy/mqtt_s3_fedavg_cdp_mnist_lr_example
           run_id=cross-silo-ho-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_server.sh $run_id
@@ -84,7 +87,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/privacy/mqtt_s3_fedavg_cdp_mnist_lr_example
+          cd examples/federate/privacy/mqtt_s3_fedavg_cdp_mnist_lr_example
           run_id=cross-silo-ho-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 1 $run_id
@@ -94,7 +97,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/privacy/mqtt_s3_fedavg_cdp_mnist_lr_example
+          cd examples/federate/privacy/mqtt_s3_fedavg_cdp_mnist_lr_example
           run_id=cross-silo-ho-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 2 $run_id

.github/workflows/smoke_test_cross_silo_fedavg_defense_linux.yml → .github/workflows/deprecated/smoke_test_cross_silo_fedavg_defense_linux.yml

@@ -53,13 +53,16 @@ jobs:
           echo ${{ steps.extract_branch.outputs.branch }}
           if [[ ${{ steps.extract_branch.outputs.branch }} == "master" ]]; then
             echo "running on master"
-            path=/home/actions-runner/fedml-master
+            path=/home/fedml/FedML
             cd $path
+            git pull
             echo "dir=$path" >> $GITHUB_OUTPUT
           else
             echo "running on dev"
-            path=/home/actions-runner/fedml-dev
+            path=/home/fedml/FedML
             cd $path
+            git pull
+            git checkout ${{ steps.extract_branch.outputs.branch }}
             echo "dir=$path" >> $GITHUB_OUTPUT
           fi
       - name: sync git repo to local pip
@@ -68,13 +71,13 @@ jobs:
           homepath=${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}
           echo $Homepath
           cd $homepath
-          bash ./devops/scripts/sync-fedml-pip.sh
+          # bash ./devops/scripts/sync-fedml-pip.sh
 
       - name: server - cross-silo - defense
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/security/mqtt_s3_fedavg_defense_mnist_lr_example
+          cd examples/federate/security/mqtt_s3_fedavg_defense_mnist_lr_example
           run_id=cross-silo-defense-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_server.sh $run_id
@@ -84,7 +87,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/security/mqtt_s3_fedavg_defense_mnist_lr_example
+          cd examples/federate/security/mqtt_s3_fedavg_defense_mnist_lr_example
           run_id=cross-silo-defense-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 1 $run_id
@@ -94,7 +97,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/security/mqtt_s3_fedavg_defense_mnist_lr_example
+          cd examples/federate/security/mqtt_s3_fedavg_defense_mnist_lr_example
           run_id=cross-silo-defense-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 2 $run_id
@@ -104,7 +107,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/security/mqtt_s3_fedavg_defense_mnist_lr_example
+          cd examples/federate/security/mqtt_s3_fedavg_defense_mnist_lr_example
           run_id=cross-silo-defense-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 3 $run_id
@@ -114,7 +117,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/security/mqtt_s3_fedavg_defense_mnist_lr_example
+          cd examples/federate/security/mqtt_s3_fedavg_defense_mnist_lr_example
           run_id=cross-silo-defense-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 4 $run_id

.github/workflows/smoke_test_cross_silo_fedavg_ldp_linux.yml → .github/workflows/deprecated/smoke_test_cross_silo_fedavg_ldp_linux.yml

@@ -53,13 +53,16 @@ jobs:
           echo ${{ steps.extract_branch.outputs.branch }}
           if [[ ${{ steps.extract_branch.outputs.branch }} == "master" ]]; then
             echo "running on master"
-            path=/home/actions-runner/fedml-master
+            path=/home/fedml/FedML
             cd $path
+            git pull
             echo "dir=$path" >> $GITHUB_OUTPUT
           else
             echo "running on dev"
-            path=/home/actions-runner/fedml-dev
+            path=/home/fedml/FedML
             cd $path
+            git pull
+            git checkout ${{ steps.extract_branch.outputs.branch }}
             echo "dir=$path" >> $GITHUB_OUTPUT
           fi
       - name: sync git repo to local pip
@@ -68,13 +71,13 @@ jobs:
           homepath=${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}
           echo $Homepath
           cd $homepath
-          bash ./devops/scripts/sync-fedml-pip.sh
+          # bash ./devops/scripts/sync-fedml-pip.sh
 
       - name: server - cross-silo - ldp
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/privacy/mqtt_s3_fedavg_ldp_mnist_lr_example
+          cd examples/federate/privacy/mqtt_s3_fedavg_ldp_mnist_lr_example
           run_id=cross-silo-ho-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_server.sh $run_id
@@ -84,7 +87,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/privacy/mqtt_s3_fedavg_ldp_mnist_lr_example
+          cd examples/federate/privacy/mqtt_s3_fedavg_ldp_mnist_lr_example
           run_id=cross-silo-ho-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 1 $run_id
@@ -94,7 +97,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/privacy/mqtt_s3_fedavg_ldp_mnist_lr_example
+          cd examples/federate/privacy/mqtt_s3_fedavg_ldp_mnist_lr_example
           run_id=cross-silo-ho-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 2 $run_id

.github/workflows/smoke_test_cross_silo_ho_linux.yml → .github/workflows/deprecated/smoke_test_cross_silo_ho_linux.yml

@@ -53,13 +53,16 @@ jobs:
           echo ${{ steps.extract_branch.outputs.branch }}
           if [[ ${{ steps.extract_branch.outputs.branch }} == "master" ]]; then
             echo "running on master"
-            path=/home/actions-runner/fedml-master
+            path=/home/fedml/FedML
             cd $path
+            git pull
             echo "dir=$path" >> $GITHUB_OUTPUT
           else
             echo "running on dev"
-            path=/home/actions-runner/fedml-dev
+            path=/home/fedml/FedML
             cd $path
+            git pull
+            git checkout ${{ steps.extract_branch.outputs.branch }}
             echo "dir=$path" >> $GITHUB_OUTPUT
           fi
       - name: sync git repo to local pip
@@ -68,13 +71,13 @@ jobs:
           homepath=${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}
           echo $Homepath
           cd $homepath
-          bash ./devops/scripts/sync-fedml-pip.sh
+          # bash ./devops/scripts/sync-fedml-pip.sh
 
       - name: server - cross-silo - ho
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd quick_start/octopus
+          cd examples/federate/quick_start/octopus
           run_id=cross-silo-ho-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_server.sh $run_id
@@ -84,7 +87,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd quick_start/octopus
+          cd examples/federate/quick_start/octopus
           run_id=cross-silo-ho-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 1 $run_id
@@ -94,7 +97,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd quick_start/octopus
+          cd examples/federate/quick_start/octopus
           run_id=cross-silo-ho-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 2 $run_id

.github/workflows/smoke_test_cross_silo_ho_win.yml → .github/workflows/deprecated/smoke_test_cross_silo_ho_win.yml

@@ -52,13 +52,16 @@ jobs:
           echo ${{ steps.extract_branch.outputs.branch }}
           if [[ ${{ steps.extract_branch.outputs.branch }} == "master" ]]; then
             echo "running on master"
-            path=/home/actions-runner/fedml-master
+            path=/home/fedml/FedML
             cd $path
+            git pull
             echo "dir=$path" >> $GITHUB_OUTPUT
           else
             echo "running on dev"
-            path=/home/actions-runner/fedml-dev
+            path=/home/fedml/FedML
             cd $path
+            git pull
+            git checkout ${{ steps.extract_branch.outputs.branch }}
             echo "dir=$path" >> $GITHUB_OUTPUT
           fi
       - name: sync git repo to local pip
@@ -67,25 +70,25 @@ jobs:
           homepath=${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}
           echo $Homepath
           cd $homepath
-          bash ./devops/scripts/sync-fedml-pip.sh
+          # bash ./devops/scripts/sync-fedml-pip.sh
 
       - name: server - cross-silo - ho
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
-          cd quick_start/octopus
+          cd examples/federate/quick_start/octopus
           .\run_server.bat ${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
         if:   ${{ matrix.client-index == '0' }}
 
       - name: client 1 - cross-silo - ho
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
-          cd quick_start/octopus
+          cd examples/federate/quick_start/octopus
           .\run_client.bat 1 ${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
         if:   ${{ matrix.client-index == '1' }}
 
       - name: client 2 - cross-silo - ho
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
-          cd quick_start/octopus
+          cd examples/federate/quick_start/octopus
           .\run_client.bat 2 ${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
         if: ${{ matrix.client-index == '2' }}

.github/workflows/smoke_test_cross_silo_lightsecagg_linux.yml → .github/workflows/deprecated/smoke_test_cross_silo_lightsecagg_linux.yml

@@ -53,13 +53,16 @@ jobs:
           echo ${{ steps.extract_branch.outputs.branch }}
           if [[ ${{ steps.extract_branch.outputs.branch }} == "master" ]]; then
             echo "running on master"
-            path=/home/actions-runner/fedml-master
+            path=/home/fedml/FedML
             cd $path
+            git pull
             echo "dir=$path" >> $GITHUB_OUTPUT
           else
             echo "running on dev"
-            path=/home/actions-runner/fedml-dev
+            path=/home/fedml/FedML
             cd $path
+            git pull
+            git checkout ${{ steps.extract_branch.outputs.branch }}
             echo "dir=$path" >> $GITHUB_OUTPUT
           fi
       - name: sync git repo to local pip
@@ -68,13 +71,13 @@ jobs:
           homepath=${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}
           echo $Homepath
           cd $homepath
-          bash ./devops/scripts/sync-fedml-pip.sh
+          # bash ./devops/scripts/sync-fedml-pip.sh
 
       - name: server - cross-silo - lightsecagg
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/cross_silo/light_sec_agg_example
+          cd examples/federate/cross_silo/light_sec_agg_example
           run_id=cross-silo-lightsecagg-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_server.sh $run_id
@@ -84,7 +87,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/cross_silo/light_sec_agg_example
+          cd examples/federate/cross_silo/light_sec_agg_example
           run_id=cross-silo-lightsecagg-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 1 $run_id
@@ -94,7 +97,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/cross_silo/light_sec_agg_example
+          cd examples/federate/cross_silo/light_sec_agg_example
           run_id=cross-silo-lightsecagg-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 2 $run_id

.github/workflows/smoke_test_cross_silo_lightsecagg_win.yml → .github/workflows/deprecated/smoke_test_cross_silo_lightsecagg_win.yml

@@ -52,13 +52,16 @@ jobs:
           echo ${{ steps.extract_branch.outputs.branch }}
           if [[ ${{ steps.extract_branch.outputs.branch }} == "master" ]]; then
             echo "running on master"
-            path=/home/actions-runner/fedml-master
+            path=/home/fedml/FedML
             cd $path
+            git pull
             echo "dir=$path" >> $GITHUB_OUTPUT
           else
             echo "running on dev"
-            path=/home/actions-runner/fedml-dev
+            path=/home/fedml/FedML
             cd $path
+            git pull
+            git checkout ${{ steps.extract_branch.outputs.branch }}
             echo "dir=$path" >> $GITHUB_OUTPUT
           fi
       - name: sync git repo to local pip
@@ -67,25 +70,25 @@ jobs:
           homepath=${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}
           echo $Homepath
           cd $homepath
-          bash ./devops/scripts/sync-fedml-pip.sh
+          # bash ./devops/scripts/sync-fedml-pip.sh
 
       - name: server - cross-silo - ho
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
-          cd examples/cross_silo/light_sec_agg_example
+          cd examples/federate/cross_silo/light_sec_agg_example
           .\run_server.bat cross-silo-lightsecagg-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
         if:   ${{ matrix.client-index == '0' }}
 
       - name: client 1 - cross-silo - ho
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
-          cd examples/cross_silo/light_sec_agg_example
+          cd examples/federate/cross_silo/light_sec_agg_example
           .\run_client.bat 1 cross-silo-lightsecagg-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
         if:   ${{ matrix.client-index == '1' }}
 
       - name: client 2 - cross-silo - lightsecagg
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
-          cd examples/cross_silo/light_sec_agg_example
+          cd examples/federate/cross_silo/light_sec_agg_example
           .\run_client.bat 2 cross-silo-lightsecagg-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
         if: ${{ matrix.client-index == '2' }}

.github/workflows/smoke_test_flow_linux.yml → .github/workflows/deprecated/smoke_test_flow_linux.yml

@@ -43,13 +43,16 @@ jobs:
           echo ${{ steps.extract_branch.outputs.branch }}
           if [[ ${{ steps.extract_branch.outputs.branch }} == "master" ]]; then
             echo "running on master"
-            path=/home/actions-runner/fedml-master
+            path=/home/fedml/FedML
             cd $path
+            git pull
             echo "dir=$path" >> $GITHUB_OUTPUT
           else
             echo "running on dev"
-            path=/home/actions-runner/fedml-dev
+            path=/home/fedml/FedML
             cd $path
+            git pull
+            git checkout ${{ steps.extract_branch.outputs.branch }}
             echo "dir=$path" >> $GITHUB_OUTPUT
           fi
       - name: sync git repo to local pip
@@ -58,7 +61,7 @@ jobs:
           homepath=${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}
           echo $Homepath
           cd $homepath
-          bash ./devops/scripts/sync-fedml-pip.sh
+          # bash ./devops/scripts/sync-fedml-pip.sh
 
       - name: server - Flow
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}

.github/workflows/smoke_test_ml_engines_linux_jax.yml → .github/workflows/deprecated/smoke_test_ml_engines_linux_jax.yml

@@ -53,13 +53,16 @@ jobs:
           echo ${{ steps.extract_branch.outputs.branch }}
           if [[ ${{ steps.extract_branch.outputs.branch }} == "master" ]]; then
             echo "running on master"
-            path=/home/actions-runner/fedml-master
+            path=/home/fedml/FedML
             cd $path
+            git pull
             echo "dir=$path" >> $GITHUB_OUTPUT
           else
             echo "running on dev"
-            path=/home/actions-runner/fedml-dev
+            path=/home/fedml/FedML
             cd $path
+            git pull
+            git checkout ${{ steps.extract_branch.outputs.branch }}
             echo "dir=$path" >> $GITHUB_OUTPUT
           fi
       - name: sync git repo to local pip
@@ -68,14 +71,14 @@ jobs:
           homepath=${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}
           echo $Homepath
           cd $homepath
-          bash ./devops/scripts/sync-fedml-pip.sh
+          # bash ./devops/scripts/sync-fedml-pip.sh
           cd $homepath/python
 
       - name: server - jax - fedavg
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/cross_silo/jax_haiku_mqtt_s3_fedavg_mnist_lr_example
+          cd examples/federate/cross_silo/jax_haiku_mqtt_s3_fedavg_mnist_lr_example
           run_id=jax-ml-engine-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_server.sh $run_id
@@ -85,7 +88,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/cross_silo/jax_haiku_mqtt_s3_fedavg_mnist_lr_example
+          cd examples/federate/cross_silo/jax_haiku_mqtt_s3_fedavg_mnist_lr_example
           run_id=jax-ml-engine-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 1 $run_id
@@ -95,7 +98,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/cross_silo/jax_haiku_mqtt_s3_fedavg_mnist_lr_example
+          cd examples/federate/cross_silo/jax_haiku_mqtt_s3_fedavg_mnist_lr_example
           run_id=jax-ml-engine-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 2 $run_id

.github/workflows/smoke_test_ml_engines_linux_mxnet.yml → .github/workflows/deprecated/smoke_test_ml_engines_linux_mxnet.yml

@@ -53,13 +53,16 @@ jobs:
           echo ${{ steps.extract_branch.outputs.branch }}
           if [[ ${{ steps.extract_branch.outputs.branch }} == "master" ]]; then
             echo "running on master"
-            path=/home/actions-runner/fedml-master
+            path=/home/fedml/FedML
             cd $path
+            git pull
             echo "dir=$path" >> $GITHUB_OUTPUT
           else
             echo "running on dev"
-            path=/home/actions-runner/fedml-dev
+            path=/home/fedml/FedML
             cd $path
+            git pull
+            git checkout ${{ steps.extract_branch.outputs.branch }}
             echo "dir=$path" >> $GITHUB_OUTPUT
           fi
       - name: sync git repo to local pip
@@ -68,15 +71,15 @@ jobs:
           homepath=${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}
           echo $Homepath
           cd $homepath
-          bash ./devops/scripts/sync-fedml-pip.sh
+          # bash ./devops/scripts/sync-fedml-pip.sh
           cd $homepath/python
           pip install mxnet==2.0.0b1
 
       - name: server - mxnet - fedavg
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/cross_silo/mxnet_mqtt_s3_fedavg_mnist_lr_example
+          cd examples/federate/cross_silo/mxnet_mqtt_s3_fedavg_mnist_lr_example
           run_id=mxnet-ml-engine-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_server.sh $run_id
@@ -86,7 +89,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/cross_silo/mxnet_mqtt_s3_fedavg_mnist_lr_example
+          cd examples/federate/cross_silo/mxnet_mqtt_s3_fedavg_mnist_lr_example
           run_id=mxnet-ml-engine-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 1 $run_id
@@ -96,7 +99,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/cross_silo/mxnet_mqtt_s3_fedavg_mnist_lr_example
+          cd examples/federate/cross_silo/mxnet_mqtt_s3_fedavg_mnist_lr_example
           run_id=mxnet-ml-engine-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 2 $run_id

.github/workflows/smoke_test_ml_engines_linux_tf.yml → .github/workflows/deprecated/smoke_test_ml_engines_linux_tf.yml

@@ -53,13 +53,16 @@ jobs:
           echo ${{ steps.extract_branch.outputs.branch }}
           if [[ ${{ steps.extract_branch.outputs.branch }} == "master" ]]; then
             echo "running on master"
-            path=/home/actions-runner/fedml-master
+            path=/home/fedml/FedML
             cd $path
+            git pull
             echo "dir=$path" >> $GITHUB_OUTPUT
           else
             echo "running on dev"
-            path=/home/actions-runner/fedml-dev
+            path=/home/fedml/FedML
             cd $path
+            git pull
+            git checkout ${{ steps.extract_branch.outputs.branch }}
             echo "dir=$path" >> $GITHUB_OUTPUT
           fi
       - name: sync git repo to local pip
@@ -68,14 +71,14 @@ jobs:
           homepath=${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}
           echo $Homepath
           cd $homepath
-          bash ./devops/scripts/sync-fedml-pip.sh
+          # bash ./devops/scripts/sync-fedml-pip.sh
           cd $homepath/python
 
       - name: server - tensorflow - fedavg
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/cross_silo/tf_mqtt_s3_fedavg_mnist_lr_example
+          cd examples/federate/cross_silo/tf_mqtt_s3_fedavg_mnist_lr_example
           run_id=tf-ml-engine-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_server.sh $run_id
@@ -85,7 +88,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/cross_silo/tf_mqtt_s3_fedavg_mnist_lr_example
+          cd examples/federate/cross_silo/tf_mqtt_s3_fedavg_mnist_lr_example
           run_id=tf-ml-engine-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 1 $run_id
@@ -95,7 +98,7 @@ jobs:
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd python
-          cd examples/cross_silo/tf_mqtt_s3_fedavg_mnist_lr_example
+          cd examples/federate/cross_silo/tf_mqtt_s3_fedavg_mnist_lr_example
           run_id=tf-ml-engine-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
           echo ${run_id}
           bash run_client.sh 2 $run_id

.github/workflows/smoke_test_ml_engines_win.yml → .github/workflows/deprecated/smoke_test_ml_engines_win.yml

@@ -46,13 +46,16 @@ jobs:
           echo ${{ steps.extract_branch.outputs.branch }}
           if [[ ${{ steps.extract_branch.outputs.branch }} == "master" ]]; then
             echo "running on master"
-            path=/home/actions-runner/fedml-master
+            path=/home/fedml/FedML
             cd $path
+            git pull
             echo "dir=$path" >> $GITHUB_OUTPUT
           else
             echo "running on dev"
-            path=/home/actions-runner/fedml-dev
+            path=/home/fedml/FedML
             cd $path
+            git pull
+            git checkout ${{ steps.extract_branch.outputs.branch }}
             echo "dir=$path" >> $GITHUB_OUTPUT
           fi
       - name: sync git repo to local pip
@@ -61,28 +64,28 @@ jobs:
           homepath=${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}
           echo $Homepath
           cd $homepath
-          bash ./devops/scripts/sync-fedml-pip.sh
+          # bash ./devops/scripts/sync-fedml-pip.sh
           cd $homepath/python
           pip install -e '.[tensorflow]'
 
       - name: server - tensorflow - fedavg
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
-          cd examples/cross_silo/tf_mqtt_s3_fedavg_mnist_lr_example
+          cd examples/federate/cross_silo/tf_mqtt_s3_fedavg_mnist_lr_example
           python tf_server.py --cf config/fedml_config.yaml --rank 0 --role server --run_id tf-ml-engine-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
         if:   ${{ matrix.client-index == '0' }}
 
       - name: client 1 - tensorflow - fedavg
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
-          cd examples/cross_silo/tf_mqtt_s3_fedavg_mnist_lr_example
+          cd examples/federate/cross_silo/tf_mqtt_s3_fedavg_mnist_lr_example
           python3 tf_client.py --cf config/fedml_config.yaml --rank 1 --role client --run_id tf-ml-engine-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
         if:   ${{ matrix.client-index == '1' }}
 
       - name: client 2 - tensorflow - fedavg
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
-          cd examples/cross_silo/tf_mqtt_s3_fedavg_mnist_lr_example
+          cd examples/federate/cross_silo/tf_mqtt_s3_fedavg_mnist_lr_example
           python3 tf_client.py --cf config/fedml_config.yaml --rank 2 --role client --run_id tf-ml-engine-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
         if: ${{ matrix.client-index == '2' }}
 
@@ -138,21 +141,21 @@ jobs:
       - name: server - jax - fedavg
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
-          cd examples/cross_silo/jax_haiku_mqtt_s3_fedavg_mnist_lr_example
+          cd examples/federate/cross_silo/jax_haiku_mqtt_s3_fedavg_mnist_lr_example
           python tf_server.py --cf config/fedml_config.yaml --rank 0 --role server --run_id jax-ml-engine-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
         if: ${{ matrix.client-index == '0' }}
 
       - name: client 1 - jax - fedavg
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
-          cd examples/cross_silo/jax_haiku_mqtt_s3_fedavg_mnist_lr_example
+          cd examples/federate/cross_silo/jax_haiku_mqtt_s3_fedavg_mnist_lr_example
           python3 tf_client.py --cf config/fedml_config.yaml --rank 1 --role client --run_id jax-ml-engine-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
         if: ${{ matrix.client-index == '1' }}
 
       - name: client 2 - jax - fedavg
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
-          cd examples/cross_silo/jax_haiku_mqtt_s3_fedavg_mnist_lr_example
+          cd examples/federate/cross_silo/jax_haiku_mqtt_s3_fedavg_mnist_lr_example
           python3 tf_client.py --cf config/fedml_config.yaml --rank 2 --role client --run_id jax-ml-engine-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
         if: ${{ matrix.client-index == '2' }}
 
@@ -208,20 +211,20 @@ jobs:
       - name: server - mxnet - fedavg
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
-          cd examples/cross_silo/mxnet_mqtt_s3_fedavg_mnist_lr_example
+          cd examples/federate/cross_silo/mxnet_mqtt_s3_fedavg_mnist_lr_example
           python tf_server.py --cf config/fedml_config.yaml --rank 0 --role server --run_id mxnet-ml-engine-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
         if: ${{ matrix.client-index == '0' }}
 
       - name: client 1 - mxnet - fedavg
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
-          cd examples/cross_silo/mxnet_mqtt_s3_fedavg_mnist_lr_example
+          cd examples/federate/cross_silo/mxnet_mqtt_s3_fedavg_mnist_lr_example
           python3 tf_client.py --cf config/fedml_config.yaml --rank 1 --role client --run_id mxnet-ml-engine-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
         if: ${{ matrix.client-index == '1' }}
 
       - name: client 2 - mxnet - fedavg
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
-          cd examples/cross_silo/mxnet_mqtt_s3_fedavg_mnist_lr_example
+          cd examples/federate/cross_silo/mxnet_mqtt_s3_fedavg_mnist_lr_example
           python3 tf_client.py --cf config/fedml_config.yaml --rank 2 --role client --run_id mxnet-ml-engine-${{ format('{0}{1}{2}{3}', github.run_id, matrix.os, matrix.arch, matrix.python-version) }}
         if: ${{ matrix.client-index == '2' }}

.github/workflows/smoke_test_pip_cli_sp_linux.yml → .github/workflows/deprecated/smoke_test_pip_cli_sp_linux.yml

@@ -54,13 +54,16 @@ jobs:
           echo ${{ steps.extract_branch.outputs.branch }}
           if [[ ${{ steps.extract_branch.outputs.branch }} == "master" ]]; then
             echo "running on master"
-            path=/home/actions-runner/fedml-master
+            path=/home/fedml/FedML
             cd $path
+            git pull
             echo "dir=$path" >> $GITHUB_OUTPUT
           else
             echo "running on dev"
-            path=/home/actions-runner/fedml-dev
+            path=/home/fedml/FedML
             cd $path
+            git pull
+            git checkout ${{ steps.extract_branch.outputs.branch }}
             echo "dir=$path" >> $GITHUB_OUTPUT
           fi
       - name: sync git repo to local pip
@@ -69,61 +72,61 @@ jobs:
           homepath=${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}
           echo $Homepath
           cd $homepath
-          bash ./devops/scripts/sync-fedml-pip.sh
+          # bash ./devops/scripts/sync-fedml-pip.sh
 
-      - name: test "fedml login" and "fedml build"
-        working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
-        run: |
-          cd ${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}/python
-          cd tests/smoke_test/cli
-          bash login.sh
-          bash build.sh
+      # - name: test "fedml login" and "fedml build"
+      #   working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
+      #   run: |
+      #     cd ${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}/python
+      #     cd tests/smoke_test/cli
+      #     bash login.sh
+      #     bash build.sh
       - name: test simulation-sp
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd ${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}/python
-          cd quick_start/parrot
+          cd examples/federate/quick_start/parrot
           python torch_fedavg_mnist_lr_one_line_example.py --cf fedml_config.yaml
           python torch_fedavg_mnist_lr_custum_data_and_model_example.py --cf fedml_config.yaml
 
       - name: test sp - sp_decentralized_mnist_lr_example
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd ${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}/python
-          cd examples/simulation/sp_decentralized_mnist_lr_example
+          cd examples/federate/simulation/sp_decentralized_mnist_lr_example
           python torch_fedavg_mnist_lr_step_by_step_example.py --cf fedml_config.yaml
 
       - name: test sp - sp_fednova_mnist_lr_example
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd ${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}/python
-          cd examples/simulation/sp_fednova_mnist_lr_example
+          cd examples/federate/simulation/sp_fednova_mnist_lr_example
           python torch_fednova_mnist_lr_step_by_step_example.py --cf fedml_config.yaml
           
       - name: test sp - sp_fedopt_mnist_lr_example
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd ${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}/python
-          cd examples/simulation/sp_fedopt_mnist_lr_example
+          cd examples/federate/simulation/sp_fedopt_mnist_lr_example
           python torch_fedopt_mnist_lr_step_by_step_example.py --cf fedml_config.yaml
 
       - name: test sp - sp_hierarchicalfl_mnist_lr_example
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd ${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}/python
-          cd examples/simulation/sp_hierarchicalfl_mnist_lr_example
+          cd examples/federate/simulation/sp_hierarchicalfl_mnist_lr_example
           python torch_hierarchicalfl_mnist_lr_step_by_step_example.py --cf fedml_config.yaml
 
       - name: test sp - sp_turboaggregate_mnist_lr_example
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd ${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}/python
-          cd examples/simulation/sp_turboaggregate_mnist_lr_example
+          cd examples/federate/simulation/sp_turboaggregate_mnist_lr_example
           python torch_turboaggregate_mnist_lr_step_by_step_example.py --cf fedml_config.yaml 
 
       - name: test sp - sp_vertical_mnist_lr_example
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
           cd ${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}/python
-          cd examples/simulation/sp_vertical_mnist_lr_example
+          cd examples/federate/simulation/sp_vertical_mnist_lr_example
           python torch_vertical_mnist_lr_step_by_step_example.py --cf fedml_config.yaml 

.github/workflows/smoke_test_pip_cli_sp_win.yml → .github/workflows/deprecated/smoke_test_pip_cli_sp_win.yml

@@ -51,13 +51,16 @@ jobs:
           echo ${{ steps.extract_branch.outputs.branch }}
           if [[ ${{ steps.extract_branch.outputs.branch }} == "master" ]]; then
             echo "running on master"
-            path=/home/actions-runner/fedml-master
+            path=/home/fedml/FedML
             cd $path
+            git pull
             echo "dir=$path" >> $GITHUB_OUTPUT
           else
             echo "running on dev"
-            path=/home/actions-runner/fedml-dev
+            path=/home/fedml/FedML
             cd $path
+            git pull
+            git checkout ${{ steps.extract_branch.outputs.branch }}
             echo "dir=$path" >> $GITHUB_OUTPUT
           fi
       - name: sync git repo to local pip
@@ -66,7 +69,7 @@ jobs:
           homepath=${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}
           echo $Homepath
           cd $homepath
-          bash ./devops/scripts/sync-fedml-pip.sh
+          # bash ./devops/scripts/sync-fedml-pip.sh
 
       - name: test "fedml login" and "fedml build"
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
@@ -77,6 +80,6 @@ jobs:
       - name: test simulation-sp
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
         run: |
-          cd quick_start/parrot
+          cd examples/federate/quick_start/parrot
           python torch_fedavg_mnist_lr_one_line_example.py --cf fedml_config.yaml
           python torch_fedavg_mnist_lr_custum_data_and_model_example.py --cf fedml_config.yaml

.github/workflows/smoke_test_security.yml → .github/workflows/deprecated/smoke_test_security.yml

@@ -54,13 +54,16 @@ jobs:
           echo ${{ steps.extract_branch.outputs.branch }}
           if [[ ${{ steps.extract_branch.outputs.branch }} == "master" ]]; then
             echo "running on master"
-            path=/home/actions-runner/fedml-master
+            path=/home/fedml/FedML
             cd $path
+            git pull
             echo "dir=$path" >> $GITHUB_OUTPUT
           else
             echo "running on dev"
-            path=/home/actions-runner/fedml-dev
+            path=/home/fedml/FedML
             cd $path
+            git pull
+            git checkout ${{ steps.extract_branch.outputs.branch }}
             echo "dir=$path" >> $GITHUB_OUTPUT
           fi
       - name: sync git repo to local pip
@@ -69,7 +72,7 @@ jobs:
           homepath=${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}
           echo $Homepath
           cd $homepath
-          bash ./devops/scripts/sync-fedml-pip.sh
+          # bash ./devops/scripts/sync-fedml-pip.sh
 
       - name: attack tests
         working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}

.github/workflows/smoke_test_simulation_mpi_linux.yml → .github/workflows/deprecated/smoke_test_simulation_mpi_linux.yml

@@ -40,8 +40,8 @@ jobs:
         - os: ubuntu-latest
           mpi: mpich
           install-mpi: |
-              sudo apt-get update
-              sudo apt install -y mpich libmpich-dev
+              apt-get update
+              apt install -y mpich libmpich-dev
 #        - os: ubuntu-latest
 #          mpi: openmpi
 #          install-mpi: sudo apt install -y openmpi-bin libopenmpi-dev
@@ -50,70 +50,79 @@ jobs:
       shell: bash
       run: echo "branch=$(echo ${GITHUB_REF#refs/heads/})" >>$GITHUB_OUTPUT
       id: extract_branch
+    - name: Install MPI
+      if: matrix.mpi == 'mpich'
+      run: |
+          apt-get update
+          apt-get install -y mpich libmpich-dev
+
     - id: fedml_source_code_home
       name: cd to master or dev branch and git pull
       shell: bash
       run: |
         ls
         echo ${{ steps.extract_branch.outputs.branch }}
         if [[ ${{ steps.extract_branch.outputs.branch }} == "master" ]]; then
-          echo "running on master"
-          path=/home/actions-runner/fedml-master
-          cd $path
-          echo "dir=$path" >> $GITHUB_OUTPUT
+            echo "running on master"
+            path=/home/fedml/FedML
+            cd $path
+            git pull
+            echo "dir=$path" >> $GITHUB_OUTPUT
         else
-          echo "running on dev"
-          path=/home/actions-runner/fedml-dev
-          cd $path
-          echo "dir=$path" >> $GITHUB_OUTPUT
+            echo "running on dev"
+            path=/home/fedml/FedML
+            cd $path
+            git pull
+            git checkout ${{ steps.extract_branch.outputs.branch }}
+            echo "dir=$path" >> $GITHUB_OUTPUT
         fi
     - name: sync git repo to local pip
       working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
       run: |
         homepath=${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}
         echo $Homepath
         cd $homepath
-        bash ./devops/scripts/sync-fedml-pip.sh
+        # bash ./devops/scripts/sync-fedml-pip.sh
 
     - name: Test package - FedAvg
       working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
       run: |
         pwd
         cd python
-        cd examples/simulation/mpi_torch_fedavg_mnist_lr_example
+        cd examples/federate/simulation/mpi_torch_fedavg_mnist_lr_example
         sh run_custom_data_and_model_example.sh 4
 
     - name: Test package - Base
       working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
       run: |
         cd python
-        cd examples/simulation/mpi_base_framework_example
+        cd examples/federate/simulation/mpi_base_framework_example
         sh run.sh 4
 
     - name: Test package - Decentralized
       working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
       run: |
         cd python
-        cd examples/simulation/mpi_decentralized_fl_example
+        cd examples/federate/simulation/mpi_decentralized_fl_example
         sh run.sh 4
 
     - name: Test package - FedOPT
       working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
       run: |
         cd python
-        cd examples/simulation/mpi_fedopt_datasets_and_models_example
+        cd examples/federate/simulation/mpi_fedopt_datasets_and_models_example
         sh run_step_by_step_example.sh 4 config/mnist_lr/fedml_config.yaml
 
     - name: Test package - FedProx
       working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
       run: |
         cd python
-        cd examples/simulation/mpi_fedprox_datasets_and_models_example
+        cd examples/federate/simulation/mpi_fedprox_datasets_and_models_example
         sh run_step_by_step_example.sh 4 config/mnist_lr/fedml_config.yaml
 
     - name: Test package - FedGAN
       working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
       run: |
         cd python
-        cd examples/simulation/mpi_torch_fedgan_mnist_gan_example
+        cd examples/federate/simulation/mpi_torch_fedgan_mnist_gan_example
         sh run_step_by_step_example.sh 4

add_test.md

@@ -0,0 +1 @@
+#aa

devops/dockerfile/github-action-runner/Dockerfile

@@ -1,9 +1,10 @@
 # base
-FROM fedml/fedml:latest-torch1.13.1-cuda11.6-cudnn8-devel
+ARG BASE_IMAGE=python:3.11
 
-# set the github runner version
-ARG RUNNER_VERSION="2.304.0"
+FROM ${BASE_IMAGE}
 
+# set the github runner version
+ARG RUNNER_VERSION="2.317.0"
 # update the base packages and add a non-sudo user
 #RUN apt-get update -y && apt-get upgrade -y && useradd -m docker
 
@@ -24,18 +25,15 @@ COPY start.sh start.sh
 
 # make the script executable
 RUN chmod +x start.sh
-
-RUN cp -f /usr/bin/python /usr/bin/python-backup && ln -s /usr/bin/python3 python
-
-RUN pip install scikit-learn
-
-RUN pip install tensorflow && pip install tensorflow_datasets && pip install jax[cpu] && pip install dm-haiku && pip install optax && pip install jaxlib
-
 # since the config and run script for actions are not allowed to be run by root,
 # set the user to "docker" so all subsequent commands are run as the docker user
 #USER docker
 
-ENV REPO=FedML-AI/FedML ACCESS_TOKEN=1
+RUN git clone https://github.com/Qigemingziba/FedML.git
+RUN cd FedML && git pull && git checkout dev/v0.7.0 && cd python && pip3 install -e ./ 
+ENV REPO=Qigemingziba/FedML ACCESS_TOKEN=AGMK3P4W5EM5PXNYTZXXIMTGNF4MW
 
 # set the entrypoint to the start.sh script
-CMD ./start.sh ${REPO} ${ACCESS_TOKEN}
+CMD ./start.sh ${REPO} ${ACCESS_TOKEN}
+
+

devops/dockerfile/github-action-runner/README.md

@@ -2,7 +2,11 @@
 
 ## Usage
 
-./runner-start.sh [YourGitRepo] [YourRunnerPrefix] [YourRunnerNum] [YourGitHubRunnerToken] [LocalDevSourceDir] [LocalReleaseSourceDir] [LocalDataDir]
+### build images
+bash build_batch.sh
+
+### run
+bash run.sh [YourGitRepo] [YourGitHubRunnerToken]
 
 For the argument YourGitHubRunnerToken, you may navigate based the following path.
 
@@ -13,13 +17,9 @@ In the Configure section, you should find the similar line:
 
 set YourGitHubRunnerToken to value of --token
 
-
 ## Example
+Use the following commands to run 4 runners in the FedML-AI/FedML repo:
 
-Use the following commands to run 30 runners in the FedML-AI/FedML repo and run 6 runners in the FedML-AI/Front-End-Auto-Test repo:
-
-./runner-start.sh FedML-AI/FedML fedml-runner 30 AXRYPLZLZN6XVJB3BAIXSP3EMFC7U /home/fedml/FedML4GitHubAction-Dev /home/fedml/FedML4GitHubAction /home/fedml/fedml_data
-./runner-start.sh FedML-AI/Front-End-Auto-Test webtest-runner 6 AXRYPL57ZD35ZGDWZKRKFHLEMGLTK /home/fedml/FedML4GitHubAction-Dev /home/fedml/FedML4GitHubAction /home/fedml/fedml_data
+bash main.sh FedML-AI/FedML AXRYPLZLZN6XVJB3BAIXSP3EMFC7U
 
-./runner-start.sh FedML-AI/FedML fedml-runner 30 AXRYPL6CCBH24ZVRSUEAYTTEMKD56 /home/chaoyanghe/sourcecode/FedML4GitHubAction-Dev /home/chaoyanghe/sourcecode/FedML4GitHubAction /home/chaoyanghe/fedml_data
-./runner-start.sh FedML-AI/Front-End-Auto-Test webtest-runner 6 AXRYPL57ZD35ZGDWZKRKFHLEMGLTK /home/chaoyanghe/sourcecode/FedML4GitHubAction-Dev /home/chaoyanghe/sourcecode/FedML4GitHubAction /home/chaoyanghe/fedml_data
+bash main.sh Qigemingziba/FedML AGMK3PYAURK7QSRM475HF6LGN7L6A

devops/dockerfile/github-action-runner/WindowsDockerfile

@@ -0,0 +1,22 @@
+# ARG BASE_IMAGE=python:3.11
+
+# 使用 Windows Server Core 作为基础镜像
+FROM mcr.microsoft.com/windows/servercore:ltsc2022
+
+# 下载并安装 Python 3.11
+SHELL ["powershell", "-Command"]
+RUN Invoke-WebRequest -Uri https://www.python.org/ftp/python/3.11.0/python-3.11.0-amd64.exe -OutFile python-3.11.0-amd64.exe; \
+    Start-Process python-3.11.0-amd64.exe -ArgumentList '/quiet InstallAllUsers=1 PrependPath=1' -NoNewWindow -Wait; \
+    Remove-Item -Force python-3.11.0-amd64.exe
+
+# Create a folder under the drive root
+RUN mkdir actions-runner; cd actions-runner
+# Download the latest runner package
+RUN Invoke-WebRequest -Uri https://github.com/actions/runner/releases/download/v2.317.0/actions-runner-win-x64-2.317.0.zip -OutFile actions-runner-win-x64-2.317.0.zip
+# Extract the installer
+RUN Add-Type -AssemblyName System.IO.Compression.FileSystem ; [System.IO.Compression.ZipFile]::ExtractToDirectory("$PWD/actions-runner-win-x64-2.317.0.zip", "$PWD")
+
+RUN ./config.cmd --url https://github.com/Qigemingziba/FedML --token AGMK3P3JNXYCBCEGMET7T6DGNQSVW
+CMD ./run.cmd
+
+

devops/dockerfile/github-action-runner/build_batch.sh

@@ -0,0 +1,12 @@
+tag="0.1.0"
+
+platform="linux/amd64"
+
+echo "build python:3.11"
+docker build --no-cache --platform $platform --build-arg BASE_IMAGE=python:3.11 -t fedml/action_runner_3.11_linux64:$tag -f ./Dockerfile .
+echo "build python:3.10"
+docker build --no-cache  --platform $platform --build-arg BASE_IMAGE=python:3.10 -t fedml/action_runner_3.10_linux64:$tag -f ./Dockerfile .
+echo "build python:3.9"
+docker build --no-cache --platform $platform --build-arg BASE_IMAGE=python:3.9 -t fedml/action_runner_3.9_linux64:$tag -f ./Dockerfile .
+echo "build python:3.8"
+docker build --no-cache --platform $platform --build-arg BASE_IMAGE=python:3.8 -t fedml/action_runner_3.8_linux64:$tag -f ./Dockerfile .

devops/dockerfile/github-action-runner/build_push.sh

@@ -0,0 +1 @@
+bash build.sh

devops/dockerfile/github-action-runner/build_test.sh

@@ -0,0 +1,2 @@
+docker login
+docker build -t fedml/action_runner_3.11_linux64:0.1 -f ./Dockerfile .

devops/dockerfile/github-action-runner/main.sh

@@ -0,0 +1,45 @@
+REPO=$1
+ACCESS_TOKEN=$2
+DOCKER_PULL=false
+ARCH=linux64
+TAG="0.1.0"
+
+if [ $# != 2 ]; then
+  echo "Please provide two arguments."
+  echo "./runner-start.sh [YourGitRepo][YourGitHubRunnerToken]"
+  exit -1
+fi
+
+# List of Docker container names
+# containers=("fedml/action_runner_3.8_$ARCH:0.1.0" "fedml/action_runner_3.9_$ARCH:0.1.0" "fedml/action_runner_3.10_$ARCH:0.1.0" "fedml/action_runner_3.11_$ARCH:0.1.0")
+containers=("action_runner_3.8_$ARCH" "action_runner_3.9_$ARCH" "action_runner_3.10_$ARCH" "action_runner_3.11_$ARCH")
+python_versions=("python3.8" "python3.9" "python3.10" "python3.11")
+
+
+# Iterate through each container
+for container_index in "${!containers[@]}"; do
+
+    container=${containers[$container_index]}
+    # Find the running container
+    if [ "$DOCKER_PULL" = "true" ]; then
+        echo "docker pull fedml/$container:$TAG"
+        docker pull fedml/$container:$TAG
+    fi
+    # docker stop `sudo docker ps |grep ${TAG}- |awk -F' ' '{print $1}'`
+
+    running_container=$(docker ps -a | grep $container | awk -F ' ' '{print $1}')
+
+    if [ -n "$running_container" ]; then
+        # Stop the running container
+        echo "Stopping running container: $container}"
+        docker rm "$running_container"
+    else
+        echo "No running container found for: $container"
+    fi
+    # docker pull $container
+    ACT_NAME=${containers[$container_index]}
+    docker run --rm --name $ACT_NAME --env REPO=$REPO --env ACCESS_TOKEN=$ACCESS_TOKEN -d fedml/${containers[$container_index]}:$TAG bash ./start.sh ${REPO} ${ACCESS_TOKEN} ${python_versions[$container_index]}
+
+done
+echo "Script completed."
+

devops/dockerfile/github-action-runner/start.sh

@@ -2,13 +2,15 @@
 
 ORGANIZATION=$1
 ACCESS_TOKEN=$2
+PYTHON_VERSION=$3
 
 echo $ORGANIZATION
 echo $ACCESS_TOKEN
+echo $PYTHON_VERSION
 
 cd /home/fedml/actions-runner
 
-RUNNER_ALLOW_RUNASROOT="1" ./config.sh --url https://github.com/${ORGANIZATION} --token ${ACCESS_TOKEN}
+RUNNER_ALLOW_RUNASROOT="1" ./config.sh --url https://github.com/${ORGANIZATION} --token ${ACCESS_TOKEN} --labels self-hosted,Linux,X64,$PYTHON_VERSION
 
 cleanup() {
     echo "Removing runner..."

devops/dockerfile/github-action-runner/windows

@@ -0,0 +1,13 @@
+# 使用 Windows Server Core 作为基础镜像
+FROM mcr.microsoft.com/windows/servercore:ltsc2022
+
+# 设置 PowerShell 作为默认 shell
+SHELL ["powershell", "-Command"]
+
+# 示例：下载并安装 Python 3.11
+RUN Invoke-WebRequest -Uri https://www.python.org/ftp/python/3.11.0/python-3.11.0-amd64.exe -OutFile python-3.11.0-amd64.exe; \
+    Start-Process python-3.11.0-amd64.exe -ArgumentList '/quiet InstallAllUsers=1 PrependPath=1' -NoNewWindow -Wait; \
+    Remove-Item -Force python-3.11.0-amd64.exe
+
+# 设置默认命令
+CMD ["python"]

devops/scripts/install-fedml.sh

@@ -0,0 +1,2 @@
+cd python
+pip install -e ./

devops/scripts/sync-fedml-pip.sh

@@ -24,7 +24,7 @@ else
   fi
 fi
 
-mkdir -p /home/fedml/fedml_data
-cp -Rf /home/fedml/fedml_data_host/* /home/fedml/fedml_data
+mkdir -p ./fedml/fedml_data
+cp -Rf ./fedml/fedml_data_host/* ./fedml/fedml_data
 
 exit 0

python/examples/federate/cross_silo/cuda_rpc_fedavg_mnist_lr_example/README.md

@@ -26,7 +26,7 @@ For info on `trpc_master_config_path` refer to `python/examples/cross_silo/cuda_
 
 Example is provided at:
 
-`python/examples/cross_silo/cuda_rpc_fedavg_mnist_lr_example/one_line`
+`python/examples/federate/cross_silo/cuda_rpc_fedavg_mnist_lr_example/one_line`
 ### Training Script
 
 At the client side, the client ID (a.k.a rank) starts from 1.

python/examples/launch/examples/launch/hello_world/launch_config/fedml_config.yaml

@@ -0,0 +1,14 @@
+containerize: false
+data_args:
+  dataset_name: mnist
+  dataset_path: ./dataset
+  dataset_type: csv
+environment_args:
+  bootstrap: fedml_bootstrap_generated.sh
+model_args:
+  input_dim: '784'
+  model_cache_path: /Users/alexliang/fedml_models
+  model_name: lr
+  output_dim: '10'
+training_params:
+  learning_rate: 0.004

python/examples/launch/hello_job.yaml

@@ -56,7 +56,7 @@ computing:
   maximum_cost_per_hour: $3000   # max cost per hour for your job per gpu card
   #allow_cross_cloud_resources: true # true, false
   #device_type: CPU              # options: GPU, CPU, hybrid
-  resource_type: RTX-4090       # e.g., A100-80G, please check the resource type list by "fedml show-resource-type" or visiting URL: https://open.fedml.ai/accelerator_resource_type
+  resource_type: A100-80GB-SXM       # e.g., A100-80G, please check the resource type list by "fedml show-resource-type" or visiting URL: https://open.fedml.ai/accelerator_resource_type
 
 data_args:
   dataset_name: mnist

python/examples/launch/hello_world/hello_world.py

@@ -1,6 +1,5 @@
 import os
 import time
-
 import fedml
 
 if __name__ == "__main__":

python/examples/launch/serve_job_mnist.yaml

@@ -35,4 +35,4 @@ computing:
   maximum_cost_per_hour: $3000   # max cost per hour for your job per gpu card
   #allow_cross_cloud_resources: true # true, false
   #device_type: CPU              # options: GPU, CPU, hybrid
-  resource_type: A100-80G       # e.g., A100-80G, please check the resource type list by "fedml show-resource-type" or visiting URL: https://open.fedml.ai/accelerator_resource_type
+  resource_type: A100-80GB-SXM   # e.g., A100-80G, please check the resource type list by "fedml show-resource-type" or visiting URL: https://open.fedml.ai/accelerator_resource_type

python/examples/train/mnist_train/examples/train/mnist_train/launch_config/fedml_config.yaml

@@ -0,0 +1,3 @@
+containerize: false
+environment_args:
+  bootstrap: fedml_bootstrap_generated.sh

python/examples/train/mnist_train/train.py

@@ -0,0 +1,98 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+import torchvision
+import torchvision.transforms as transforms
+from torch.utils.data import DataLoader
+import fedml
+# Set random seed for reproducibility
+torch.manual_seed(42)
+
+# Define hyperparameters
+batch_size = 64
+learning_rate = 0.001
+num_epochs = 3
+
+# Prepare dataset and data loaders
+transform = transforms.Compose([
+    transforms.ToTensor(),  # Convert image to tensor, normalize to [0, 1]
+    transforms.Normalize((0.5,), (0.5,))  # Normalize with mean and std deviation of 0.5
+])
+
+train_dataset = torchvision.datasets.MNIST(root='./data', train=True, transform=transform, download=True)
+train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
+
+test_dataset = torchvision.datasets.MNIST(root='./data', train=False, transform=transform, download=True)
+test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)
+
+# Define a simple convolutional neural network model
+class SimpleCNN(nn.Module):
+    def __init__(self):
+        super(SimpleCNN, self).__init__()
+        self.conv1 = nn.Conv2d(1, 16, kernel_size=5, padding=2)
+        self.conv2 = nn.Conv2d(16, 32, kernel_size=5, padding=2)
+        self.fc1 = nn.Linear(32 * 7 * 7, 128)
+        self.fc2 = nn.Linear(128, 10)
+
+    def forward(self, x):
+        x = torch.relu(self.conv1(x))
+        x = torch.max_pool2d(x, kernel_size=2, stride=2)
+        x = torch.relu(self.conv2(x))
+        x = torch.max_pool2d(x, kernel_size=2, stride=2)
+        x = x.view(-1, 32 * 7 * 7)
+        x = torch.relu(self.fc1(x))
+        x = self.fc2(x)
+        return x
+
+model = SimpleCNN()
+
+# Define loss function and optimizer
+criterion = nn.CrossEntropyLoss()
+optimizer = optim.Adam(model.parameters(), lr=learning_rate)
+
+# Train the model
+for epoch in range(num_epochs):
+
+    # Evaluate the model on the test set during training
+    model.eval()
+    with torch.no_grad():
+        correct = 0
+        total = 0
+        for images, labels in test_loader:
+            outputs = model(images)
+            _, predicted = torch.max(outputs.data, 1)
+            total += labels.size(0)
+            correct += (predicted == labels).sum().item()
+        acc = 100 * correct / total
+        fedml.mlops.log_metric({"epoch":epoch, "acc": acc})
+
+    model.train()
+    for images, labels in train_loader:
+        # Forward pass
+        outputs = model(images)
+        loss = criterion(outputs, labels)
+
+        # Backward and optimize
+        optimizer.zero_grad()
+        loss.backward()
+        optimizer.step()
+
+# Final evaluation on the test set
+model.eval()
+with torch.no_grad():
+    correct = 0
+    total = 0
+    for images, labels in test_loader:
+        outputs = model(images)
+        _, predicted = torch.max(outputs.data, 1)
+        total += labels.size(0)
+        correct += (predicted == labels).sum().item()
+
+    acc = 100 * correct / total
+    print('Final Test Accuracy: {:.2f} %'.format(acc))
+    fedml.mlops.log_metric({"epoch":num_epochs, "acc": acc})
+
+fedml.mlops.log_model(f"model-file@test", "./simple_cnn.pth")
+# # Save the model parameters
+# torch.save(model.state_dict(), 'simple_cnn.pth')
+# print('Model saved to simple_cnn.pth')

python/examples/train/mnist_train/train.yaml

@@ -0,0 +1,50 @@
+# Local directory where your source code resides.
+# It should be the relative path to this job yaml file or the absolute path.
+# If your job doesn't contain any source code, it can be empty.
+workspace: .
+
+# Running entry commands which will be executed as the job entry point.
+# If an error occurs, you should exit with a non-zero code, e.g. exit 1.
+# Otherwise, you should exit with a zero code, e.g. exit 0.
+# Support multiple lines, which can not be empty.
+job: |
+    echo "current job id: $FEDML_CURRENT_RUN_ID"
+    echo "current edge id: $FEDML_CURRENT_EDGE_ID"
+    echo "Hello, Here is the launch platform."
+    echo "Current directory is as follows."
+    pwd
+    python3 train.py
+    echo "training job finished."
+
+# If you want to use the job created by the MLOps platform,
+# just uncomment the following three, then set job_id and config_id to your desired job id and related config.
+#job_args:
+#  job_id: 2070
+#  config_id: 111
+
+# If you want to create the job with specific name, just uncomment the following line and set job_name to your desired job name
+#job_name: cv_job
+
+job_type: train              # options: train, deploy, federate
+
+# train subtype: general_training, single_machine_training, cluster_distributed_training, cross_cloud_training
+# federate subtype: cross_silo, simulation, web, smart_phone
+# deploy subtype: none
+job_subtype: generate_training
+
+# containerize
+containerize: false
+
+# Bootstrap shell commands which will be executed before running entry commands.
+# Support multiple lines, which can be empty.
+bootstrap: |
+  # pip install -r requirements.txt
+  echo "Bootstrap finished."
+
+computing:
+  minimum_num_gpus: 1           # minimum # of GPUs to provision
+  maximum_cost_per_hour: $3000   # max cost per hour for your job per gpu card
+  #allow_cross_cloud_resources: true # true, false
+  #device_type: CPU              # options: GPU, CPU, hybrid
+  resource_type: A100-80GB-SXM       # e.g., A100-80G, please check the resource type list by "fedml show-resource-type" or visiting URL: https://open.fedml.ai/accelerator_resource_type
+

python/fedml/__init__.py

@@ -452,28 +452,14 @@ def _init_multiprocessing():
     """
     if platform.system() == "Windows":
         if multiprocessing.get_start_method() != "spawn":
-            # force all platforms (Windows) to use the same way (spawn) for multiprocessing
+            # force all platforms (Windows/Linux/macOS) to use the same way (spawn) for multiprocessing
             multiprocessing.set_start_method("spawn", force=True)
     else:
         if multiprocessing.get_start_method() != "fork":
-            # force all platforms (Linux/macOS) to use the same way (fork) for multiprocessing
+            # force all platforms (Windows/Linux/macOS) to use the same way (fork) for multiprocessing
             multiprocessing.set_start_method("fork", force=True)
 
 
-def get_multiprocessing_context():
-    if platform.system() == "Windows":
-        return multiprocessing.get_context("spawn")
-    else:
-        return multiprocessing.get_context("fork")
-
-
-def get_process(target=None, args=None):
-    if platform.system() == "Windows":
-        return multiprocessing.Process(target=target, args=args)
-    else:
-        return multiprocessing.get_context("fork").Process(target=target, args=args)
-
-
 def set_env_version(version):
     set_env_kv("FEDML_ENV_VERSION", version)
     load_env()

python/fedml/api/__init__.py

@@ -270,6 +270,9 @@ def model_deploy(name, endpoint_name, endpoint_id, local, master_ids, worker_ids
 def model_run(endpoint_id, json_string):
     model_module.run(endpoint_id, json_string)
 
+def get_endpoint(endpoint_id):
+    return model_module.get_endpoint(endpoint_id)
+
 
 def endpoint_delete(endpoint_id):
     model_module.delete_endpoint(endpoint_id)

python/fedml/api/api_test.py

@@ -4,9 +4,9 @@
 import fedml
 
 # Login
-fedml.set_env_version("local")
+fedml.set_env_version("test")
 fedml.set_local_on_premise_platform_port(18080)
-error_code, error_msg = fedml.api.fedml_login(api_key="1316b93c82da40ce90113a2ed12f0b14")
+error_code, error_msg = fedml.api.fedml_login(api_key="")
 if error_code != 0:
     print("API Key is invalid!")
     exit(1)
@@ -19,7 +19,7 @@
 
 # Launch job
 launch_result_list = list()
-for i in range(0, 1):
+for i in range(0, 10):
     launch_result = fedml.api.launch_job(yaml_file)
     launch_result_list.append(launch_result)
     # launch_result = fedml.api.launch_job_on_cluster(yaml_file, "alex-cluster")

python/fedml/api/modules/model.py

@@ -320,6 +320,19 @@ def run(endpoint_id: str, json_string: str) -> bool:
         click.echo("Failed to run model.")
         return False
 
+def get_endpoint(endpoint_id: str):
+    api_key = get_api_key()
+    if api_key == "":
+        click.echo('''
+                Please use one of the ways below to login first:
+                (1) CLI: `fedml login $api_key`
+                (2) API: fedml.api.fedml_login(api_key=$api_key)
+                ''')
+        return False
+
+    endpoint_detail_result = FedMLModelCards.get_instance().query_endpoint_detail_api(user_api_key=api_key, 
+                                                                endpoint_id=endpoint_id)
+    return endpoint_detail_result
 
 def delete_endpoint(endpoint_id: str) -> bool:
     api_key = get_api_key()

python/fedml/computing/scheduler/comm_utils/network_util.py

@@ -0,0 +1,18 @@
+import os
+from fedml.computing.scheduler.model_scheduler.device_client_constants import ClientConstants
+
+
+def return_this_device_connectivity_type() -> str:
+    """
+    Return -> "http" | "http_proxy" |"mqtt"
+    """
+    # Get the environmental variable's value and convert to lower case.
+    env_conn_type = os.getenv(ClientConstants.ENV_CONNECTION_TYPE_KEY, "").lower()
+    if env_conn_type in [
+        ClientConstants.WORKER_CONNECTIVITY_TYPE_HTTP,
+        ClientConstants.WORKER_CONNECTIVITY_TYPE_HTTP_PROXY,
+        ClientConstants.WORKER_CONNECTIVITY_TYPE_MQTT
+    ]:
+        return env_conn_type
+    else:
+        return ClientConstants.WORKER_CONNECTIVITY_TYPE_DEFAULT

python/fedml/computing/scheduler/model_scheduler/device_client_constants.py

@@ -97,6 +97,12 @@ class ClientConstants(object):
     INFERENCE_INFERENCE_SERVER_VERSION = "v2"
     INFERENCE_REQUEST_TIMEOUT = 30
 
+    ENV_CONNECTION_TYPE_KEY = "FEDML_CONNECTION_TYPE"
+    WORKER_CONNECTIVITY_TYPE_HTTP = "http"
+    WORKER_CONNECTIVITY_TYPE_HTTP_PROXY = "http_proxy"
+    WORKER_CONNECTIVITY_TYPE_MQTT = "mqtt"
+    WORKER_CONNECTIVITY_TYPE_DEFAULT = WORKER_CONNECTIVITY_TYPE_HTTP
+
     MSG_MODELOPS_DEPLOYMENT_STATUS_INITIALIZING = "INITIALIZING"
     MSG_MODELOPS_DEPLOYMENT_STATUS_DEPLOYING = "DEPLOYING"
     MSG_MODELOPS_DEPLOYMENT_STATUS_INFERRING = "INFERRING"

python/fedml/computing/scheduler/model_scheduler/device_model_cache.py

@@ -344,9 +344,13 @@ def get_result_item_info(self, result_item):
             result_payload = result_item_json["result"]
         return device_id, replica_no, result_payload
 
-    def get_idle_device(self, end_point_id, end_point_name,
-                        model_name, model_version,
-                        check_end_point_status=True, limit_specific_model_version=False):
+    def get_idle_device(self,
+                        end_point_id,
+                        end_point_name,
+                        model_name,
+                        model_version,
+                        check_end_point_status=True,
+                        limit_specific_model_version=False):
         # Deprecated the model status logic, query directly from the deployment result list
         idle_device_list = list()
 
@@ -365,7 +369,7 @@ def get_idle_device(self, end_point_id, end_point_name,
                 if "model_status" in result_payload and result_payload["model_status"] == "DEPLOYED":
                     idle_device_list.append({"device_id": device_id, "end_point_id": end_point_id})
 
-        logging.info(f"{len(idle_device_list)} devices this model has on it: {idle_device_list}")
+        logging.debug(f"{len(idle_device_list)} devices this model has on it: {idle_device_list}")
 
         if len(idle_device_list) <= 0:
             return None, None
@@ -394,7 +398,7 @@ def get_idle_device(self, end_point_id, end_point_name,
             logging.info("Inference Device selection Failed:")
             logging.info(e)
 
-        logging.info(f"Using Round Robin, the device index is {selected_device_index}")
+        logging.debug(f"Using Round Robin, the device index is {selected_device_index}")
         idle_device_dict = idle_device_list[selected_device_index]
 
         # Note that within the same endpoint_id, there could be one device with multiple same models
@@ -407,7 +411,7 @@ def get_idle_device(self, end_point_id, end_point_name,
         # Find deployment result from the target idle device.
         try:
             for result_item in result_list:
-                logging.info("enter the for loop")
+                logging.debug("enter the for loop")
                 device_id, _, result_payload = self.get_result_item_info(result_item)
                 found_end_point_id = result_payload["end_point_id"]
                 found_end_point_name = result_payload["end_point_name"]
@@ -421,7 +425,7 @@ def get_idle_device(self, end_point_id, end_point_name,
                     if same_model_device_rank > 0:
                         same_model_device_rank -= 1
                         continue
-                    logging.info(f"The chosen device is {device_id}")
+                    logging.debug(f"The chosen device is {device_id}")
                     return result_payload, device_id
         except Exception as e:
             logging.info(str(e))

python/fedml/computing/scheduler/model_scheduler/device_model_cards.py

@@ -14,7 +14,6 @@
 
 from fedml.core.common.singleton import Singleton
 from fedml.computing.scheduler.model_scheduler.modelops_configs import ModelOpsConfigs
-from fedml.computing.scheduler.model_scheduler.device_model_deployment import get_model_info
 from fedml.computing.scheduler.model_scheduler.device_server_constants import ServerConstants
 from fedml.computing.scheduler.model_scheduler.device_model_object import FedMLModelList, FedMLEndpointDetail
 from fedml.computing.scheduler.model_scheduler.device_client_constants import ClientConstants

python/fedml/computing/scheduler/model_scheduler/device_model_inference.py

@@ -210,7 +210,8 @@ async def _predict(
                 return inference_response
 
             # Found idle inference device
-            idle_device, end_point_id, model_id, model_name, model_version, inference_host, inference_output_url = \
+            idle_device, end_point_id, model_id, model_name, model_version, inference_host, inference_output_url,\
+                connectivity_type = \
                 found_idle_inference_device(in_end_point_id, in_end_point_name, in_model_name, in_model_version)
             if idle_device is None or idle_device == "":
                 FEDML_MODEL_CACHE.update_pending_requests_counter(end_point_id, decrease=True)
@@ -229,19 +230,22 @@ async def _predict(
             model_metrics.set_start_time(start_time)
 
             # Send inference request to idle device
-            logging.info("inference url {}.".format(inference_output_url))
+            logging.debug("inference url {}.".format(inference_output_url))
             if inference_output_url != "":
                 input_list = input_json.get("inputs", input_json)
                 stream_flag = input_json.get("stream", False)
                 input_list["stream"] = input_list.get("stream", stream_flag)
                 output_list = input_json.get("outputs", [])
+
+                # main execution of redirecting the inference request to the idle device
                 inference_response = await send_inference_request(
                     idle_device,
                     end_point_id,
                     inference_output_url,
                     input_list,
                     output_list,
-                    inference_type=in_return_type)
+                    inference_type=in_return_type,
+                    connectivity_type=connectivity_type)
 
             # Calculate model metrics
             try:
@@ -304,37 +308,40 @@ def found_idle_inference_device(end_point_id, end_point_name, in_model_name, in_
     inference_host = ""
     inference_output_url = ""
     model_version = ""
+    connectivity_type = ""
+
     # Found idle device (TODO: optimize the algorithm to search best device for inference)
     payload, idle_device = FEDML_MODEL_CACHE. \
         get_idle_device(end_point_id, end_point_name, in_model_name, in_model_version)
-    if payload is not None:
-        logging.info("found idle deployment result {}".format(payload))
-        deployment_result = payload
-        model_name = deployment_result["model_name"]
-        model_version = deployment_result["model_version"]
-        model_id = deployment_result["model_id"]
-        end_point_id = deployment_result["end_point_id"]
-        inference_output_url = deployment_result["model_url"]
+    if payload:
+        model_name = payload["model_name"]
+        model_version = payload["model_version"]
+        model_id = payload["model_id"]
+        end_point_id = payload["end_point_id"]
+        inference_output_url = payload["model_url"]
+        connectivity_type = \
+            payload.get("connectivity_type",
+                        ClientConstants.WORKER_CONNECTIVITY_TYPE_DEFAULT)
         url_parsed = urlparse(inference_output_url)
         inference_host = url_parsed.hostname
     else:
         logging.info("not found idle deployment result")
 
-    return idle_device, end_point_id, model_id, model_name, model_version, inference_host, inference_output_url
+    res = (idle_device, end_point_id, model_id, model_name, model_version, inference_host, inference_output_url,
+           connectivity_type)
+    logging.debug(f"found idle device with metrics: {res}")
+
+    return res
 
 
 async def send_inference_request(idle_device, end_point_id, inference_url, input_list, output_list,
-                                 inference_type="default", has_public_ip=True):
+                                 inference_type="default",
+                                 connectivity_type=ClientConstants.WORKER_CONNECTIVITY_TYPE_DEFAULT):
     request_timeout_sec = FEDML_MODEL_CACHE.get_endpoint_settings(end_point_id) \
         .get("request_timeout_sec", ClientConstants.INFERENCE_REQUEST_TIMEOUT)
 
     try:
-        http_infer_available = os.getenv("FEDML_INFERENCE_HTTP_AVAILABLE", True)
-        if not http_infer_available:
-            if http_infer_available == "False" or http_infer_available == "false":
-                http_infer_available = False
-
-        if http_infer_available:
+        if connectivity_type == ClientConstants.WORKER_CONNECTIVITY_TYPE_HTTP:
             response_ok = await FedMLHttpInference.is_inference_ready(
                 inference_url,
                 timeout=request_timeout_sec)
@@ -345,24 +352,25 @@ async def send_inference_request(idle_device, end_point_id, inference_url, input
                     output_list,
                     inference_type=inference_type,
                     timeout=request_timeout_sec)
-                logging.info(f"Use http inference. return {response_ok}")
+                logging.debug(f"Use http inference. return {response_ok}")
                 return inference_response
-
-        response_ok = await FedMLHttpProxyInference.is_inference_ready(
-            inference_url,
-            timeout=request_timeout_sec)
-        if response_ok:
-            response_ok, inference_response = await FedMLHttpProxyInference.run_http_proxy_inference_with_request(
-                end_point_id,
+        elif connectivity_type == ClientConstants.WORKER_CONNECTIVITY_TYPE_HTTP_PROXY:
+            logging.warning("Use http proxy inference.")
+            response_ok = await FedMLHttpProxyInference.is_inference_ready(
                 inference_url,
-                input_list,
-                output_list,
-                inference_type=inference_type,
                 timeout=request_timeout_sec)
-            logging.info(f"Use http proxy inference. return {response_ok}")
-            return inference_response
-
-        if not has_public_ip:
+            if response_ok:
+                response_ok, inference_response = await FedMLHttpProxyInference.run_http_proxy_inference_with_request(
+                    end_point_id,
+                    inference_url,
+                    input_list,
+                    output_list,
+                    inference_type=inference_type,
+                    timeout=request_timeout_sec)
+                logging.info(f"Use http proxy inference. return {response_ok}")
+                return inference_response
+        elif connectivity_type == ClientConstants.WORKER_CONNECTIVITY_TYPE_MQTT:
+            logging.warning("Use mqtt inference.")
             agent_config = {"mqtt_config": Settings.mqtt_config}
             mqtt_inference = FedMLMqttInference(
                 agent_config=agent_config,
@@ -385,7 +393,8 @@ async def send_inference_request(idle_device, end_point_id, inference_url, input
 
             logging.info(f"Use mqtt inference. return {response_ok}.")
             return inference_response
-        return {"error": True, "message": "Failed to use http, http-proxy for inference, no response from replica."}
+        else:
+            return {"error": True, "message": "Failed to use http, http-proxy for inference, no response from replica."}
     except Exception as e:
         inference_response = {"error": True,
                               "message": f"Exception when using http, http-proxy and mqtt "

python/fedml/computing/scheduler/model_scheduler/master_job_runner.py

@@ -250,14 +250,6 @@ def process_deployment_result_message(self, topic=None, payload=None):
         logging.info(f"Endpoint {end_point_id}; Device {device_id}; replica {replica_no}; "
                      f"run_operation {run_operation} model status {model_status}.")
 
-        # OPTIONAL DEBUG PARAMS
-        # this_run_controller = self.model_runner_mapping[run_id_str].replica_controller
-        # logging.info(f"The current replica controller state is "
-        #              f"Total version diff num {this_run_controller.total_replica_version_diff_num}")
-        # logging.info(f"self.request_json now {self.request_json}")    # request_json will be deprecated
-        # this_run_request_json = self.request_json
-        # logging.info(f"self.request_json now {this_run_request_json}")
-
         # Set redis + sqlite deployment result
         FedMLModelCache.get_instance().set_redis_params(self.redis_addr, self.redis_port, self.redis_password)
 
@@ -461,7 +453,6 @@ def process_deployment_result_message(self, topic=None, payload=None):
             time.sleep(3)
             self.trigger_completed_event()
 
-
     def cleanup_runner_process(self, run_id):
         ServerConstants.cleanup_run_process(run_id, not_kill_subprocess=True)
 

python/fedml/computing/scheduler/model_scheduler/worker_job_runner.py

@@ -9,6 +9,8 @@
 from abc import ABC
 import yaml
 from fedml.computing.scheduler.comm_utils.job_utils import JobRunnerUtils
+from fedml.computing.scheduler.comm_utils.network_util import return_this_device_connectivity_type
+
 from fedml.core.mlops import MLOpsRuntimeLog
 from fedml.computing.scheduler.comm_utils import file_utils
 from .device_client_constants import ClientConstants
@@ -234,8 +236,11 @@ def run_impl(self, run_extend_queue_list, sender_message_center,
         running_model_name, inference_output_url, inference_model_version, model_metadata, model_config = \
             "", "", model_version, {}, {}
 
+        # ip and connectivity
+        worker_ip = GeneralConstants.get_ip_address(self.request_json)
+        connectivity = return_this_device_connectivity_type()
+
         if op == "add":
-            worker_ip = GeneralConstants.get_ip_address(self.request_json)
             for rank in range(prev_rank + 1, prev_rank + 1 + op_num):
                 try:
                     running_model_name, inference_output_url, inference_model_version, model_metadata, model_config = \
@@ -269,7 +274,9 @@ def run_impl(self, run_extend_queue_list, sender_message_center,
                     result_payload = self.send_deployment_results(
                         end_point_name, self.edge_id, ClientConstants.MSG_MODELOPS_DEPLOYMENT_STATUS_DEPLOYED,
                         model_id, model_name, inference_output_url, model_version, inference_port_external,
-                        inference_engine, model_metadata, model_config, replica_no=rank + 1)
+                        inference_engine, model_metadata, model_config, replica_no=rank + 1,
+                        connectivity=connectivity
+                    )
 
                     if inference_port_external != inference_port:
                         # Save internal port to local db
@@ -278,16 +285,16 @@ def run_impl(self, run_extend_queue_list, sender_message_center,
                         result_payload = self.construct_deployment_results(
                             end_point_name, self.edge_id, ClientConstants.MSG_MODELOPS_DEPLOYMENT_STATUS_DEPLOYED,
                             model_id, model_name, inference_output_url, model_version, inference_port,
-                            inference_engine, model_metadata, model_config, replica_no=rank + 1)
+                            inference_engine, model_metadata, model_config, replica_no=rank + 1,
+                            connectivity=connectivity
+                        )
 
                     FedMLModelDatabase.get_instance().set_deployment_result(
                         run_id, end_point_name, model_name, model_version, self.edge_id,
                         json.dumps(result_payload), replica_no=rank + 1)
 
                     logging.info(f"Deploy replica {rank + 1} / {prev_rank + 1 + op_num} successfully.")
-                    time.sleep(5)
 
-            time.sleep(1)
             self.status_reporter.run_id = self.run_id
             self.status_reporter.report_client_id_status(
                 self.edge_id, ClientConstants.MSG_MLOPS_CLIENT_STATUS_FINISHED,
@@ -326,7 +333,6 @@ def run_impl(self, run_extend_queue_list, sender_message_center,
             return True
         elif op == "update" or op == "rollback":
             # Update is combine of delete and add
-            worker_ip = GeneralConstants.get_ip_address(self.request_json)
             for rank in replica_rank_to_update:
                 # Delete a replica (container) if exists
                 self.replica_handler.remove_replica(rank)
@@ -340,7 +346,8 @@ def run_impl(self, run_extend_queue_list, sender_message_center,
 
                 # TODO (Raphael) check if this will allow another job to seize the gpu during high concurrency:
                 try:
-                    JobRunnerUtils.get_instance().release_partial_job_gpu(run_id, self.edge_id, replica_occupied_gpu_ids)
+                    JobRunnerUtils.get_instance().release_partial_job_gpu(
+                        run_id, self.edge_id, replica_occupied_gpu_ids)
                 except Exception as e:
                     if op == "rollback":
                         pass
@@ -387,7 +394,7 @@ def run_impl(self, run_extend_queue_list, sender_message_center,
                         JobRunnerUtils.get_instance().release_partial_job_gpu(
                             run_id, self.edge_id, replica_occupied_gpu_ids)
 
-                    result_payload = self.send_deployment_results(
+                    self.send_deployment_results(
                         end_point_name, self.edge_id, ClientConstants.MSG_MODELOPS_DEPLOYMENT_STATUS_FAILED,
                         model_id, model_name, inference_output_url, inference_model_version, inference_port,
                         inference_engine, model_metadata, model_config)
@@ -402,15 +409,19 @@ def run_impl(self, run_extend_queue_list, sender_message_center,
                     result_payload = self.send_deployment_results(
                         end_point_name, self.edge_id, ClientConstants.MSG_MODELOPS_DEPLOYMENT_STATUS_DEPLOYED,
                         model_id, model_name, inference_output_url, model_version, inference_port_external,
-                        inference_engine, model_metadata, model_config, replica_no=rank + 1)
+                        inference_engine, model_metadata, model_config, replica_no=rank + 1,
+                        connectivity=connectivity
+                    )
 
                     if inference_port_external != inference_port:  # Save internal port to local db
                         logging.info("inference_port_external {} != inference_port {}".format(
                             inference_port_external, inference_port))
                         result_payload = self.construct_deployment_results(
                             end_point_name, self.edge_id, ClientConstants.MSG_MODELOPS_DEPLOYMENT_STATUS_DEPLOYED,
                             model_id, model_name, inference_output_url, model_version, inference_port,
-                            inference_engine, model_metadata, model_config, replica_no=rank + 1)
+                            inference_engine, model_metadata, model_config, replica_no=rank + 1,
+                            connectivity=connectivity
+                        )
 
                     FedMLModelDatabase.get_instance().set_deployment_result(
                         run_id, end_point_name, model_name, model_version, self.edge_id,
@@ -433,7 +444,8 @@ def run_impl(self, run_extend_queue_list, sender_message_center,
     def construct_deployment_results(self, end_point_name, device_id, model_status,
                                      model_id, model_name, model_inference_url,
                                      model_version, inference_port, inference_engine,
-                                     model_metadata, model_config, replica_no=1):
+                                     model_metadata, model_config, replica_no=1,
+                                     connectivity=ClientConstants.WORKER_CONNECTIVITY_TYPE_DEFAULT):
         deployment_results_payload = {"end_point_id": self.run_id, "end_point_name": end_point_name,
                                       "model_id": model_id, "model_name": model_name,
                                       "model_url": model_inference_url, "model_version": model_version,
@@ -444,6 +456,7 @@ def construct_deployment_results(self, end_point_name, device_id, model_status,
                                       "model_status": model_status,
                                       "inference_port": inference_port,
                                       "replica_no": replica_no,
+                                      "connectivity_type": connectivity,
                                       }
         return deployment_results_payload
 
@@ -466,30 +479,22 @@ def construct_deployment_status(self, end_point_name, device_id,
     def send_deployment_results(self, end_point_name, device_id, model_status,
                                 model_id, model_name, model_inference_url,
                                 model_version, inference_port, inference_engine,
-                                model_metadata, model_config, replica_no=1):
+                                model_metadata, model_config, replica_no=1,
+                                connectivity=ClientConstants.WORKER_CONNECTIVITY_TYPE_DEFAULT):
         deployment_results_topic = "model_device/model_device/return_deployment_result/{}/{}".format(
             self.run_id, device_id)
 
         deployment_results_payload = self.construct_deployment_results(
             end_point_name, device_id, model_status,
             model_id, model_name, model_inference_url,
             model_version, inference_port, inference_engine,
-            model_metadata, model_config, replica_no=replica_no)
+            model_metadata, model_config, replica_no=replica_no, connectivity=connectivity)
 
         logging.info("[client] send_deployment_results: topic {}, payload {}.".format(deployment_results_topic,
                                                                                       deployment_results_payload))
         self.message_center.send_message_json(deployment_results_topic, json.dumps(deployment_results_payload))
         return deployment_results_payload
 
-    def send_deployment_status(self, end_point_name, device_id,
-                               model_id, model_name, model_version,
-                               model_inference_url, model_status,
-                               inference_port=ClientConstants.MODEL_INFERENCE_DEFAULT_PORT,
-                               replica_no=1,     # start from 1
-                               ):
-        # Deprecated
-        pass
-
     def reset_devices_status(self, edge_id, status):
         self.status_reporter.run_id = self.run_id
         self.status_reporter.edge_id = edge_id

python/tests/cross-silo/run_cross_silo.sh

@@ -1,10 +1,10 @@
 #!/bin/bash
 set -e
 WORKSPACE=$(pwd)
-PROJECT_HOME=$WORKSPACE/../../
-cd $PROJECT_HOME
+# PROJECT_HOME=$WORKSPACE/../../
+# cd $PROJECT_HOME
 
-cd examples/cross_silo/mqtt_s3_fedavg_mnist_lr_example/custom_data_and_model
+cd examples/federate/cross_silo/mqtt_s3_fedavg_mnist_lr_example/custom_data_and_model
 
 # run client(s)
 RUN_ID="$(python -c "import uuid; print(uuid.uuid4().hex)")"

python/tests/smoke_test/cli/build.sh

@@ -16,7 +16,7 @@
 #  --help                     Show this message and exit.
 
 # build client package
-cd ../../../examples/cross_silo/mqtt_s3_fedavg_mnist_lr_example/one_line
+cd ../../../examples/federate/cross_silo/mqtt_s3_fedavg_mnist_lr_example/one_line
 echo "$PWD"
 
 SOURCE=client
@@ -30,4 +30,4 @@ SOURCE=server
 ENTRY=torch_server.py
 CONFIG=config
 DEST=./mlops
-fedml build -t server -sf $SOURCE -ep $ENTRY -cf $CONFIG -df $DEST
+fedml build -t server -sf $SOURCE -ep $ENTRY -cf $CONFIG -df $DEST

python/tests/test_deploy/test_deploy.py

@@ -0,0 +1,38 @@
+import os.path
+import time
+import fedml
+# Login
+fedml.set_env_version("test")
+fedml.set_local_on_premise_platform_port(18080)
+error_code, error_msg = fedml.api.fedml_login(api_key="")
+if error_code != 0:
+    raise Exception("API Key is invalid!")
+
+# Yaml file
+cur_dir = os.path.dirname(__file__)
+fedml_dir = os.path.dirname(cur_dir)
+python_dir = os.path.dirname(fedml_dir)
+yaml_file = os.path.join(python_dir, "examples", "launch", "serve_job_mnist.yaml")
+
+# Launch job
+launch_result_dict = {}
+launch_result_status = {}
+
+launch_result = fedml.api.launch_job(yaml_file)
+print("Endpoint id is", launch_result.inner_id)
+
+cnt = 0
+while 1:
+    try:
+        r = fedml.api.get_endpoint(endpoint_id=launch_result.inner_id)
+    except Exception as e:
+        raise Exception(f"FAILED to get endpoint:{launch_result.inner_id}. {e}")
+    if r.status == "DEPLOYED":
+        print("Deployment has been successfully!")
+        break 
+    elif r.status == "FAILED":
+        raise Exception("FAILED to deploy.")
+    time.sleep(1)
+    cnt += 1
+    if cnt %3 ==0:
+        print('Deployment status is', r.status)

python/tests/test_federate/test_federate.sh

@@ -0,0 +1,29 @@
+    #   - name: test simulation-sp
+    #     working-directory: ${{ steps.fedml_source_code_home.outputs.dir }}
+    #     run: |
+    #       cd ${{ format('{0}', steps.fedml_source_code_home.outputs.dir) }}/python
+WORKSPACE=`pwd`
+echo $WORKSPACE
+cd $WORKSPACE/python/examples/federate/quick_start/parrot
+python torch_fedavg_mnist_lr_one_line_example.py --cf fedml_config.yaml
+python torch_fedavg_mnist_lr_custum_data_and_model_example.py --cf fedml_config.yaml
+
+cd $WORKSPACE/python/examples/federate/simulation/sp_decentralized_mnist_lr_example
+python torch_fedavg_mnist_lr_step_by_step_example.py --cf fedml_config.yaml
+
+cd $WORKSPACE/python/examples/federate/simulation/sp_fednova_mnist_lr_example
+python torch_fednova_mnist_lr_step_by_step_example.py --cf fedml_config.yaml
+
+cd $WORKSPACE/python/examples/federate/simulation/sp_fedopt_mnist_lr_example
+python torch_fedopt_mnist_lr_step_by_step_example.py --cf fedml_config.yaml
+
+cd $WORKSPACE/python/examples/federate/simulation/sp_hierarchicalfl_mnist_lr_example
+python torch_hierarchicalfl_mnist_lr_step_by_step_example.py --cf fedml_config.yaml
+
+
+cd $WORKSPACE/python/examples/federate/simulation/sp_turboaggregate_mnist_lr_example
+python torch_turboaggregate_mnist_lr_step_by_step_example.py --cf fedml_config.yaml 
+
+
+cd $WORKSPACE/python/examples/federate/simulation/sp_vertical_mnist_lr_example
+python torch_vertical_mnist_lr_step_by_step_example.py --cf fedml_config.yaml 

python/tests/test_launch/test_launch.py

@@ -0,0 +1,49 @@
+import os.path
+import time
+import fedml
+from fedml.api.constants import RunStatus
+
+# Login
+fedml.set_env_version("test")
+fedml.set_local_on_premise_platform_port(18080)
+error_code, error_msg = fedml.api.fedml_login(api_key="")
+if error_code != 0:
+    raise Exception("API Key is invalid!")
+
+# Yaml file
+cur_dir = os.path.dirname(__file__)
+fedml_dir = os.path.dirname(cur_dir)
+python_dir = os.path.dirname(fedml_dir)
+yaml_file = os.path.join(python_dir, "examples", "launch", "hello_job.yaml")
+
+# Launch job
+
+launch_result = fedml.api.launch_job(yaml_file)
+
+# launch_result = fedml.api.launch_job_on_cluster(yaml_file, "alex-cluster")
+if launch_result.result_code != 0:
+    raise Exception(f"Failed to launch job. Reason: {launch_result.result_message}")
+
+# check job status
+while 1:
+    time.sleep(1)
+    # if 
+    #     if launch_result_status[run_id] == RunStatus.FINISHED:
+    #         continue
+    log_result = fedml.api.run_logs(launch_result.run_id, 1, 5)
+    if log_result is None or log_result.run_status is None:
+        raise Exception(f"Failed to get job status.")
+
+    print(f"run_id: {launch_result.run_id} run_status: {log_result.run_status}")
+
+    if log_result.run_status in [RunStatus.ERROR, RunStatus.FAILED]:
+        log_result = fedml.api.run_logs(launch_result.run_id, 1, 100)
+        if log_result is None or log_result.run_status is None:
+            raise Exception(f"run_id:{launch_result.run_id} run_status:{log_result.run_status} and failed to get run logs.")
+
+        raise Exception(f"run_id:{launch_result.run_id} run_status:{log_result.run_status} run logs: {log_result.log_line_list}")
+    if log_result.run_status == RunStatus.FINISHED:
+        print(f"Job finished successfully.")
+        break
+
+

python/tests/test_server/test_server.py

@@ -0,0 +1,30 @@
+import os.path
+import time
+import fedml
+from fedml.api.constants import RunStatus
+
+# Login
+fedml.set_env_version("test")
+fedml.set_local_on_premise_platform_port(18080)
+error_code, error_msg = fedml.api.fedml_login(api_key="")
+if error_code != 0:
+    raise Exception("API Key is invalid!")
+
+# Yaml file
+cur_dir = os.path.dirname(__file__)
+fedml_dir = os.path.dirname(cur_dir)
+python_dir = os.path.dirname(fedml_dir)
+yaml_file = os.path.join(python_dir, "examples", "launch", "serve_job_mnist.yaml")
+
+# Launch job
+launch_result_dict = {}
+launch_result_status = {}
+
+launch_result = fedml.api.launch_job(yaml_file)
+
+# launch_result = fedml.api.launch_job_on_cluster(yaml_file, "alex-cluster")
+if launch_result.result_code != 0:
+    raise Exception(f"Failed to launch job. Reason: {launch_result.result_message}")
+
+launch_result_dict[launch_result.run_id] = launch_result
+launch_result_status[launch_result.run_id] = RunStatus.STARTING

python/tests/test_train/test_train.py

@@ -0,0 +1,48 @@
+import os.path
+import time
+import fedml
+from fedml.api.constants import RunStatus
+
+# Login
+fedml.set_env_version("test")
+fedml.set_local_on_premise_platform_port(18080)
+error_code, error_msg = fedml.api.fedml_login(api_key="1316b93c82da40ce90113a2ed12f0b14")
+if error_code != 0:
+    raise Exception("API Key is invalid!")
+
+# Yaml file
+cur_dir = os.path.dirname(__file__)
+fedml_dir = os.path.dirname(cur_dir)
+python_dir = os.path.dirname(fedml_dir)
+yaml_file = os.path.join(python_dir, "examples", "train", "mnist_train", "train.yaml")
+
+# Launch job
+
+launch_result = fedml.api.launch_job(yaml_file)
+
+# launch_result = fedml.api.launch_job_on_cluster(yaml_file, "alex-cluster")
+if launch_result.result_code != 0:
+    raise Exception(f"Failed to launch job. Reason: {launch_result.result_message}")
+
+# check job status
+while 1:
+    time.sleep(1)
+    # if 
+    #     if launch_result_status[run_id] == RunStatus.FINISHED:
+    #         continue
+    log_result = fedml.api.run_logs(launch_result.run_id, 1, 5)
+    if log_result is None or log_result.run_status is None:
+        raise Exception(f"Failed to get job status.")
+
+    print(f"run_id: {launch_result.run_id} run_status: {log_result.run_status}")
+
+    if log_result.run_status in [RunStatus.ERROR, RunStatus.FAILED]:
+        log_result = fedml.api.run_logs(launch_result.run_id, 1, 100)
+        if log_result is None or log_result.run_status is None:
+            raise Exception(f"run_id:{launch_result.run_id} run_status:{log_result.run_status} and failed to get run logs.")
+
+        raise Exception(f"run_id:{launch_result.run_id} run_status:{log_result.run_status} run logs: {log_result.log_line_list}")
+    if log_result.run_status == RunStatus.FINISHED:
+        print(f"Job finished successfully.")
+        break
+