Merge pull request #686 from alex-liang-kh/dev/v0.7.0

update model deployment cli.

Author: fedml-alex

python/fedml/cli/model_deployment/device_model_deployment.py

@@ -38,6 +38,12 @@ def start_deployment(model_storage_local_path, inference_model_name, inference_e
     if sys_name == "Linux":
         os.system(sudo_prefix + "apt-get update")
         os.system(sudo_prefix + "apt-get install docker-ce docker-ce-cli containerd.io docker-compose-plugin")
+        os.system("distribution=$(. /etc/os-release;echo $ID$VERSION_ID) \
+      && curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
+      && curl -s -L https://nvidia.github.io/libnvidia-container/experimental/$distribution/libnvidia-container.list | \
+         sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
+         sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list")
+        os.system(sudo_prefix + "apt-get update")
         os.system(sudo_prefix + "apt-get install -y nvidia-docker2")
         os.system(sudo_prefix + "systemctl restart docker")
 

python/fedml/cli/model_deployment/device_server_runner.py

@@ -200,7 +200,7 @@ def run(self):
                 self.run_id, model_id, model_name, "",
                 str(ServerConstants.MODEL_INFERENCE_DEFAULT_PORT)),
             should_capture_stdout=False,
-            should_capture_stderr=True
+            should_capture_stderr=False
         )
         ServerConstants.save_learning_process(process.pid)
 
@@ -220,7 +220,7 @@ def run(self):
                 "model_inference_url"
             ],
             should_capture_stdout=False,
-            should_capture_stderr=True
+            should_capture_stderr=False
         )
         ServerConstants.save_learning_process(self.monitor_process.pid)
         self.release_client_mqtt_mgr()