Merge pull request #78819 from YutongTie-MSFT/patch-45

(AzureCXP) fixes MicrosftDocs/azure-docs#32753

Author: PRMerger7

articles/machine-learning/service/how-to-deploy-fpga-web-service.md

@@ -305,7 +305,7 @@ If you want to use TensorFlow Serving, you can [download a sample client](https:
 
 ```python
 # Using the grpc client in Azure ML Accelerated Models SDK package
-from azureml.accel.client import PredictionClient
+from azureml.accel import PredictionClient
 
 address = aks_service.scoring_uri
 ssl_enabled = address.startswith("https")
@@ -361,4 +361,4 @@ For information on securing FPGA web services, see the [Secure web services](how
 
 ## PBS Family VMs
 
-The PBS Family of Azure VMs contains Intel Arria 10 FPGAs.  It will show as "Standard PBS Family vCPUs" when you check your Azure quota allocation.  The PB6 VM has six vCPUs and one FPGA, and it will automatically be provisioned by Azure ML as part of deploying a model to an FPGA.  It is only used with Azure ML, and it cannot run arbitrary bitstreams.  For example, you will not be able to flash the FPGA with bitstreams to do encryption, encoding, etc. 
+The PBS Family of Azure VMs contains Intel Arria 10 FPGAs.  It will show as "Standard PBS Family vCPUs" when you check your Azure quota allocation.  The PB6 VM has six vCPUs and one FPGA, and it will automatically be provisioned by Azure ML as part of deploying a model to an FPGA.  It is only used with Azure ML, and it cannot run arbitrary bitstreams.  For example, you will not be able to flash the FPGA with bitstreams to do encryption, encoding, etc.