doc: Update doc for model_server_workers param in PyTorchModel (#3868)

Author: knikure

src/sagemaker/pytorch/model.py

@@ -123,9 +123,9 @@ def __init__(
                 to call to create a predictor with an endpoint name and
                 SageMaker ``Session``. If specified, ``deploy()`` returns the
                 result of invoking this function on the created endpoint name.
-            model_server_workers (int or PipelineVariable): Optional. The number of worker processes
-                used by the inference server. If None, server will use one
-                worker per vCPU.
+            model_server_workers (int or PipelineVariable): Optional. The number of worker
+                processes used by the TorchServe model server. If None, available GPUs
+                in system or number of logical processors available to the JVM.
             **kwargs: Keyword arguments passed to the superclass
                 :class:`~sagemaker.model.FrameworkModel` and, subsequently, its
                 superclass :class:`~sagemaker.model.Model`.