Add max_tokens alias to max_out_tokens arg to maintain backwards compatibility (#2508)

This PR adds a max_tokens alias to the max_out_tokens argument in the init_inference API to support backwards compatibility after the config refactor PR https://github.com/microsoft/DeepSpeed/pull/2472.

Thanks @molly-smith and @mrwyattii.

deepspeed/inference/config.py

@@ -224,7 +224,7 @@ class DeepSpeedInferenceConfig(DeepSpeedConfigModel):
 
     config: Dict = None  # todo: really no need for this field if we can refactor
 
-    max_out_tokens: int = 1024
+    max_out_tokens: int = Field(1024, alias="max_tokens")
     """
     This argument shows the maximum number of tokens inference-engine can work
     with, including the input and output tokens. Please consider increasing it