diff --git a/src/python/library/tritonclient/grpc/_client.py b/src/python/library/tritonclient/grpc/_client.py
index 1c68115c4..9fc50493a 100755
--- a/src/python/library/tritonclient/grpc/_client.py
+++ b/src/python/library/tritonclient/grpc/_client.py
@@ -1741,7 +1741,8 @@ def wrapped_callback(call_future):
             raise_error_grpc(rpc_error)
 
     def start_stream(
-        self, callback, stream_timeout=None, headers=None, compression_algorithm=None
+        self, callback, stream_timeout=None, headers=None, compression_algorithm=None, 
+        daemon=None,
     ):
         """Starts a grpc bi-directional stream to send streaming inferences.
         Note: When using stream, user must ensure the InferenceServerClient.close()
@@ -1768,6 +1769,8 @@ def start_stream(
             Optional grpc compression algorithm to be used on client side.
             Currently supports "deflate", "gzip" and None. By default, no
             compression is used.
+        daemon : bool
+            Make internal thread daemonic if set True. By default set to None.
 
         Raises
         ------
@@ -1784,7 +1787,7 @@ def start_stream(
             )
         metadata = self._get_metadata(headers)
 
-        self._stream = _InferStream(callback, self._verbose)
+        self._stream = _InferStream(callback, self._verbose, daemon=daemon)
 
         try:
             response_iterator = self._client_stub.ModelStreamInfer(
diff --git a/src/python/library/tritonclient/grpc/_infer_stream.py b/src/python/library/tritonclient/grpc/_infer_stream.py
index 92ec05890..ca3181c71 100755
--- a/src/python/library/tritonclient/grpc/_infer_stream.py
+++ b/src/python/library/tritonclient/grpc/_infer_stream.py
@@ -52,9 +52,11 @@ class _InferStream:
         'error' would be None for a successful inference.
     verbose : bool
         Enables verbose mode if set True.
+    daemon : bool
+        Make handler thread daemonic if set True (default None).
     """
 
-    def __init__(self, callback, verbose):
+    def __init__(self, callback, verbose, daemon=None):
         self._callback = callback
         self._verbose = verbose
         self._request_queue = queue.Queue()
@@ -62,6 +64,7 @@ def __init__(self, callback, verbose):
         self._cancelled = False
         self._active = True
         self._response_iterator = None
+        self.daemon = daemon
 
     def __del__(self):
         self.close(cancel_requests=True)
@@ -100,7 +103,7 @@ def _init_handler(self, response_iterator):
         if self._handler is not None:
             raise_error("Attempted to initialize already initialized InferStream")
         # Create a new thread to handle the gRPC response stream
-        self._handler = threading.Thread(target=self._process_response)
+        self._handler = threading.Thread(target=self._process_response, daemon=self.daemon)
         self._handler.start()
         if self._verbose:
             print("stream started...")