diff --git a/onnxruntime/core/framework/utils.cc b/onnxruntime/core/framework/utils.cc
index d762211f78..b6dd851734 100644
--- a/onnxruntime/core/framework/utils.cc
+++ b/onnxruntime/core/framework/utils.cc
@@ -478,9 +478,9 @@ static common::Status CopyInputsAcrossDevices(const SessionState& session_state,
   // TODO: this sync is because the graph inputs can be consumed by multiple stream,
   // but we can only place the MemCpyAsync on one of the stream. Ideally we should make
   // other stream wait on the event of the memory copy stream, instead of host sync stream.
+  std::unordered_set<Stream*> visited;
   for (auto* stream : feed_streams) {
-    if (stream)
-      stream->Flush();
+    if (stream && visited.insert(stream).second) stream->Flush();
   }
   return Status::OK();
 }