Qualcomm AI Engine Direct - Optimize memory usage at runtime (pytorch…

…#7003) Qualcomm AI Engine Direct - Optimize memory at runtime
kirklandsign · Nov 21, 2024 · 96a9d35 · 96a9d35
1 parent 2c65b97
commit 96a9d35
Showing 1 changed file with 2 additions and 0 deletions.
diff --git a/backends/qualcomm/runtime/QnnExecuTorchBackend.cpp b/backends/qualcomm/runtime/QnnExecuTorchBackend.cpp
@@ -90,6 +90,8 @@ Result<DelegateHandle*> QnnExecuTorchBackend::init(
     }
   }
   add_cached_delegate(signature, qnn_manager);
+  // This backend does not need its processed data after Init.
+  processed->Free();
   return qnn_manager;
 }