Fix decoupled shared memory leak

triton-inference-server · Jan 17, 2024 · da3dde1 · da3dde1
1 parent de3f051
commit da3dde1
Showing 1 changed file with 1 addition and 0 deletions.
diff --git a/src/python_be.cc b/src/python_be.cc
@@ -1328,6 +1328,7 @@ ModelInstanceState::ProcessRequestsDecoupled(
 
   AllocatedSharedMemory<ResponseBatch> response_batch =
       Stub()->ShmPool()->Load<ResponseBatch>(received_message_->Args());
+  received_message_.reset();
 
   uint64_t compute_end_ns = 0;
   SET_TIMESTAMP(compute_end_ns);