diff --git a/single_include/kompute/Kompute.hpp b/single_include/kompute/Kompute.hpp
index 2f59d7fe5..0ef873e58 100755
--- a/single_include/kompute/Kompute.hpp
+++ b/single_include/kompute/Kompute.hpp
@@ -1464,7 +1464,10 @@ OpAlgoLhsRhsOut<tX, tY, tZ>::record()
       vk::PipelineStageFlagBits::eComputeShader,
       vk::PipelineStageFlagBits::eTransfer);
 
-    this->mTensorOutputStaging->recordCopyFrom(this->mTensorOutput, true);
+    this->mTensorOutputStaging->recordCopyFrom(
+            this->mCommandBuffer,
+            this->mTensorOutput,
+            true);
 }
 
 template<uint32_t tX, uint32_t tY, uint32_t tZ>
diff --git a/src/include/kompute/operations/OpAlgoLhsRhsOut.hpp b/src/include/kompute/operations/OpAlgoLhsRhsOut.hpp
index 41f8c103e..2f4352579 100644
--- a/src/include/kompute/operations/OpAlgoLhsRhsOut.hpp
+++ b/src/include/kompute/operations/OpAlgoLhsRhsOut.hpp
@@ -199,7 +199,10 @@ OpAlgoLhsRhsOut<tX, tY, tZ>::record()
       vk::PipelineStageFlagBits::eComputeShader,
       vk::PipelineStageFlagBits::eTransfer);
 
-    this->mTensorOutputStaging->recordCopyFrom(this->mTensorOutput, true);
+    this->mTensorOutputStaging->recordCopyFrom(
+            this->mCommandBuffer,
+            this->mTensorOutput,
+            true);
 }
 
 template<uint32_t tX, uint32_t tY, uint32_t tZ>