fix serving

InternLM · Nov 17, 2023 · 4dc9b53 · 4dc9b53
1 parent df40522
commit 4dc9b53
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/src/turbomind/triton_backend/libfastertransformer.cc b/src/turbomind/triton_backend/libfastertransformer.cc
@@ -1715,7 +1715,7 @@ void ModelInstanceState::ReadOutputTensors(size_t
                                 output_dtype,
                                 batchn_shape,
                                 output_buffer,
-                                TRITONSERVER_MEMORY_GPU,
+                                TRITONSERVER_MEMORY_CPU,
                                 model_instance_device_id_start_);
     }