diff --git a/deepspeed/inference/engine.py b/deepspeed/inference/engine.py
index c029aaa707e5..d2f9bf9cf0b2 100755
--- a/deepspeed/inference/engine.py
+++ b/deepspeed/inference/engine.py
@@ -253,7 +253,7 @@ def _post_forward_hook(self, module, input, output):
         else:
             get_accelerator().synchronize()
             self._end = time.time()
-            elapsed_time = self._end - self._start
+            elapsed_time = (self._end - self._start) * 1e3  # convert seconds to ms
         self._model_times.append(elapsed_time)
 
     def _create_model_parallel_group(self, config):
@@ -612,7 +612,7 @@ def forward(self, *inputs, **kwargs):
 
         if self.model_profile_enabled and self._config.enable_cuda_graph:
             get_accelerator().synchronize()
-            duration = time.time() - start
+            duration = (time.time() - start) * 1e3  # convert seconds to ms
             self._model_times.append(duration)
 
         return outputs