diff --git a/deepmd/pt/utils/auto_batch_size.py b/deepmd/pt/utils/auto_batch_size.py index 0af7cdcc47..6dfb80067a 100644 --- a/deepmd/pt/utils/auto_batch_size.py +++ b/deepmd/pt/utils/auto_batch_size.py @@ -57,6 +57,7 @@ def is_oom_error(self, e: Exception) -> bool: # (the meaningless error message should be considered as a bug in cusolver) if isinstance(e, RuntimeError) and ( "CUDA out of memory." in e.args[0] + or "CUDA driver error: out of memory" in e.args[0] or "cusolver error: CUSOLVER_STATUS_INTERNAL_ERROR" in e.args[0] ): # Release all unoccupied cached memory