diff --git a/vllm/model_executor/determinism/batch_invariant.py b/vllm/model_executor/determinism/batch_invariant.py index 6490e69a60..403f475702 100644 --- a/vllm/model_executor/determinism/batch_invariant.py +++ b/vllm/model_executor/determinism/batch_invariant.py @@ -918,7 +918,7 @@ def mean_batch_invariant(input, dim, keepdim=False, dtype: torch.dtype | None = for d in sorted_dims: result = result.squeeze(d) - return result + return result if dtype is not None else result.to(input.dtype) @triton.jit