diff --git a/aten/src/ATen/native/LinearAlgebra.cpp b/aten/src/ATen/native/LinearAlgebra.cpp
index 8721080816de3..4bf90198dd8bb 100644
--- a/aten/src/ATen/native/LinearAlgebra.cpp
+++ b/aten/src/ATen/native/LinearAlgebra.cpp
@@ -1712,7 +1712,8 @@ Tensor _matmul_impl(
   } else if (dim_tensor1 == 2 && dim_tensor2 == 1) {
     return has_out ? at::mv_out(out, tensor1, tensor2) : tensor1.mv(tensor2);
   } else if (dim_tensor1 == 1 && dim_tensor2 == 2) {
-    return has_out ? at::mv_out(out, tensor2.t(), tensor1) : tensor2.t().mv(tensor1);
+    return has_out ? at::mm_out(out, tensor1.unsqueeze(0), tensor2).squeeze_(0)
+                   : tensor1.unsqueeze(0).mm(tensor2).squeeze_(0);
   } else if (dim_tensor1 == 2 && dim_tensor2 == 2) {
     return has_out ? at::mm_out(out, tensor1, tensor2) : tensor1.mm(tensor2);
   } else if (should_fold(tensor1, dim_tensor2) || should_fold(tensor2, dim_tensor1)) {
diff --git a/torch/testing/_internal/common_methods_invocations.py b/torch/testing/_internal/common_methods_invocations.py
index 939ca9077e5b0..00eb3f7f09b5f 100644
--- a/torch/testing/_internal/common_methods_invocations.py
+++ b/torch/testing/_internal/common_methods_invocations.py
@@ -12192,6 +12192,8 @@ def error_inputs_mean(op_info, device, **kwargs):
                             'TestCommon', 'test_noncontiguous_samples',
                             device_type='cpu'), ],
            skips=(
+               # Strides are not the same!
+               DecorateInfo(unittest.expectedFailure, 'TestCommon', 'test_out'),
                # https://github.com/pytorch/pytorch/issues/67470
                DecorateInfo(unittest.skip("67470!"),
                             'TestCommon', 'test_noncontiguous_samples',
@@ -13517,6 +13519,8 @@ def error_inputs_mean(op_info, device, **kwargs):
                DecorateInfo(unittest.expectedFailure, 'TestCompositeCompliance', 'test_forward_ad'),
            ),
            decorators=(
+               # Strides are not the same!
+               DecorateInfo(unittest.expectedFailure, 'TestCommon', 'test_out'),
                DecorateInfo(toleranceOverride({torch.float16: tol(atol=1e-02, rtol=1e-02)}),
                             'TestCudaFuserOpInfo', 'test_nvfuser_correctness'),
            )),