[Bugfix] Fix Stream usage in CPU model runner and OneDNN kernel check (#25046)

Signed-off-by: jiang1.li <jiang1.li@intel.com>

csrc/cpu/dnnl_kernels.cpp

@@ -523,7 +523,7 @@ void onednn_mm(torch::Tensor& c,        // [M, OC], row-major
   CPU_KERNEL_GUARD_IN(onednn_mm)
   TORCH_CHECK(a.dim() == 2);
   TORCH_CHECK(a.stride(-1) == 1);
-  TORCH_CHECK(c.is_contiguous());
+  TORCH_CHECK(c.stride(-1) == 1);
   MatMulPrimitiveHandler* ptr =
       reinterpret_cast<MatMulPrimitiveHandler*>(handler);