diff --git a/python/tvm/autotvm/task/relay_integration.py b/python/tvm/autotvm/task/relay_integration.py
index 11f40ed62756..c5e7694017a1 100644
--- a/python/tvm/autotvm/task/relay_integration.py
+++ b/python/tvm/autotvm/task/relay_integration.py
@@ -130,6 +130,10 @@ def extract_from_multiple_program(mods, params, target, target_host=None, ops=No
             assert isinstance(
                 mod, tvm.IRModule
             ), "only support relay Module or Function to be tuned"
+
+            with target:
+                mod = tvm.relay.transform.AlterOpLayout()(mod)
+
             relay.backend.te_compiler.get().clear()
             # wrap build call in thread to avoid multiprocessing problems
             build_thread = threading.Thread(target=_lower, args=(mod, target, param))
diff --git a/tests/python/relay/test_autotvm_task_extraction.py b/tests/python/relay/test_autotvm_task_extraction.py
index 83480a044f45..7092d71849b5 100644
--- a/tests/python/relay/test_autotvm_task_extraction.py
+++ b/tests/python/relay/test_autotvm_task_extraction.py
@@ -122,6 +122,22 @@ def get_net(batch, in_dim, out_dim, dtype, out_dtype):
     assert len(tasks) == 1 and tasks[0].name == "dense_int8.cuda"
 
 
+def test_task_extraction_for_dense_int8_vnni():
+    target = "llvm -mcpu=cascadelake"
+
+    def get_net(batch, in_dim, out_dim, dtype_input, dtype_weight, out_dtype):
+        data = tvm.relay.var("data", shape=[batch, in_dim], dtype=dtype_input)
+        weight = tvm.relay.var("weight", shape=[out_dim, in_dim], dtype=dtype_weight)
+        out = relay.nn.dense(data, weight, out_dtype=out_dtype)
+        mod, params = relay.testing.create_workload(out)
+        return mod, params
+
+    mod, params = get_net(1, 16, 32, "uint8", "int8", "int32")
+    tasks = autotvm.task.extract_from_program(mod, target=target, params=params)
+    assert len(tasks) == 1 and tasks[0].name == "dense_vnni.x86"
+
+
 if __name__ == "__main__":
     test_task_extraction()
     test_task_extraction_for_dense_int8_cuda()
+    test_task_extraction_for_dense_int8_vnni()