diff --git a/auto_round/utils/common.py b/auto_round/utils/common.py
index 9d4e4c98a..702b815ad 100644
--- a/auto_round/utils/common.py
+++ b/auto_round/utils/common.py
@@ -88,8 +88,6 @@ def __init__(self):
             "auto_round:gptqmodel",
             "auto_round:auto_awq",
             "auto_round:llm_compressor",
-            "itrex",
-            "itrex_xpu",
             "fake",
             "llm_compressor",
         )
diff --git a/test/test_cpu/test_autoround.py b/test/test_cpu/test_autoround.py
index adadaa837..dd188e6ad 100644
--- a/test/test_cpu/test_autoround.py
+++ b/test/test_cpu/test_autoround.py
@@ -162,28 +162,6 @@ def test_nv_fp4(self):
         print(result["results"]["lambada_openai"]["acc,none"])
         self.assertGreater(result["results"]["lambada_openai"]["acc,none"], 0.35)
 
-    def test_default(self):
-        bits, group_size, sym = 4, 128, False
-        autoround = AutoRound(
-            self.model,
-            self.tokenizer,
-            bits=bits,
-            group_size=group_size,
-            sym=sym,
-            iters=2,
-            seqlen=2,
-            dataset=self.llm_dataloader,
-        )
-        autoround.quantize()
-
-        autoround.save_quantized(output_dir="./saved", inplace=False, format="itrex")
-        try:
-            import auto_gptq
-        except:
-            return
-        if torch.cuda.is_available():
-            autoround.save_quantized(output_dir="./saved", inplace=False)
-
     def test_w4g1(self):
         model_name = "/tf_dataset/auto_round/models/facebook/opt-125m"
         bits, group_size, sym = 4, -1, True
diff --git a/test/test_cpu/test_autoround_acc.py b/test/test_cpu/test_autoround_acc.py
index 97211ade4..41b28e663 100644
--- a/test/test_cpu/test_autoround_acc.py
+++ b/test/test_cpu/test_autoround_acc.py
@@ -13,7 +13,6 @@
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 from auto_round import AutoRound  # pylint: disable=E0401
-from auto_round.export.export_to_itrex.export import pack_model  # pylint: disable=E0401
 
 
 class LLMDataLoader: