diff --git a/tests/kit/model_zoo/transformers/gpt.py b/tests/kit/model_zoo/transformers/gpt.py
index f2b139bec..73d9b683e 100644
--- a/tests/kit/model_zoo/transformers/gpt.py
+++ b/tests/kit/model_zoo/transformers/gpt.py
@@ -113,6 +113,7 @@ config = transformers.GPT2Config(
     problem_type="single_label_classification",
     pad_token_id=1022,
     tie_word_embeddings=True,
+    attn_implementation="flash_attention_2",
 )
 
 config_for_token_classification = copy.deepcopy(config)
diff --git a/tests/test_zero/test_gemini/test_inference.py b/tests/test_zero/test_gemini/test_inference.py
index 6da19d410..61e9e14f5 100644
--- a/tests/test_zero/test_gemini/test_inference.py
+++ b/tests/test_zero/test_gemini/test_inference.py
@@ -114,7 +114,6 @@ def run_dist(rank, world_size, port):
     exam_inference()
 
 
-@pytest.mark.skip("this test failed")
 @pytest.mark.dist
 @pytest.mark.parametrize("world_size", [1, 4])
 def test_inference(world_size):
diff --git a/version.txt b/version.txt
index 76914ddc0..8f0916f76 100644
--- a/version.txt
+++ b/version.txt
@@ -1 +1 @@
-0.4.9
+0.5.0