diff --git a/python/llm/test/inference_gpu/test_transformers_api.py b/python/llm/test/inference_gpu/test_transformers_api.py
index 92bcd4d9..9a9bb8a3 100644
--- a/python/llm/test/inference_gpu/test_transformers_api.py
+++ b/python/llm/test/inference_gpu/test_transformers_api.py
@@ -32,7 +32,7 @@ print(f'Running on {device}')
 @pytest.mark.parametrize('Model, Tokenizer, model_path',[
     (AutoModelForCausalLM, LlamaTokenizer, os.environ.get('LLAMA2_7B_ORIGIN_PATH')),
     (AutoModel, AutoTokenizer, os.environ.get('CHATGLM2_6B_ORIGIN_PATH')),
-    # (AutoModelForCausalLM, AutoTokenizer, os.environ.get('FALCON_7B_ORIGIN_PATH')),
+    (AutoModelForCausalLM, AutoTokenizer, os.environ.get('FALCON_7B_ORIGIN_PATH')),
     (AutoModelForCausalLM, AutoTokenizer, os.environ.get('MPT_7B_ORIGIN_PATH')),
     # (AutoModelForCausalLM, AutoTokenizer, os.environ.get('MISTRAL_7B_INSTRUCT_V0_1_ORIGIN_PATH')),
     # (AutoModelForCausalLM, AutoTokenizer, os.environ.get('BAICHUAN2_7B_ORIGIN_PATH')),
diff --git a/python/llm/test/inference_gpu/test_transformers_api_attention.py b/python/llm/test/inference_gpu/test_transformers_api_attention.py
index 870ba8fe..0a7a6ac2 100644
--- a/python/llm/test/inference_gpu/test_transformers_api_attention.py
+++ b/python/llm/test/inference_gpu/test_transformers_api_attention.py
@@ -30,7 +30,7 @@ PROMPT = "Once upon a time, there existed a little girl who liked to have advent
 TEST_MODEL_LIST = [
     ("MPT-7B", AutoModelForCausalLM, AutoTokenizer, os.environ.get('MPT_7B_ORIGIN_PATH')),
     ("Llama2-7B", AutoModelForCausalLM, LlamaTokenizer, os.environ.get('LLAMA2_7B_ORIGIN_PATH')),
-    # ("Falcon-7B", AutoModelForCausalLM, AutoTokenizer, os.environ.get('FALCON_7B_ORIGIN_PATH')),
+    ("Falcon-7B", AutoModelForCausalLM, AutoTokenizer, os.environ.get('FALCON_7B_ORIGIN_PATH')),
     ("ChatGLM2-6B", AutoModel, AutoTokenizer, os.environ.get('CHATGLM2_6B_ORIGIN_PATH')),
     ("Mistral-7B-Instruct-v0.1", AutoModelForCausalLM, AutoTokenizer, os.environ.get('MISTRAL_7B_INSTRUCT_V0_1_ORIGIN_PATH')),
     ("Baichuan2-7B-Chat", AutoModelForCausalLM, AutoTokenizer, os.environ.get('BAICHUAN2_7B_ORIGIN_PATH')),
diff --git a/python/llm/test/inference_gpu/test_transformers_api_final_logits.py b/python/llm/test/inference_gpu/test_transformers_api_final_logits.py
index 80acdcfd..02e3cc27 100644
--- a/python/llm/test/inference_gpu/test_transformers_api_final_logits.py
+++ b/python/llm/test/inference_gpu/test_transformers_api_final_logits.py
@@ -29,7 +29,7 @@ print(f'Running on {device}')
 PROMPT = "Once upon a time, there existed a little girl who liked to have adventures. She wanted to go to places and meet new people, and have fun"
 TEST_MODEL_LIST = [
     ("MPT-7B", AutoModelForCausalLM, AutoTokenizer, os.environ.get('MPT_7B_ORIGIN_PATH')),
-    # ("Falcon-7B", AutoModelForCausalLM, AutoTokenizer, os.environ.get('FALCON_7B_ORIGIN_PATH')),
+    ("Falcon-7B", AutoModelForCausalLM, AutoTokenizer, os.environ.get('FALCON_7B_ORIGIN_PATH')),
 ]