diff --git a/tests/integration/post_training/test_post_training.py b/tests/integration/post_training/test_post_training.py
index bb4639d17..4439c293f 100644
--- a/tests/integration/post_training/test_post_training.py
+++ b/tests/integration/post_training/test_post_training.py
@@ -58,6 +58,7 @@ class TestPostTraining:
         ],
     )
     @pytest.mark.timeout(360)  # 6 minutes timeout
+    @pytest.mark.skip(reason="test failing with No endpoint found for /v1/post-training/supervised-fine-tune")
     def test_supervised_fine_tune(self, llama_stack_client, purpose, source):
         logger.info("Starting supervised fine-tuning test")
 
diff --git a/tests/integration/telemetry/test_telemetry.py b/tests/integration/telemetry/test_telemetry.py
index c46de3742..fb6efd250 100644
--- a/tests/integration/telemetry/test_telemetry.py
+++ b/tests/integration/telemetry/test_telemetry.py
@@ -10,6 +10,7 @@ from uuid import uuid4
 from llama_stack_client import Agent
 
 
+@pytest.mark.skip(reason="telemetry is not stable")
 def test_agent_query_spans(llama_stack_client, text_model_id):
     agent = Agent(llama_stack_client, model=text_model_id, instructions="You are a helpful assistant")
     session_id = agent.create_session(f"test-session-{uuid4()}")