diff --git a/.buildkite/test-pipeline.yaml b/.buildkite/test-pipeline.yaml
index 93ac8a29c676..a6616d7b4148 100644
--- a/.buildkite/test-pipeline.yaml
+++ b/.buildkite/test-pipeline.yaml
@@ -198,6 +198,7 @@ steps:
   commands:
     # split the test to avoid interference
     - pytest -v -s v1/core
+    - pytest -v -s v1/entrypoints
     - pytest -v -s v1/engine
     - pytest -v -s v1/sample
     - pytest -v -s v1/worker
diff --git a/tests/v1/entrypoints/llm/test_struct_output_generate.py b/tests/v1/entrypoints/llm/test_struct_output_generate.py
index b4eb475c23ba..98983fa05b83 100644
--- a/tests/v1/entrypoints/llm/test_struct_output_generate.py
+++ b/tests/v1/entrypoints/llm/test_struct_output_generate.py
@@ -18,6 +18,9 @@ MODELS_TO_TEST = [
     "Qwen/Qwen2.5-1.5B-Instruct", "mistralai/Ministral-8B-Instruct-2410"
 ]
 
+# Undo after https://github.com/vllm-project/vllm/pull/14868
+pytest.skip(allow_module_level=True)
+
 
 @pytest.mark.skip_global_cleanup
 @pytest.mark.parametrize("guided_decoding_backend",