[V1][CI/Test] Do basic test for top-p & top-k sampling (vllm-project#…

…12469)

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

tests/v1/engine/test_engine_core.py

@@ -144,7 +144,7 @@ def test_engine_core(monkeypatch):
 def test_engine_core_advanced_sampling(monkeypatch):
     """
     A basic end-to-end test to verify that the engine functions correctly 
-    when additional sampling parameters, such as min_tokens and 
+    when additional sampling parameters, such as top_p, min_tokens, and 
     presence_penalty, are set.
     """
     with monkeypatch.context() as m:
@@ -167,11 +167,23 @@ def test_engine_core_advanced_sampling(monkeypatch):
             stop_token_ids=[1001, 1002],
         )
         engine_core.add_request(request)
-        assert len(engine_core.scheduler.waiting) == 1
-        assert len(engine_core.scheduler.running) == 0
-        # Loop through until they are all done.
-        while len(engine_core.step().outputs) > 0:
-            pass
 
-        assert len(engine_core.scheduler.waiting) == 0
-        assert len(engine_core.scheduler.running) == 0
+        def _check_engine_state():
+            assert len(engine_core.scheduler.waiting) == 1
+            assert len(engine_core.scheduler.running) == 0
+            # Loop through until they are all done.
+            while len(engine_core.step().outputs) > 0:
+                pass
+            assert len(engine_core.scheduler.waiting) == 0
+            assert len(engine_core.scheduler.running) == 0
+
+        _check_engine_state()
+
+        # Second request.
+        request2 = make_request()
+        request2.sampling_params = SamplingParams(
+            top_p=0.99,
+            top_k=50,
+        )
+        engine_core.add_request(request2)
+        _check_engine_state()