Support (1 <= dp < tp) in the dp attention in DeepEP (#4770)

Co-authored-by: Cheng Wan <cwan39@gatech.edu>

test/srt/test_moe_deepep.py

@@ -12,7 +12,42 @@ from sglang.test.test_utils import (
 )
 
 
-class TestDeepEPMoE(CustomTestCase):
+class TestPureTP(CustomTestCase):
+    @classmethod
+    def setUpClass(cls):
+        cls.model = DEFAULT_MLA_MODEL_NAME_FOR_TEST
+        cls.base_url = DEFAULT_URL_FOR_TEST
+        cls.process = popen_launch_server(
+            cls.model,
+            cls.base_url,
+            timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
+            other_args=[
+                "--trust-remote-code",
+                "--tp",
+                "2",
+                "--enable-deepep-moe",
+                "--disable-cuda-graph",
+            ],
+        )
+
+    @classmethod
+    def tearDownClass(cls):
+        kill_process_tree(cls.process.pid)
+
+    def test_mmlu(self):
+        args = SimpleNamespace(
+            base_url=self.base_url,
+            model=self.model,
+            eval_name="mmlu",
+            num_examples=64,
+            num_threads=32,
+        )
+
+        metrics = run_eval(args)
+        self.assertGreater(metrics["score"], 0.5)
+
+
+class TestDPAttn(unittest.TestCase):
     @classmethod
     def setUpClass(cls):
         cls.model = DEFAULT_MLA_MODEL_NAME_FOR_TEST