[7/N] MoE Refactor: the implementation of new framework (#9269)

test/srt/test_mla_deepseek_v3.py

@@ -1,3 +1,4 @@
+import os
 import unittest
 from types import SimpleNamespace
 
@@ -49,6 +50,42 @@ class TestMLADeepseekV3(CustomTestCase):
         self.assertGreater(metrics["accuracy"], 0.62)
 
 
+class TestMLADeepseekV3DisableFusedFunc(CustomTestCase):
+    @classmethod
+    def setUpClass(cls):
+        os.environ["SGLANG_CI_DISABLE_MOE_FUSED_FUNC"] = "1"
+        cls.model = "lmsys/sglang-ci-dsv3-test"
+        cls.base_url = DEFAULT_URL_FOR_TEST
+        other_args = ["--trust-remote-code", "--chunked-prefill-size", "256"]
+        if is_cuda():
+            other_args.extend(["--cuda-graph-max-bs", "2"])
+        cls.process = popen_launch_server(
+            cls.model,
+            cls.base_url,
+            timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
+            other_args=other_args,
+        )
+
+    @classmethod
+    def tearDownClass(cls):
+        kill_process_tree(cls.process.pid)
+
+    def test_gsm8k(self):
+        args = SimpleNamespace(
+            num_shots=5,
+            data_path=None,
+            num_questions=200,
+            max_new_tokens=512,
+            parallel=128,
+            host="http://127.0.0.1",
+            port=int(self.base_url.split(":")[-1]),
+        )
+        metrics = run_eval_few_shot_gsm8k(args)
+        print(metrics)
+
+        self.assertGreater(metrics["accuracy"], 0.62)
+
+
 @unittest.skipIf(is_hip(), "FA is not available.")
 class TestMLADeepseekV3Fa3Fp8Kvcache(CustomTestCase):
     @classmethod