[feat][Ascend][Mindspore]: support model-impl of mindspore (#9234)

test/srt/ascend/test_mindspore_models.py

@@ -0,0 +1,64 @@
+"""
+Usage:
+python3 -m unittest test_mindspore_models.TestMindSporeQwen3.test_gsm8k
+"""
+
+import unittest
+from types import SimpleNamespace
+
+from sglang.srt.utils import kill_process_tree
+from sglang.test.few_shot_gsm8k import run_eval
+from sglang.test.test_utils import (
+    DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
+    DEFAULT_URL_FOR_TEST,
+    CustomTestCase,
+    popen_launch_server,
+)
+
+
+class TestMindSporeQwen3(CustomTestCase):
+    @classmethod
+    def setUpClass(cls):
+        cls.model = "Qwen/Qwen3-8B"
+        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=[
+                "--device",
+                "npu",
+                "--model-impl",
+                "mindspore",
+                "--attention-backend",
+                "ascend",
+                "--tp-size",
+                "1",
+                "--dp-size",
+                "1",
+                "--mem-fraction-static",
+                0.8,
+            ],
+        )
+
+    @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(args)
+        print(f"{metrics=}")
+        self.assertGreater(metrics["accuracy"], 0.78)
+
+
+if __name__ == "__main__":
+    unittest.main()

test/srt/run_suite.py

@@ -536,6 +536,9 @@ suite_ascend = {
         TestFile("ascend/test_ascend_deepep.py", 400),
         TestFile("ascend/test_ascend_deepseek_mtp.py", 400),
     ],
+    "__not_in_ascend_ci__": [
+        TestFile("ascend/test_mindspore_models.py"),
+    ],
 }
 
 suites.update(suite_amd)