Unify GSM8K eval path to Chat API for regression CI readiness (#21667)

test/manual/models/test_llama4_models.py

@@ -2,7 +2,7 @@ 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.run_eval import run_eval
 from sglang.test.test_utils import (
     DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
     DEFAULT_URL_FOR_TEST,
@@ -44,17 +44,16 @@ class TestLlama4(CustomTestCase):
                     ],
                 )
                 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]),
+                    base_url=self.base_url,
+                    eval_name="gsm8k",
+                    api="completion",
+                    max_tokens=512,
+                    num_examples=200,
+                    num_threads=128,
                 )
                 metrics = run_eval(args)
                 print(f"{metrics=}")
-                self.assertGreaterEqual(metrics["accuracy"], model.accuracy)
+                self.assertGreaterEqual(metrics["score"], model.accuracy)
             except Exception as e:
                 print(f"Error testing {model.model}: {e}")
                 self.fail(f"Test failed for {model.model}: {e}")