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

test/registered/quant/test_w8a8_quantization.py

@@ -6,7 +6,7 @@ import requests
 
 from sglang.srt.utils import kill_process_tree
 from sglang.test.ci.ci_register import register_cuda_ci
-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,
@@ -51,17 +51,17 @@ class BaseW8A8Test(CustomTestCase):
             self.skipTest("gsm8k_accuracy_threshold not set for this test")
 
         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,
+            model=self.model,
+            eval_name="gsm8k",
+            api="completion",
+            max_tokens=512,
+            num_examples=200,
+            num_threads=128,
         )
         metrics = run_eval(args)
         print(metrics)
-        self.assertGreater(metrics["accuracy"], self.gsm8k_accuracy_threshold)
+        self.assertGreater(metrics["score"], self.gsm8k_accuracy_threshold)
 
     def run_decode(self, max_new_tokens):
         response = requests.post(