[Test] Consolidate eval accuracy test mixins into eval_accuracy_kit (#21047)

test/registered/tokenizer/test_multi_tokenizer.py

@@ -1,9 +1,8 @@
 import unittest
-from types import SimpleNamespace
 
 from sglang.srt.utils import kill_process_tree
 from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
-from sglang.test.run_eval import run_eval
+from sglang.test.kits.eval_accuracy_kit import MMLUMixin
 from sglang.test.test_utils import (
     DEFAULT_MODEL_NAME_FOR_TEST,
     DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
@@ -21,8 +20,11 @@ register_cuda_ci(est_time=230, suite="stage-b-test-1-gpu-large")
 register_amd_ci(est_time=345, suite="stage-b-test-1-gpu-small-amd")
 
 
-class TestMultiTokenizer(CustomTestCase):
-    # from test_hicache.py
+class TestMultiTokenizer(CustomTestCase, MMLUMixin):
+    mmlu_score_threshold = 0.65
+    mmlu_num_examples = 64
+    mmlu_num_threads = 32
+
     @classmethod
     def setUpClass(cls):
         cls.model = DEFAULT_MODEL_NAME_FOR_TEST
@@ -43,17 +45,6 @@ class TestMultiTokenizer(CustomTestCase):
     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.assertGreaterEqual(metrics["score"], 0.65)
-
     def test_multi_tokenizer_ttft(self):
         # from test_bench_serving.py run_bench_serving
         args = get_benchmark_args(