[Test] Stage-a sanity kits; consolidate core/ + models_e2e/ tests (#25831)

test/registered/radix_cache/test_cpp_radix_cache.py

@@ -0,0 +1,41 @@
+import unittest
+
+from sglang.srt.environ import envs
+from sglang.srt.utils import kill_process_tree
+from sglang.test.ci.ci_register import register_cuda_ci
+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,
+    DEFAULT_URL_FOR_TEST,
+    CustomTestCase,
+    popen_launch_server,
+)
+
+# Note: AMD registration removed - test_cpp_radix_cache fails on AMD due to C++ radix tree issues
+register_cuda_ci(est_time=60, suite="nightly-1-gpu", nightly=True)
+
+
+class TestCppRadixCache(CustomTestCase, MMLUMixin):
+    mmlu_score_threshold = 0.65
+    mmlu_num_examples = 64
+    mmlu_num_threads = 32
+
+    @classmethod
+    def setUpClass(cls):
+        envs.SGLANG_EXPERIMENTAL_CPP_RADIX_TREE.set(True)
+        cls.model = DEFAULT_MODEL_NAME_FOR_TEST
+        cls.base_url = DEFAULT_URL_FOR_TEST
+        cls.process = popen_launch_server(
+            cls.model,
+            cls.base_url,
+            timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
+        )
+
+    @classmethod
+    def tearDownClass(cls):
+        kill_process_tree(cls.process.pid)
+
+
+if __name__ == "__main__":
+    unittest.main()