[UnifiedRadixTree]: Support HiCache Framework for UnifiedRadixTree (#23316)

Co-authored-by: JINZ <1023553676@qq.com>
Co-authored-by: diemchai <diemchai@tencent.com>

test/registered/radix_cache/test_unified_radix_cache_kl.py

@@ -262,5 +262,55 @@ class TestUnifiedSWARadixCache(UnifiedRadixTreeTestMixin, CustomTestCase):
         kill_process_tree(cls.process.pid)
 
 
+# TODO(hzh): Currently, HiCache is not fully compatible with the CI CUDA13 environment; we need to wait for the fix before re-enabling the tests below.
+# class TestUnifiedMambaRadixCacheWithHiCache(UnifiedRadixTreeTestMixin, CustomTestCase):
+#     """Mamba hybrid + UnifiedRadixCache."""
+#
+#     kl_threshold = 0.003
+#     prefill_cache_assert = staticmethod(
+#         make_mamba_prefill_assert(chunk_size=MAMBA_CHUNK_SIZE)
+#     )
+#     decode_cache_assert = staticmethod(
+#         make_mamba_decode_assert(track_interval=MAMBA_TRACK_INTERVAL)
+#     )
+#
+#     @classmethod
+#     def setUpClass(cls):
+#         cls.model = MAMBA_MODEL
+#         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=[
+#                 "--tp-size",
+#                 "4",
+#                 "--chunked-prefill-size",
+#                 "2048",
+#                 "--mem-fraction-static",
+#                 "0.85",
+#                 "--mamba-scheduler-strategy",
+#                 "extra_buffer",
+#                 "--mamba-track-interval",
+#                 str(MAMBA_TRACK_INTERVAL),
+#                 "--enable-hierarchical-cache",
+#                 "--hicache-ratio",
+#                 "1.5",
+#                 "--hicache-write-policy",
+#                 "write_through",
+#                 "--hicache-io-backend",
+#                 "direct",
+#                 "--hicache-mem-layout",
+#                 "page_first_direct",
+#             ],
+#             env={"SGLANG_ENABLE_UNIFIED_RADIX_TREE": "1"},
+#         )
+#         cls.input_ids = get_input_ids(cls.model, num_samples=18)
+#
+#     @classmethod
+#     def tearDownClass(cls):
+#         kill_process_tree(cls.process.pid)
+
+
 if __name__ == "__main__":
     unittest.main()