diff --git a/tests/integration/defs/accuracy/test_disaggregated_serving.py b/tests/integration/defs/accuracy/test_disaggregated_serving.py
index 67ca753bef1f..21518fb61cc9 100644
--- a/tests/integration/defs/accuracy/test_disaggregated_serving.py
+++ b/tests/integration/defs/accuracy/test_disaggregated_serving.py
@@ -1371,15 +1371,12 @@ def test_kv_cache_v2_nixl_python(self):
         }
         disaggregated_server_config = {
             "hostname": "localhost",
-            "port": 8000,
             "backend": "pytorch",
             "context_servers": {
-                "num_instances": 1,
-                "urls": ["localhost:8001"]
+                "num_instances": 1
             },
             "generation_servers": {
-                "num_instances": 1,
-                "urls": ["localhost:8002"]
+                "num_instances": 1
             }
         }
         with launch_disaggregated_llm(disaggregated_server_config,
@@ -1843,6 +1840,61 @@ def test_auto_dtype_with_helix(self, comms_medium, cuda_graph_config,
                                       max_workers=128) as llm:
             run_accuracy_test(llm, self.MODEL_NAME, ["GSM8K"])
 
+    @pytest.mark.skip_less_device(4)
+    @pytest.mark.parametrize("use_kv_cache_manager_v2", [False],
+                             ids=["cache_mgr_v1"])
+    def test_kv_cache_v2_nixl_python(self, use_kv_cache_manager_v2):
+        """Test with KV cache manager v1, block_reuse=False, backend=NIXL, transceiver_runtime=PYTHON."""
+        max_num_tokens = 8192
+        moe_config = {"backend": "TRTLLM", "max_num_tokens": max_num_tokens}
+        ctx_server_config = {
+            "disable_overlap_scheduler": True,
+            "kv_cache_config": {
+                "free_gpu_memory_fraction": 0.5,
+                "enable_block_reuse": False,
+                "use_kv_cache_manager_v2": use_kv_cache_manager_v2
+            },
+            "cache_transceiver_config": {
+                "backend": "NIXL",
+                "transceiver_runtime": "PYTHON",
+                "max_tokens_in_buffer": 4096
+            },
+            "tensor_parallel_size": 2,
+            "moe_expert_parallel_size": 2,
+            "enable_autotuner": False,
+        }
+        gen_server_config = {
+            "disable_overlap_scheduler": False,
+            "moe_config": moe_config,
+            "kv_cache_config": {
+                "free_gpu_memory_fraction": 0.5,
+                "enable_block_reuse": False,
+                "use_kv_cache_manager_v2": use_kv_cache_manager_v2
+            },
+            "cache_transceiver_config": {
+                "backend": "NIXL",
+                "transceiver_runtime": "PYTHON",
+                "max_tokens_in_buffer": 4096
+            },
+            "tensor_parallel_size": 2,
+            "moe_expert_parallel_size": 2,
+            "enable_autotuner": False,
+        }
+        disaggregated_server_config = {
+            "hostname": "localhost",
+            "backend": "pytorch",
+            "context_servers": {
+                "num_instances": 1,
+            },
+            "generation_servers": {
+                "num_instances": 1,
+            }
+        }
+        with launch_disaggregated_llm(disaggregated_server_config,
+                                      ctx_server_config, gen_server_config,
+                                      self.MODEL_PATH) as llm:
+            run_accuracy_test(llm, self.MODEL_NAME, ["GSM8K"])
+
 
 @pytest.mark.timeout(DEFAULT_TEST_TIMEOUT)
 @skip_pre_hopper
@@ -2754,3 +2806,66 @@ def test_auto_dtype(self):
                                       server_waiting_timeout=3600) as llm:
             task = MMLU(self.MODEL_NAME)
             task.evaluate(llm, is_integration_test=True)
+
+
+@pytest.mark.timeout(DEFAULT_TEST_TIMEOUT)
+@skip_pre_blackwell
+@pytest.mark.skip_less_device_memory(80000)
+class TestDeepSeekR1(LlmapiAccuracyTestHarness):
+    MODEL_NAME = "deepseek-ai/DeepSeek-R1"
+    MODEL_PATH = f"{llm_models_root()}/DeepSeek-R1-0528-FP4-v2"
+
+    @pytest.mark.skip_less_device(4)
+    @pytest.mark.parametrize("use_kv_cache_manager_v2", [False],
+                             ids=["cache_mgr_v1"])
+    def test_kv_cache_v2_nixl_python(self, use_kv_cache_manager_v2):
+        """Test with KV cache manager v1, block_reuse=False, backend=NIXL, transceiver_runtime=PYTHON."""
+        max_num_tokens = 8192
+        moe_config = {"backend": "TRTLLM", "max_num_tokens": max_num_tokens}
+        ctx_server_config = {
+            "disable_overlap_scheduler": True,
+            "kv_cache_config": {
+                "free_gpu_memory_fraction": 0.5,
+                "enable_block_reuse": False,
+                "use_kv_cache_manager_v2": use_kv_cache_manager_v2
+            },
+            "cache_transceiver_config": {
+                "backend": "NIXL",
+                "transceiver_runtime": "PYTHON",
+                "max_tokens_in_buffer": 4096
+            },
+            "tensor_parallel_size": 2,
+            "moe_expert_parallel_size": 2,
+            "enable_autotuner": False,
+        }
+        gen_server_config = {
+            "disable_overlap_scheduler": False,
+            "moe_config": moe_config,
+            "kv_cache_config": {
+                "free_gpu_memory_fraction": 0.5,
+                "enable_block_reuse": False,
+                "use_kv_cache_manager_v2": use_kv_cache_manager_v2
+            },
+            "cache_transceiver_config": {
+                "backend": "NIXL",
+                "transceiver_runtime": "PYTHON",
+                "max_tokens_in_buffer": 4096
+            },
+            "tensor_parallel_size": 2,
+            "moe_expert_parallel_size": 2,
+            "enable_autotuner": False,
+        }
+        disaggregated_server_config = {
+            "hostname": "localhost",
+            "backend": "pytorch",
+            "context_servers": {
+                "num_instances": 1,
+            },
+            "generation_servers": {
+                "num_instances": 1,
+            }
+        }
+        with launch_disaggregated_llm(disaggregated_server_config,
+                                      ctx_server_config, gen_server_config,
+                                      self.MODEL_PATH) as llm:
+            run_accuracy_test(llm, self.MODEL_NAME, ["GSM8K"])
diff --git a/tests/integration/test_lists/qa/llm_function_core.txt b/tests/integration/test_lists/qa/llm_function_core.txt
index 0be227bc27e8..4e3bd088ee17 100644
--- a/tests/integration/test_lists/qa/llm_function_core.txt
+++ b/tests/integration/test_lists/qa/llm_function_core.txt
@@ -1,8 +1,10 @@
+accuracy/test_disaggregated_serving.py::TestDeepSeekR1::test_kv_cache_v2_nixl_python[cache_mgr_v1]
 accuracy/test_disaggregated_serving.py::TestDeepSeekV32Exp::test_auto_dtype[False]
 accuracy/test_disaggregated_serving.py::TestDeepSeekV32Exp::test_auto_dtype_with_helix[fifo-cudagraph:with_padding-pp1dp2cp2]
 accuracy/test_disaggregated_serving.py::TestDeepSeekV32Exp::test_auto_dtype_with_helix[fifo-cudagraph:with_padding-pp1tp1cp4]
 accuracy/test_disaggregated_serving.py::TestDeepSeekV32Exp::test_auto_dtype_with_helix[fifo-cudagraph:with_padding-pp1tp2cp2]
 accuracy/test_disaggregated_serving.py::TestDeepSeekV32Exp::test_auto_dtype_with_helix[fifo-cudagraph:with_padding-pp2tp1cp2]
+accuracy/test_disaggregated_serving.py::TestDeepSeekV32Exp::test_kv_cache_v2_nixl_python[cache_mgr_v1]
 accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=0-overlap_scheduler=False]
 accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=0-overlap_scheduler=True]
 accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=2-overlap_scheduler=False]
diff --git a/tests/integration/test_lists/test-db/l0_dgx_b300.yml b/tests/integration/test_lists/test-db/l0_dgx_b300.yml
index 5b53885685f9..64f4d5632310 100644
--- a/tests/integration/test_lists/test-db/l0_dgx_b300.yml
+++ b/tests/integration/test_lists/test-db/l0_dgx_b300.yml
@@ -64,6 +64,8 @@ l0_dgx_b300:
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4a16[dp4-auto]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4a16[dp4-fp8]
   - accuracy/test_disaggregated_serving.py::TestQwen3_8B::test_nixl_backend
+  - accuracy/test_disaggregated_serving.py::TestDeepSeekR1::test_kv_cache_v2_nixl_python[cache_mgr_v1]
+  - accuracy/test_disaggregated_serving.py::TestDeepSeekV32Exp::test_kv_cache_v2_nixl_python[cache_mgr_v1]
   - accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_nixl_backend
   - accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_kv_cache_v2_nixl_python
   - accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_kv_cache_v2_nixl_python