diff --git a/tests/integration/defs/accuracy/test_llm_api_autodeploy.py b/tests/integration/defs/accuracy/test_llm_api_autodeploy.py
index acbfdcc1d6..3fbb077843 100644
--- a/tests/integration/defs/accuracy/test_llm_api_autodeploy.py
+++ b/tests/integration/defs/accuracy/test_llm_api_autodeploy.py
@@ -66,11 +66,13 @@ class TestLlama3_1_8B(LlmapiAccuracyTestHarness):
                               use_beam_search=beam_width > 1)
 
     @pytest.mark.skip_less_device_memory(32000)
-    def test_auto_dtype(self):
+    @pytest.mark.parametrize("world_size", [1, 2, 4])
+    def test_auto_dtype(self, world_size):
         kwargs = self.get_default_kwargs()
         sampling_params = self.get_default_sampling_params()
         with AutoDeployLLM(model=self.MODEL_PATH,
                            tokenizer=self.MODEL_PATH,
+                           world_size=world_size,
                            **kwargs) as llm:
             task = CnnDailymail(self.MODEL_NAME)
             task.evaluate(llm)
diff --git a/tests/integration/test_lists/test-db/l0_b200.yml b/tests/integration/test_lists/test-db/l0_b200.yml
index 1e052ea11e..8f2cf4abd0 100644
--- a/tests/integration/test_lists/test-db/l0_b200.yml
+++ b/tests/integration/test_lists/test-db/l0_b200.yml
@@ -74,6 +74,8 @@ l0_b200:
   - unittest/_torch/modeling -k "modeling_llama"
   - unittest/_torch/modeling -k "modeling_mixtral"
   - unittest/_torch/modeling -k "modeling_gpt_oss"
+    # ------------- AutoDeploy tests ---------------
+  - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[1]
   - unittest/_torch/auto_deploy/unit/singlegpu
 - condition:
     ranges:
diff --git a/tests/integration/test_lists/test-db/l0_dgx_b200.yml b/tests/integration/test_lists/test-db/l0_dgx_b200.yml
index f98f0c029d..5a8b3f35a6 100644
--- a/tests/integration/test_lists/test-db/l0_dgx_b200.yml
+++ b/tests/integration/test_lists/test-db/l0_dgx_b200.yml
@@ -181,5 +181,3 @@ l0_dgx_b200:
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-cutlass-auto]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-triton-auto]
   - disaggregated/test_disaggregated.py::test_disaggregated_benchmark_on_diff_backends[llama-v3-8b-hf]
-  # ------------- AutoDeploy tests ---------------
-  - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype
diff --git a/tests/integration/test_lists/test-db/l0_dgx_h100.yml b/tests/integration/test_lists/test-db/l0_dgx_h100.yml
index b4f8adc07c..b2cf63bf03 100644
--- a/tests/integration/test_lists/test-db/l0_dgx_h100.yml
+++ b/tests/integration/test_lists/test-db/l0_dgx_h100.yml
@@ -41,7 +41,7 @@ l0_dgx_h100:
   - accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_auto_dtype[True-True-False]
   - accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_auto_dtype[True-True-True]
   # ------------- AutoDeploy tests ---------------
-  - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype
+  - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[2]
 - condition:
     ranges:
       system_gpu_count:
diff --git a/tests/integration/test_lists/test-db/l0_dgx_h200.yml b/tests/integration/test_lists/test-db/l0_dgx_h200.yml
index 36cd9b9696..c31066f3d4 100644
--- a/tests/integration/test_lists/test-db/l0_dgx_h200.yml
+++ b/tests/integration/test_lists/test-db/l0_dgx_h200.yml
@@ -34,8 +34,6 @@ l0_dgx_h200:
   - unittest/_torch/multi_gpu_modeling/test_llama4.py::test_llama4[pp1-ep1-disable_adp-enable_graph-tp8-trtllm-scout]
   - unittest/_torch/multi_gpu_modeling/test_llama4.py::test_llama4[pp1-ep4-enable_adp-enable_graph-tp8-trtllm-scout]
   - unittest/llmapi/test_llm_pytorch.py::test_nemotron_nas_lora
-  # ------------- AutoDeploy tests ---------------
-  - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype
 - condition:
     ranges:
       system_gpu_count:
@@ -121,6 +119,8 @@ l0_dgx_h200:
   - test_e2e.py::test_trtllm_bench_llmapi_launch[pytorch_backend-llama-v3-llama3-8b]
   - test_e2e.py::test_trtllm_bench_mgmn
   - unittest/_torch/multi_gpu -m "post_merge" TIMEOUT (90)
+  # ------------- AutoDeploy tests ---------------
+  - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[4]
 - condition:
     ranges:
       system_gpu_count:
diff --git a/tests/integration/test_lists/test-db/l0_h100.yml b/tests/integration/test_lists/test-db/l0_h100.yml
index c6b4f446c5..8b4d3261be 100644
--- a/tests/integration/test_lists/test-db/l0_h100.yml
+++ b/tests/integration/test_lists/test-db/l0_h100.yml
@@ -114,7 +114,7 @@ l0_h100:
   - test_e2e.py::test_ptp_quickstart_multimodal[gemma-3-27b-it-gemma/gemma-3-27b-it-image-True] TIMEOUT (90)
   - test_e2e.py::test_trtllm_benchmark_serving[llama-3.1-model/Meta-Llama-3.1-8B]
   # ------------- AutoDeploy tests ---------------
-  - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype
+  - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[1]
   - accuracy/test_llm_api_autodeploy.py::TestNemotronH::test_auto_dtype
 - condition:
     ranges: