diff --git a/tests/integration/test_lists/qa/examples_test_list.txt b/tests/integration/test_lists/qa/examples_test_list.txt
index 0565af43c3..8ff4627a4c 100644
--- a/tests/integration/test_lists/qa/examples_test_list.txt
+++ b/tests/integration/test_lists/qa/examples_test_list.txt
@@ -445,6 +445,10 @@ accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_8gpus[tp8ep4---cuda
 accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_8gpus[tp8ep4-mtp_nextn=2--cuda_graph-overlap_scheduler]
 accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_8gpus[tp8ep8---cuda_graph-overlap_scheduler]
 accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_8gpus[tp8ep8-mtp_nextn=2--cuda_graph-overlap_scheduler]
+accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_fp8_block_scales[latency]
+accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_fp8_block_scales[latency]
+accuracy/test_disaggregated_serving.py::TestLlama3_1_8B::test_auto_dtype[False]
+accuracy/test_disaggregated_serving.py::TestLlama3_1_8B::test_auto_dtype[True]
 
 test_e2e.py::test_benchmark_sanity[bert_base] # 127.18s
 test_e2e.py::test_benchmark_sanity[gpt_350m] # 64.06s