add test cases into qa test list

xinhe-nv · xinhe-nv · commit a5cc148b64ce · 2025-09-30T09:29:39.000+08:00
Signed-off-by: Xin He (SW-GPU) &lt;200704525+xinhe-nv@users.noreply.github.com&gt;
diff --git a/tests/integration/test_lists/qa/llm_function_core.txt b/tests/integration/test_lists/qa/llm_function_core.txt
@@ -622,6 +622,7 @@ test_e2e.py::test_qwen_e2e_cpprunner_large_new_tokens[DeepSeek-R1-Distill-Qwen-1
 test_e2e.py::test_openai_multi_chat_example
 test_e2e.py::test_openai_consistent_chat
 test_e2e.py::test_openai_chat_guided_decoding
+test_e2e.py::test_openai_chat_harmony
 test_e2e.py::test_trtllm_benchmark_serving[llama-3.1-model/Meta-Llama-3.1-8B]
 test_e2e.py::test_trtllm_benchmark_serving[gpt_oss/gpt-oss-20b]
 test_e2e.py::test_trtllm_multimodal_benchmark_serving
@@ -745,6 +746,7 @@ disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_simple_qwen3[
 disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_simple_qwen3[True-True-Qwen3-8B-FP8]
 disaggregated/test_disaggregated.py::test_disaggregated_ctxtp2pp2_gentp2pp2[TinyLlama-1.1B-Chat-v1.0]
 disaggregated/test_disaggregated.py::test_disaggregated_ctxpp4_genpp4[TinyLlama-1.1B-Chat-v1.0]
+disaggregated/test_disaggregated.py::test_disaggregated_kv_cache_time_output[TinyLlama-1.1B-Chat-v1.0]
 disaggregated/test_workers.py::test_workers_conditional_disaggregation[TinyLlama-1.1B-Chat-v1.0]
 disaggregated/test_workers.py::test_workers_kv_cache_events[TinyLlama-1.1B-Chat-v1.0]
 disaggregated/test_workers.py::test_workers_kv_cache_aware_router[TinyLlama-1.1B-Chat-v1.0]
diff --git a/tests/integration/test_lists/qa/llm_function_core_sanity.txt b/tests/integration/test_lists/qa/llm_function_core_sanity.txt
@@ -207,6 +207,7 @@ disaggregated/test_workers.py::test_workers_conditional_disaggregation[TinyLlama
 disaggregated/test_workers.py::test_workers_kv_cache_aware_router_eviction[TinyLlama-1.1B-Chat-v1.0]
 disaggregated/test_workers.py::test_workers_kv_cache_aware_router[TinyLlama-1.1B-Chat-v1.0]
 disaggregated/test_workers.py::test_workers_kv_cache_events[TinyLlama-1.1B-Chat-v1.0]
+test_e2e.py::test_openai_chat_harmony
 test_e2e.py::test_openai_consistent_chat
 test_e2e.py::test_openai_multi_chat_example
 test_e2e.py::test_ptp_quickstart
diff --git a/tests/integration/test_lists/qa/llm_function_nim.txt b/tests/integration/test_lists/qa/llm_function_nim.txt
@@ -173,6 +173,7 @@ accuracy/test_llm_api_pytorch.py::TestQwQ_32B::test_auto_dtype_tp4
 accuracy/test_llm_api_pytorch.py::TestCodestral_22B_V01::test_auto_dtype
 accuracy/test_llm_api_pytorch.py::TestKimiK2::test_fp8_blockscale[latency]
 
+test_e2e.py::test_openai_chat_harmony
 test_e2e.py::test_ptp_quickstart_advanced_8gpus[Nemotron-Ultra-253B-nemotron-nas/Llama-3_1-Nemotron-Ultra-253B-v1]
 test_e2e.py::test_ptp_quickstart_advanced[Nemotron4_4B-BF16-nemotron/Minitron-4B-Base]
 test_e2e.py::test_ptp_quickstart_advanced[Nemotron-H-8B-Nemotron-H-8B-Base-8K]
