[None][chore] Add failed cases into waives.txt (#8669)

Signed-off-by: xinhe-nv <[email protected]>
Signed-off-by: Xin He (SW-GPU) <[email protected]>

Author: xinhe-nv

tests/integration/defs/accuracy/test_cli_flow.py

@@ -18,13 +18,19 @@
                                  MedusaDecodingConfig)
 from tensorrt_llm.quantization import QuantAlgo
 
-from ..conftest import (llm_models_root, parametrize_with_ids, skip_no_nvls,
-                        skip_post_blackwell, skip_pre_ada, skip_pre_blackwell,
-                        skip_pre_hopper)
+from ..conftest import (get_sm_version, llm_models_root, parametrize_with_ids,
+                        skip_no_nvls, skip_post_blackwell, skip_pre_ada,
+                        skip_pre_blackwell, skip_pre_hopper)
 from .accuracy_core import (MMLU, CliFlowAccuracyTestHarness, CnnDailymail,
                             Humaneval, PassKeyRetrieval64k,
                             PassKeyRetrieval128k, SlimPajama6B, ZeroScrolls)
 
+# skip trt flow cases on post-Blackwell-Ultra
+if get_sm_version() >= 103:
+    pytest.skip(
+        "TRT workflow tests are not supported on post Blackwell-Ultra architecture",
+        allow_module_level=True)
+
 
 class TestGpt2(CliFlowAccuracyTestHarness):
     MODEL_NAME = "gpt2"

tests/integration/test_lists/waives.txt

@@ -391,3 +391,10 @@ accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_bf16[multi_gpus_no_cache] S
 triton_server/test_triton.py::test_llava[llava] SKIP (https://nvbugs/5547414)
 disaggregated/test_workers.py::test_workers_kv_cache_aware_router[TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/5607238)
 unittest/executor/test_rpc_proxy.py SKIP (https://nvbugs/5605741)
+full:RTX/accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype SKIP (https://nvbugs/5569696)
+full:RTX/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[tp2-trtllm-auto] SKIP (https://nvbugs/5569719)
+full:RTX/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[tp2-trtllm-fp8] SKIP (https://nvbugs/5569719)
+full:RTX/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[ep2-trtllm-auto] SKIP (https://nvbugs/5569719)
+full:RTX/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[ep2-trtllm-fp8] SKIP (https://nvbugs/5569719)
+full:RTX/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[dp2-trtllm-auto] SKIP (https://nvbugs/5569719)
+full:RTX/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[dp2-trtllm-fp8] SKIP (https://nvbugs/5569719)