[None][fix] waive failed tests (#9090)

Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com>

Author: xinhe-nv

tests/integration/defs/examples/test_llama.py

@@ -33,7 +33,8 @@
 from defs.conftest import (get_device_count, get_device_memory,
                            get_host_total_memory, get_sm_version,
                            skip_fp8_pre_ada, skip_no_nvls, skip_post_blackwell,
-                           skip_pre_ada, skip_pre_blackwell)
+                           skip_post_blackwell_ultra, skip_pre_ada,
+                           skip_pre_blackwell)
 # yapf: enable
 from defs.trt_test_alternative import check_call, exists
 
@@ -288,6 +289,7 @@ def test_llm_llama_v1_manage_weights_1gpu_summarize(llama_example_root,
 
 
 @skip_pre_blackwell
+@skip_post_blackwell_ultra
 @pytest.mark.parametrize("data_type", ['bfloat16', 'float16'])
 @pytest.mark.parametrize("fp4_type", ["plugin", "ootb", "disable"],
                          ids=["fp4_plugin", "fp4_ootb", "disable_fp4"])
@@ -2187,6 +2189,7 @@ def test_llm_llama_code_llama_1gpu_summary(
     venv_check_call(llm_venv, summary_cmd)
 
 
+@skip_post_blackwell_ultra
 @pytest.mark.timeout(7200)
 @pytest.mark.skip_less_device_memory(40000)
 @pytest.mark.parametrize("num_beams", [1, 4],
@@ -3383,6 +3386,7 @@ def test_llm_llama_v3_2_smoothquant_1node_single_gpu(
 @pytest.mark.timeout(7200)
 @pytest.mark.skip_less_device_memory(80000)
 @pytest.mark.skip_less_device(4)
+@skip_post_blackwell_ultra
 @pytest.mark.parametrize("fp8_quant",
                          [pytest.param(True, marks=skip_post_blackwell), False],
                          ids=['enable_fp8', 'disable_fp8'])

tests/integration/test_lists/waives.txt

@@ -397,3 +397,13 @@ accuracy/test_disaggregated_serving.py::TestQwen3_8B::test_auto_dtype[True] SKIP
 disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_bf16_empty_batch[DeepSeek-V3-Lite-bf16] SKIP (https://nvbugs/5601682)
 accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_eagle3[eagle3_one_model=False-overlap_scheduler=False] SKIP (https://nvbugs/5655584)
 accuracy/test_disaggregated_serving.py::TestQwen3_8B::test_chunked_prefill SKIP (https://nvbugs/5608930)
+accuracy/test_disaggregated_serving.py::TestQwen3_8B::test_auto_dtype[False] SKIP (https://nvbugspro.nvidia.com/bug/5651854)
+test_e2e.py::test_ptp_quickstart_multimodal_chunked_prefill[phi4-multimodal-instruct-fp4-multimodals/Phi-4-multimodal-instruct-FP4-0.8-image] SKIP (https://nvbugs/5568836)
+test_e2e.py::test_ptp_quickstart_multimodal_chunked_prefill[phi4-multimodal-instruct-fp4-multimodals/Phi-4-multimodal-instruct-FP4-0.8-image] SKIP (https://nvbugs/5568836)
+test_e2e.py::test_ptp_quickstart_multimodal_kv_cache_reuse[phi4-multimodal-instruct-fp4-multimodals/Phi-4-multimodal-instruct-FP4-0.8-image] SKIP (https://nvbugs/5568836)
+test_e2e.py::test_ptp_quickstart_multimodal_multiturn[phi4-multimodal-instruct-fp4-multimodals/Phi-4-multimodal-instruct-FP4] SKIP (https://nvbugs/5568836)
+examples/test_multimodal.py::test_llm_multimodal_general[llava-1.5-7b-hf-pp:1-tp:1-float16-bs:1-cpp_e2e:False-nb:1] SKIP (https://nvbugs/5655832)
+examples/test_multimodal.py::test_llm_multimodal_general[llava-1.5-7b-hf-pp:1-tp:1-float16-bs:8-cpp_e2e:False-nb:1] SKIP (https://nvbugs/5655832)
+examples/test_multimodal.py::test_llm_multimodal_general[llava-onevision-qwen2-7b-ov-hf-video-pp:1-tp:1-float16-bs:1-cpp_e2e:False-nb:1] SKIP (https://nvbugs/5655832)
+examples/test_multimodal.py::test_llm_multimodal_general[llava-onevision-qwen2-7b-ov-hf-pp:1-tp:1-float16-bs:1-cpp_e2e:False-nb:1] SKIP (https://nvbugs/5655832)
+examples/test_multimodal.py::test_llm_multimodal_general[Qwen2-VL-7B-Instruct-pp:1-tp:1-float16-bs:1-cpp_e2e:False-nb:4] SKIP (https://nvbugs/5655832)