tests: waive failed cases on main (#5781)

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

Author: xinhe-nv

tests/integration/defs/accuracy/test_llm_api_pytorch.py

@@ -1517,6 +1517,7 @@ class TestNemotronUltra(LlmapiAccuracyTestHarness):
  ids=["tp8", "tp8ep4", "tp8ep8"])
  def test_auto_dtype(self, cuda_graph, tp_size, pp_size, ep_size):
  with LLM(self.MODEL_PATH,
+ max_batch_size=32,
  tensor_parallel_size=tp_size,
  pipeline_parallel_size=pp_size,
  moe_expert_parallel_size=ep_size,
@@ -1526,9 +1527,9 @@ def test_auto_dtype(self, cuda_graph, tp_size, pp_size, ep_size):
  task.evaluate(llm)
  task = GSM8K(self.MODEL_NAME)
  task.evaluate(llm)
- task = GPQADiamond(self.MODEL_NAME)
- task.evaluate(llm,
- extra_evaluator_kwargs=dict(apply_chat_template=True))
+ # task = GPQADiamond(self.MODEL_NAME)
+ # task.evaluate(llm,
+ #  extra_evaluator_kwargs=dict(apply_chat_template=True))
 
  @pytest.mark.skip_less_device(8)
  @pytest.mark.skip_device_not_contain(["H100", "B200"])

tests/integration/defs/test_e2e.py

@@ -1857,13 +1857,13 @@ def test_relaxed_acceptance_quickstart_advanced_deepseek_r1_8gpus(
  marks=skip_pre_hopper),
  pytest.param('Llama3.1-405B-FP8',
  'llama-3.1-model/Llama-3.1-405B-Instruct-FP8',
- marks=skip_pre_hopper),
+ marks=(skip_pre_hopper, pytest.mark.timeout(7200))),
  pytest.param('Mixtral-8x7B-NVFP4',
  'nvfp4-quantized/Mixtral-8x7B-Instruct-v0.1',
  marks=skip_pre_blackwell),
  pytest.param('Nemotron-Ultra-253B',
  'nemotron-nas/Llama-3_1-Nemotron-Ultra-253B-v1',
- marks=skip_pre_hopper),
+ marks=(skip_pre_hopper, pytest.mark.timeout(12600))),
 ])
 def test_ptp_quickstart_advanced_8gpus(llm_root, llm_venv, model_name,
  model_path):

tests/integration/test_lists/waives.txt

@@ -451,3 +451,9 @@ disaggregated/test_workers.py::test_workers_kv_cache_aware_router_eviction[TinyL
 test_e2e.py::test_ptp_quickstart_advanced[Mixtral-8x7B-NVFP4-nvfp4-quantized/Mixtral-8x7B-Instruct-v0.1] SKIP (https://nvbugs/5377465)
 test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-70B-FP8-llama-3.1-model/Llama-3.1-70B-Instruct-FP8] SKIP (https://nvbugs/5377465)
 accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[4gpu_latency_moe_cutlass] SKIP (https://nvbugs/5369010)
+accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_auto_dtype[tp8ep4-cuda_graph=True] SKIP (https://nvbugs/5358226)
+accuracy/test_llm_api_pytorch.py::TestLlama4ScoutInstruct::test_auto_dtype[tp8ep8-cuda_graph=True] SKIP (https://nvbugs/5358226)
+examples/test_multimodal.py::test_llm_multimodal_general[VILA1.5-3b-pp:1-tp:1-float16-bs:1-cpp_e2e:True-nb:1] SKIP (https://nvbugs/5360086)
+accuracy/test_llm_api_pytorch.py::TestNemotronNas::test_auto_dtype_tp8 SKIP (https://nvbugs/5380101)
+test_e2e.py::test_ptp_quickstart_advanced_8gpus[Llama3.1-405B-FP8-llama-3.1-model/Llama-3.1-405B-Instruct-FP8] SKIP (https://nvbugs/5380570)
+test_e2e.py::test_ptp_quickstart_advanced_8gpus[Nemotron-Ultra-253B-nemotron-nas/Llama-3_1-Nemotron-Ultra-253B-v1] SKIP (https://nvbugs/5380570)