[None][infra] Waive failed tests on main branch 8/20 (NVIDIA#7092)

Signed-off-by: qqiao <[email protected]>

Author: EmmaQiaoCh

tests/integration/test_lists/waives.txt

@@ -319,3 +319,4 @@ disaggregated/test_disaggregated.py::test_disaggregated_diff_max_tokens[TinyLlam
 disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_fp8_tp1_single_gpu_mtp[DeepSeek-V3-Lite-fp8] SKIP (https://nvbugs/5465642)
 examples/test_multimodal.py::test_llm_multimodal_general[Mistral-Small-3.1-24B-Instruct-2503-pp:1-tp:1-bfloat16-bs:1-cpp_e2e:False-nb:1] SKIP (https://nvbugs/5431146)
 accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_fp8_blockscale[latency] SKIP (https://nvbugs/5464461)
+disaggregated/test_disaggregated.py::test_disaggregated_benchmark_on_diff_backends[DeepSeek-V3-Lite-fp8] SKIP (https://nvbugs/5448449)

tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py

@@ -600,6 +600,7 @@ def test_trtllm_bench(llm_root):  # noqa: F811
         run_benchmark(model_name, dataset_path, temp_dir)
 
 
+@pytest.mark.skip(reason="https://nvbugs/5458798")
 @pytest.mark.no_xdist
 def test_trtllm_bench_backend_comparison(llm_root):  # noqa: F811
     """Test that compares autodeploy backend performance against pytorch backend

tests/unittest/_torch/modules/test_fused_moe.py

@@ -289,6 +289,7 @@ def per_rank_test_fused_moe_alltoall(job_id):
             assert r is None
 
 
+@pytest.mark.skip(reason="https://nvbugs/5467531")
 @pytest.mark.skipif(torch.cuda.device_count() < 4,
                     reason="needs 4 GPUs to run this test")
 @pytest.mark.parametrize("alltoall_method_type", [