[None][chore] Add failed cases into waives.txt (NVIDIA#9193)

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

Author: xinhe-nv

tests/integration/defs/examples/serve/test_serve.py

@@ -2,7 +2,7 @@
 import time
 
 import requests
-from defs.conftest import llm_models_root, skip_pre_hopper
+from defs.conftest import llm_models_root, skip_post_blackwell, skip_pre_hopper
 from defs.trt_test_alternative import popen, print_error, print_info
 from openai import OpenAI
 from requests.exceptions import RequestException
@@ -93,6 +93,7 @@ def check_openai_chat_completion(http_port="8000",
 
 
 @skip_pre_hopper
+@skip_post_blackwell
 def test_extra_llm_api_options(serve_test_root):
     test_configs_root = f"{serve_test_root}/test_configs"
     config_file = f"{test_configs_root}/Qwen3-30B-A3B-FP8.yml"

tests/integration/test_lists/waives.txt

@@ -35,36 +35,21 @@ examples/test_multimodal.py::test_llm_multimodal_general[video-neva-pp:1-tp:1-bf
 examples/test_whisper.py::test_llm_whisper_general[large-v3-enable_gemm_plugin-enable_attention_plugin-disable_weight_only-float16-nb:1-use_python_runtime] SKIP (https://nvbugs/4866931)
 examples/test_nemotron.py::test_llm_nemotron_3_8b_1gpu[bfloat16-fp8] SKIP (https://nvbugs/4961624)
 examples/test_mistral.py::test_llm_mistral_v1_1gpu[mistral-7b-v0.1-float16-max_attention_window_size_4096-chunked_summarization_long] SKIP (https://nvbugs/5321371)
-full:B200_PCIe/unittest/trt/functional SKIP (Disable for Blackwell)
-full:B200_PCIe/unittest/trt/quantization SKIP (Disable for Blackwell)
-full:B200_PCIe/unittest/trt/attention/test_bert_attention.py SKIP (Disable for Blackwell)
-full:B200_PCIe/unittest/trt/model/test_mamba.py SKIP (Disable for Blackwell)
-full:B200_PCIe/unittest/bindings SKIP (Disable for Blackwell)
-full:B200_PCIe/unittest/trt/attention/test_sage_attention.py unittest/llmapi/test_llm_download.py unittest/llmapi/test_llm_kv_cache_events.py unittest/trt/model/redrafter unittest/trt/model/test_phi.py unittest/trt/model/test_unet.py unittest/trt/python_plugin unittest/tools unittest/utils unittest/others SKIP (Disable for Blackwell)
-full:B200_PCIe/unittest/trt/quantization/test_weight_only_quant_matmul.py SKIP (Disable for Blackwell)
-full:B200_PCIe/unittest/trt/quantization/test_weight_only_groupwise_quant_matmul.py SKIP (Disable for Blackwell)
-full:B200_PCIe/unittest/trt/model/test_gpt.py -k "partition0" SKIP (Disable for Blackwell)
-full:B200_PCIe/unittest/test_model_runner_cpp.py SKIP (Disable for Blackwell)
-full:B200_PCIe/unittest/llmapi/test_llm_models.py -m "part0" SKIP (Disable for Blackwell for context fmha doesn't support when headsize is 80/96)
-full:B200_PCIe/examples/test_nemotron.py::test_llm_nemotron_3_8b_1gpu[bfloat16-fp8] SKIP (megatron-core 0.8 is not supported in python 3.12)
-full:B200_PCIe/accuracy/test_cli_flow.py::TestMixtral8x7B::test_fp4_plugin SKIP (Disable for Blackwell OOM)
-full:B200_PCIe/unittest/llmapi/test_llm_models.py -m "not (part0 or part1)" SKIP (Disable for Blackwell OOM)
-full:B200/unittest/trt/functional SKIP (Disable for Blackwell)
-full:B200/unittest/trt/quantization SKIP (Disable for Blackwell)
-full:B200/unittest/trt/attention/test_bert_attention.py SKIP (Disable for Blackwell)
-full:B200/unittest/trt/model/test_mamba.py SKIP (Disable for Blackwell)
-full:B200/unittest/bindings SKIP (Disable for Blackwell)
-full:B200/unittest/trt/attention/test_sage_attention.py unittest/llmapi/test_llm_download.py unittest/llmapi/test_llm_kv_cache_events.py unittest/trt/model/redrafter unittest/trt/model/test_phi.py unittest/trt/model/test_unet.py unittest/trt/python_plugin unittest/tools unittest/utils unittest/others SKIP (Disable for Blackwell)
-full:B200/unittest/trt/quantization/test_weight_only_quant_matmul.py SKIP (Disable for Blackwell)
-full:B200/unittest/trt/quantization/test_weight_only_groupwise_quant_matmul.py SKIP (Disable for Blackwell)
-full:B200/unittest/trt/model/test_gpt.py -k "partition0" SKIP (Disable for Blackwell)
-full:B200/unittest/test_model_runner_cpp.py SKIP (Disable for Blackwell)
-full:B200/unittest/llmapi/test_llm_models.py -m "part0" SKIP (Disable for Blackwell for context fmha doesn't support when headsize is 80/96)
-full:B200/examples/test_multimodal.py::test_llm_multimodal_general[video-neva-pp:1-tp:1-bfloat16-bs:1-cpp_e2e:False-nb:1] SKIP (megatron-core 0.8 is not supported in python 3.12)
-full:B200/examples/test_nemotron.py::test_llm_nemotron_3_8b_1gpu[bfloat16-fp8] SKIP (megatron-core 0.8 is not supported in python 3.12)
-full:B200/accuracy/test_cli_flow.py::TestMixtral8x7B::test_fp4_plugin SKIP (Disable for Blackwell OOM)
-full:B200/unittest/llmapi/test_llm_models.py -m "not (part0 or part1)" SKIP (Disable for Blackwell OOM)
-full:B200/examples/test_mixtral.py::test_llm_mixtral_moe_plugin_fp8_lora_4gpus[Mixtral-8x7B-v0.1-chinese-mixtral-lora] SKIP (https://nvbugs/5064768)
+full:sm100/unittest/trt/functional SKIP (Disable for Blackwell)
+full:sm100/unittest/trt/quantization SKIP (Disable for Blackwell)
+full:sm100/unittest/trt/attention/test_bert_attention.py SKIP (Disable for Blackwell)
+full:sm100/unittest/trt/model/test_mamba.py SKIP (Disable for Blackwell)
+full:sm100/unittest/bindings SKIP (Disable for Blackwell)
+full:sm100/unittest/trt/attention/test_sage_attention.py unittest/llmapi/test_llm_download.py unittest/llmapi/test_llm_kv_cache_events.py unittest/trt/model/redrafter unittest/trt/model/test_phi.py unittest/trt/model/test_unet.py unittest/trt/python_plugin unittest/tools unittest/utils unittest/others SKIP (Disable for Blackwell)
+full:sm100/unittest/trt/quantization/test_weight_only_quant_matmul.py SKIP (Disable for Blackwell)
+full:sm100/unittest/trt/quantization/test_weight_only_groupwise_quant_matmul.py SKIP (Disable for Blackwell)
+full:sm100/unittest/trt/model/test_gpt.py -k "partition0" SKIP (Disable for Blackwell)
+full:sm100/unittest/test_model_runner_cpp.py SKIP (Disable for Blackwell)
+full:sm100/unittest/llmapi/test_llm_models.py -m "part0" SKIP (Disable for Blackwell for context fmha doesn't support when headsize is 80/96)
+full:sm100/examples/test_nemotron.py::test_llm_nemotron_3_8b_1gpu[bfloat16-fp8] SKIP (megatron-core 0.8 is not supported in python 3.12)
+full:sm100/accuracy/test_cli_flow.py::TestMixtral8x7B::test_fp4_plugin SKIP (Disable for Blackwell OOM)
+full:sm100/unittest/llmapi/test_llm_models.py -m "not (part0 or part1)" SKIP (Disable for Blackwell OOM)
+full:sm100/examples/test_multimodal.py::test_llm_multimodal_general[video-neva-pp:1-tp:1-bfloat16-bs:1-cpp_e2e:False-nb:1] SKIP (megatron-core 0.8 is not supported in python 3.12)
 examples/test_mixtral.py::test_llm_mixtral_moe_plugin_fp8_lora_4gpus[Mixtral-8x7B-v0.1-chinese-mixtral-lora] SKIP (https://nvbugs/5064768)
 test_e2e.py::test_openai_consistent_chat SKIP (https://nvbugs/5112075)
 examples/test_eagle.py::test_qwen_eagle_1gpu[qwen_7b_chat-eagle1] SKIP (https://nvbugs/5206383)
@@ -408,3 +393,13 @@ disaggregated/test_disaggregated.py::test_disaggregated_mixed[TinyLlama-1.1B-Cha
 unittest/_torch/sampler/test_torch_sampler.py::TestBatchedSampling SKIP (https://nvbugs/5661877)
 test_e2e.py::test_ptp_quickstart_multimodal[mistral-small-3.1-24b-instruct-Mistral-Small-3.1-24B-Instruct-2503-mixture_text_image-True] SKIP (https://nvbugs/5568836)
 test_e2e.py::test_trtllm_multimodal_benchmark_serving SKIP (https://nvbugs/5647825)
+unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall_fp4[MNNVL] SKIP (https://nvbugs/5664904)
+unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall_fp4[DeepEP] SKIP (https://nvbugs/5664904)
+accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus_online_eplb[mtp_nextn=2-moe_backend=WIDEEP] SKIP (https://nvbugs/5665736)
+accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus_online_eplb[fp8kv=True-moe_backend=WIDEEP] SKIP (https://nvbugs/5665736)
+accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_fp8_block_scales_4gpus_static_eplb SKIP (https://nvbugs/5666070)
+unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall[DeepEPLowLatency] SKIP (https://nvbugs/5664904)
+unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall[DeepEP] SKIP (https://nvbugs/5664904)
+unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall[MNNVL] SKIP (https://nvbugs/5664904)
+examples/test_qwen.py::test_llm_qwen_int4_single_gpu_summary[qwen2.5_14b_instruct_int4-nb:4] SKIP (https://nvbugs/5666826)
+examples/test_llama.py::test_llm_llama_1gpu_fp4[llama-3.1-70b-instruct-enable_norm_quant_fusion-enable_fused_quant-fp4_plugin-bfloat16] SKIP (https://nvbugs/5451216)