diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index b82d22060315..ba6e8929a382 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -196,6 +196,9 @@ full:B200/test_e2e.py::test_multi_nodes_eval[Qwen3/Qwen3-235B-A22B-tp16-mmlu] SK full:B200/test_e2e.py::test_multi_nodes_eval[Qwen3/saved_models_Qwen3-235B-A22B_nvfp4_hf-tp16-mmlu] SKIP (https://nvbugs/6424188) full:B200/test_e2e.py::test_qwen_e2e_cpprunner_large_new_tokens[DeepSeek-R1-Distill-Qwen-1.5B-DeepSeek-R1-Distill-Qwen-1.5B] SKIP (https://nvbugs/6414760) full:B300/accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype_with_helix[fifo_v2-cudagraph:with_padding-pp1tp2cp2] SKIP (https://nvbugs/6410881) +full:B300/accuracy/test_epd_disagg_multimodal.py::TestVideoMMEEPD::test_disaggregated_videomme[nemotron_nano_v3_omni_fp8] SKIP (https://nvbugs/6475622) +full:B300/accuracy/test_epd_disagg_multimodal.py::TestVideoMMEEPD::test_disaggregated_videomme[nemotron_nano_v3_omni_nvfp4] SKIP (https://nvbugs/6475622) +full:B300/accuracy/test_epd_disagg_multimodal.py::TestVideoMMEEPD::test_disaggregated_videomme[qwen3vl_2b_instruct] SKIP (https://nvbugs/6475622) full:B300/accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_mtp[bf16_ws4_180gb-flashinfer] SKIP (https://nvbugs/6478645) full:B300/accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_mtp[bf16_ws4_180gb-trtllm] SKIP (https://nvbugs/6478645) full:B300/accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_mtp[fp8_ws4_80gb-trtllm] SKIP (https://nvbugs/6478645) @@ -204,13 +207,17 @@ full:B300/accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_nvfp4_multi_gp full:B300/accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_nvfp4_multi_gpus[latency] SKIP (https://nvbugs/6423866) full:B300/accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_nvfp4_multi_gpus_chunked_prefill[latency_qsplit] SKIP (https://nvbugs/6423866) full:B300/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=True-enable_chunked_prefill=True-v2_kv_cache=True] SKIP (https://nvbugs/6422343) +full:B300/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_cute_dsl_nvfp4_4gpus[tp4-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=True] SKIP (https://nvbugs/6474888) +full:B300/accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_fp8_prequantized[torch_compile=True] SKIP (https://nvbugs/6475346) full:B300/accuracy/test_llm_api_pytorch.py::TestMiniMaxM3::test_auto_dtype[tp_size=8-ep_size=8] SKIP (https://nvbugs/6445375) full:B300/accuracy/test_llm_api_pytorch.py::TestMiniMaxM3::test_mxfp8[tp_size=4-ep_size=4] SKIP (https://nvbugs/6424188) full:B300/accuracy/test_llm_api_pytorch.py::TestMiniMaxM3::test_mxfp8_piecewise_cuda_graph[tp_size=8-ep_size=8] SKIP (https://nvbugs/6442594) full:B300/accuracy/test_llm_api_pytorch.py::TestMiniMaxM3::test_nvfp4[tp_size=4-ep_size=4] SKIP (https://nvbugs/6445375) full:B300/accuracy/test_llm_api_pytorch.py::TestMistralLarge3_675B::test_fp8[latency_moe_deepgemm] SKIP (https://nvbugs/6478720) +full:B300/accuracy/test_llm_api_pytorch.py::TestNemotronV3Ultra::test_nvfp4_8gpus[attention_dp_off-trtllm] SKIP (https://nvbugs/6474894) full:B300/accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_auto_dtype[forced_chunked_prefill] SKIP (https://nvbugs/6422318) full:B300/accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_auto_dtype[full_budget] SKIP (https://nvbugs/6422318) +full:B300/disaggregated/test_auto_scaling.py::test_service_discovery[http-kv_cache_aware] SKIP (https://nvbugs/6474892) full:B300/disaggregated/test_disaggregated.py::test_disaggregated_ctxpp2_genpp2[TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/6322073) full:B300/test_e2e.py::test_qwen_e2e_cpprunner_large_new_tokens[DeepSeek-R1-Distill-Qwen-1.5B-DeepSeek-R1-Distill-Qwen-1.5B] SKIP (https://nvbugs/6414760) full:B300/unittest/_torch/attention/test_attention_backends.py::test_attention_backend[gpt_oss_gqa_hd64_gptj_swa128-ctx-bf16-HND-p32-v1] SKIP (https://nvbugs/6468821)