diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index 0873db201325..00985ee3f9a4 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -349,3 +349,5 @@ full:H20-3e/accuracy/test_llm_api_pytorch.py::TestNemotronUltra::test_auto_dtype full:H20-3e/accuracy/test_llm_api_pytorch.py::TestKimiK2::test_fp8_blockscale[latency] SKIP (slow I/O) full:H20-3e/test_e2e.py::test_ptp_quickstart_advanced_multi_gpus[DeepSeek-V3-671B-FP8-DeepSeek-V3-0324-8] SKIP (slow I/O) disaggregated/test_disaggregated_single_gpu.py::test_disaggregated_spec_dec_batch_slot_limit[False-False-EAGLE3-LLaMA3.1-Instruct-8B-Llama-3.1-8B-Instruct] SKIP (https://nvbugs/5608743) +accuracy/test_disaggregated_serving.py::TestGPTOSS::test_auto_dtype[False] SKIP (https://nvbugs/5624367) +accuracy/test_disaggregated_serving.py::TestGPTOSS::test_auto_dtype[True] SKIP (https://nvbugs/5624367) diff --git a/tests/unittest/_torch/thop/parallel/test_fp8_rowwise_linear.py b/tests/unittest/_torch/thop/parallel/test_fp8_rowwise_linear.py index db5eb101d474..25234fb1f087 100644 --- a/tests/unittest/_torch/thop/parallel/test_fp8_rowwise_linear.py +++ b/tests/unittest/_torch/thop/parallel/test_fp8_rowwise_linear.py @@ -6,6 +6,7 @@ from tensorrt_llm.models.modeling_utils import QuantAlgo, QuantConfig +@pytest.mark.skip(reason="https://nvbugs/5619396") @skip_blackwell @skip_pre_hopper @pytest.mark.parametrize("dtype", [torch.float16, torch.bfloat16])