diff --git a/tests/integration/test_lists/test-db/l0_gh200.yml b/tests/integration/test_lists/test-db/l0_gh200.yml index c2dedcacb36..9c2e9818c6c 100644 --- a/tests/integration/test_lists/test-db/l0_gh200.yml +++ b/tests/integration/test_lists/test-db/l0_gh200.yml @@ -28,7 +28,7 @@ l0_gh200: - accuracy/test_cli_flow.py::TestGptNext::test_auto_dtype - accuracy/test_cli_flow.py::TestSantacoder::test_auto_dtype - examples/test_medusa.py::test_llm_medusa_with_qaunt_base_model_1gpu[fp8-use_py_session-medusa-vicuna-7b-v1.3-4-heads-float16-bs1] TIMEOUT (90) - - examples/test_medusa.py::test_llm_medusa_with_qaunt_base_model_1gpu[fp8-use_cpp_session-medusa-vicuna-7b-v1.3-4-heads-float16-bs1] + - examples/test_medusa.py::test_llm_medusa_with_qaunt_base_model_1gpu[fp8-use_cpp_session-medusa-vicuna-7b-v1.3-4-heads-float16-bs1] TIMEOUT (60) - unittest/trt/model/eagle - unittest/trt/model_api/test_model_level_api.py - unittest/trt/model_api/test_model_quantization.py diff --git a/tests/integration/test_lists/test-db/l0_h100.yml b/tests/integration/test_lists/test-db/l0_h100.yml index ada1ff80d83..bb6af71122c 100644 --- a/tests/integration/test_lists/test-db/l0_h100.yml +++ b/tests/integration/test_lists/test-db/l0_h100.yml @@ -85,7 +85,7 @@ l0_h100: tests: # ------------- CPP tests --------------- - cpp/test_unit_tests.py::test_unit_tests[common-90] - - cpp/test_unit_tests.py::test_unit_tests[kernels-90] + - cpp/test_unit_tests.py::test_unit_tests[kernels-90] TIMEOUT (60) - cpp/test_unit_tests.py::test_unit_tests[layers-90] TIMEOUT (60) - cpp/test_unit_tests.py::test_unit_tests[thop-90] - cpp/test_unit_tests.py::test_unit_tests[utils-90] diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index 733b8c3e9d7..7d33974d394 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -434,3 +434,11 @@ accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backe accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=TRTLLM-mtp_nextn=2-ep4-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False] SKIP (https://nvbugs/5349343) full:B200/test_e2e.py::test_ptp_quickstart_advanced_deepseek_multi_nodes[DeepSeek-R1/DeepSeek-R1-0528-FP4] SKIP (https://nvbugs/5344688) accuracy/test_llm_api.py::TestLlama3_1_8BInstruct::test_guided_decoding_4gpus SKIP (https://nvbugs/5346443) +test_e2e.py::test_openai_reasoning SKIP (https://nvbugs/5355091) +test_e2e.py::test_openai_misc_example SKIP (https://nvbugs/5355091) +accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=0-overlap_scheduler=False] SKIP (https://nvbugs/5354956) +accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_auto_dtype[mtp_nextn=2-overlap_scheduler=False] SKIP (https://nvbugs/5354956) +accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_fp8_block_scales[mtp=vanilla-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False] SKIP (https://nvbugs/5354946) +examples/test_multimodal.py::test_llm_multimodal_general[kosmos-2-pp:1-tp:1-float16-bs:1-cpp_e2e:True-nb:1] SKIP (https://nvbugs/5354936) +examples/test_multimodal.py::test_llm_multimodal_general[fuyu-8b-pp:1-tp:1-float16-bs:1-cpp_e2e:True-nb:1] SKIP (https://nvbugs/5354936) +accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_fp8_block_scales_4gpus_static_eplb SKIP (https://nvbugs/5354925) diff --git a/tests/unittest/llmapi/test_mpi_session.py b/tests/unittest/llmapi/test_mpi_session.py index 6d19955ff85..ae8b0eba7a0 100644 --- a/tests/unittest/llmapi/test_mpi_session.py +++ b/tests/unittest/llmapi/test_mpi_session.py @@ -54,6 +54,7 @@ def run_client(server_addr, values_to_process): return f"Error in client: {str(e)}" +@pytest.mark.skip(reason="https://nvbugs/5351244") @pytest.mark.parametrize("task_type", ["submit", "submit_sync"]) def test_remote_mpi_session(task_type: Literal["submit", "submit_sync"]): """Test RemoteMpiPoolSessionClient and RemoteMpiPoolSessionServer interaction"""