From 50a74a1daaf9bf31be1a9d31893702ca3dca5c5e Mon Sep 17 00:00:00 2001 From: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com> Date: Thu, 5 Jun 2025 10:39:21 +0800 Subject: [PATCH] tests: fix 5273697 (#4685) Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com> --- tests/integration/defs/test_e2e.py | 9 ++++----- tests/integration/test_lists/waives.txt | 1 - 2 files changed, 4 insertions(+), 6 deletions(-) diff --git a/tests/integration/defs/test_e2e.py b/tests/integration/defs/test_e2e.py index 6b461436dd..26bcdee330 100644 --- a/tests/integration/defs/test_e2e.py +++ b/tests/integration/defs/test_e2e.py @@ -1701,11 +1701,9 @@ def test_relaxed_acceptance_quickstart_advanced_deepseek_r1_8gpus( pytest.param('Mixtral-8x7B-NVFP4', 'nvfp4-quantized/Mixtral-8x7B-Instruct-v0.1', marks=skip_pre_blackwell), - pytest.param( - 'Nemotron-Ultra-253B', - 'nemotron-nas/Llama-3_1-Nemotron-Ultra-253B-v1', - marks=[skip_pre_hopper, - pytest.mark.skip_less_device_memory(140000)]), + pytest.param('Nemotron-Ultra-253B', + 'nemotron-nas/Llama-3_1-Nemotron-Ultra-253B-v1', + marks=skip_pre_hopper), ]) def test_ptp_quickstart_advanced_8gpus(llm_root, llm_venv, model_name, model_path): @@ -1730,6 +1728,7 @@ def test_ptp_quickstart_advanced_8gpus(llm_root, llm_venv, model_name, "--model_dir", f"{llm_models_root()}/{model_path}", "--tp_size=8", + "--max_batch_size=32", ], stdout=running_log) if model_name in mapping: diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index 2ba9648489..5dbd59c0e3 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -378,7 +378,6 @@ full:B200/examples/test_qwen.py::test_llm_qwen_7b_multi_gpus_summary[qwen1.5_7b_ full:B200/examples/test_qwen.py::test_llm_qwen_7b_multi_gpus_summary[qwen2_7b_instruct-enable_fmha_fp32_acc-enable_plugin-tp2pp2-nb:4] SKIP (https://nvbugs/5247837) full:B200/examples/test_qwen.py::test_llm_qwen_7b_multi_gpus_summary[qwen2.5_7b_chat-enable_fmha_fp32_acc-enable_plugin-tp2pp2-nb:4] SKIP (https://nvbugs/5247837) accuracy/test_cli_flow.py::TestMixtral8x22B::test_int8_plugin_tp8[renormalize-tensor_parallel] SKIP (https://nvbugs/5273695) -test_e2e.py::test_ptp_quickstart_advanced_8gpus[Nemotron-Ultra-253B-nemotron-nas/Llama-3_1-Nemotron-Ultra-253B-v1] SKIP (https://nvbugs/5273697) examples/test_gpt.py::test_starcoder_fp8_quantization_2gpu[starcoder] SKIP (https://nvbugs/5144931) examples/test_gpt.py::test_starcoder_fp8_quantization_2gpu[starcoderplus] SKIP (https://nvbugs/5144931) examples/test_whisper.py::test_llm_whisper_general[large-v3-disable_gemm_plugin-disable_attention_plugin-disable_weight_only-float16-nb:1-use_python_runtime] SKIP (https://nvbugs/5244570)