From ff0775408d7a23707af05f86f72656d9aa95d57b Mon Sep 17 00:00:00 2001 From: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com> Date: Thu, 22 Jan 2026 14:17:50 +0800 Subject: [PATCH] [None][fix] Fix waived tests for Nemotron-h models (#10758) Signed-off-by: Wanli Jiang <35160485+Wanli-Jiang@users.noreply.github.com> --- tests/integration/defs/accuracy/test_llm_api_pytorch.py | 3 +++ tests/integration/test_lists/waives.txt | 2 -- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/tests/integration/defs/accuracy/test_llm_api_pytorch.py b/tests/integration/defs/accuracy/test_llm_api_pytorch.py index ed5ba3f45e..ab4315f3cc 100644 --- a/tests/integration/defs/accuracy/test_llm_api_pytorch.py +++ b/tests/integration/defs/accuracy/test_llm_api_pytorch.py @@ -5387,6 +5387,7 @@ class TestNemotronV3Nano(LlmapiAccuracyTestHarness): EXTRA_EVALUATOR_KWARGS = dict(chat_template_kwargs=dict( enable_thinking=False)) + @pytest.mark.skip_less_device_memory(80000) def test_auto_dtype(self): with LLM( f"{llm_models_root()}/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", @@ -5404,6 +5405,7 @@ class TestNemotronV3Nano(LlmapiAccuracyTestHarness): extra_evaluator_kwargs=self.EXTRA_EVALUATOR_KWARGS) @skip_pre_hopper + @pytest.mark.skip_less_device_memory(40000) def test_fp8(self): with LLM( f"{llm_models_root()}/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", @@ -5427,6 +5429,7 @@ class TestNemotronV3Super(LlmapiAccuracyTestHarness): EXTRA_EVALUATOR_KWARGS = dict(chat_template_kwargs=dict( enable_thinking=False)) + @skip_pre_hopper @pytest.mark.skip_less_device_memory(64000) @pytest.mark.skip_less_mpi_world_size(4) @pytest.mark.parametrize( diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index c27ded0c7c..7a2176da94 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -350,13 +350,11 @@ accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B_Instruct_2507::test_skip_sof accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[ep4-mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=True] SKIP (https://nvbugs/5800646) accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[tp4-mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=True] SKIP (https://nvbugs/5800646) accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=2-tp4-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False] SKIP (https://nvbugs/5800672) -accuracy/test_llm_api_pytorch.py::TestNemotronV3Super::test_auto_dtype_4gpus[4-4-True-False-True] SKIP (https://nvbugs/5810980) accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_multi_gpus[latency] SKIP (https://nvbugs/5814309) accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[tp4-mtp_nextn=2-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=True] SKIP (https://nvbugs/5800646) unittest/_torch/thop/parallel/test_fp4_swizzle.py::test_swizzle_sf SKIP (https://nvbugs/5811159) stress_test/stress_test.py::test_run_stress_test[llama-v3-8b-instruct-hf_tp1-stress_time_300s_timeout_450s-MAX_UTILIZATION-pytorch-stress-test] SKIP (https://nvbugs/5814203) unittest/_torch/attention/test_trtllm_flashinfer_symbol_collision.py::test_flashinfer_fused_moe_matches_torch_moe SKIP (https://nvbugs/5814215) -full:sm89/accuracy/test_llm_api_pytorch.py::TestNemotronV3Nano::test_auto_dtype SKIP (https://nvbugs/5814504) full:sm89/accuracy/test_llm_api_pytorch_multimodal.py::TestNVILA_8B::test_auto_dtype SKIP (https://nvbugs/5814504) unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_tp_sharding.py::test_sharding_pattern_detection[NemotronHMamba2Mixer-torch_dist_all_reduce-False-False-8] SKIP (https://nvbugs/5819002) unittest/_torch/auto_deploy/unit/multigpu/transformations/library/test_tp_sharding.py::test_sharding_pattern_detection[NemotronHMamba2Mixer-torch_dist_all_reduce-False-True-8] SKIP (https://nvbugs/5819002)