From fca0d377987a8d1019d044c47566f8fff2fece8c Mon Sep 17 00:00:00 2001 From: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com> Date: Fri, 1 Aug 2025 18:27:22 +0800 Subject: [PATCH] [None][fix] update nemotron nas tests free_gpu_memory_fraction=0.8 (#6552) Signed-off-by: Xin He (SW-GPU) <200704525+xinhe-nv@users.noreply.github.com> --- tests/integration/defs/accuracy/test_llm_api_pytorch.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tests/integration/defs/accuracy/test_llm_api_pytorch.py b/tests/integration/defs/accuracy/test_llm_api_pytorch.py index 2ff42a1878..4e3248145e 100644 --- a/tests/integration/defs/accuracy/test_llm_api_pytorch.py +++ b/tests/integration/defs/accuracy/test_llm_api_pytorch.py @@ -1495,9 +1495,10 @@ class TestNemotronNas(LlmapiAccuracyTestHarness): MODEL_NAME = "nemotron-nas/Llama-3_1-Nemotron-51B-Instruct" MODEL_PATH = f"{llm_models_root()}/nemotron-nas/Llama-3_1-Nemotron-51B-Instruct" + @pytest.mark.skip_less_device_memory(80000) @pytest.mark.skip_less_device(8) def test_auto_dtype_tp8(self): - kv_cache_config = KvCacheConfig(free_gpu_memory_fraction=0.9) + kv_cache_config = KvCacheConfig(free_gpu_memory_fraction=0.8) pytorch_config = dict() with LLM(self.MODEL_PATH,