diff --git a/tests/integration/defs/disaggregated/test_disaggregated.py b/tests/integration/defs/disaggregated/test_disaggregated.py index b8136359f972..437f5c2231a4 100644 --- a/tests/integration/defs/disaggregated/test_disaggregated.py +++ b/tests/integration/defs/disaggregated/test_disaggregated.py @@ -2331,7 +2331,7 @@ def test_disaggregated_gpt_oss_120b_harmony(disaggregated_test_root, ), pytest.param(TestConfig(model_path='gpt_oss/gpt-oss-120b', test_desc='gpt_oss_120b_triton_stress', - request_count=60000, + request_count=30000, accuracy_threshold=0.42, cancellation_rate=10, cancellation_delay=0.5), diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index f08ad5e8ff18..39d794260d9f 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -230,7 +230,6 @@ full:GH200/examples/test_nemotron.py::test_llm_nemotron_3_8b_1gpu[bfloat16-fp8] full:GH200/examples/test_qwen2audio.py::test_llm_qwen2audio_single_gpu[qwen2_audio_7b_instruct] SKIP (arm is not supported) full:GH200/unittest/trt/model_api/test_model_quantization.py SKIP (https://nvbugs/4979955) full:H100/disaggregated/test_disaggregated.py::test_disaggregated_stress_test[input8k-output1k-conc512-gpt_oss_120b_eagle_triton_stress] SKIP (https://nvbugs/6250439) -full:H100/disaggregated/test_disaggregated.py::test_disaggregated_stress_test[input8k-output1k-conc512-gpt_oss_120b_triton_stress] SKIP (https://nvbugs/6222480) full:H100_PCIe/unittest/llmapi/test_llm_pytorch.py::test_llama_7b_multi_lora_evict_and_reload_lora_gpu_cache SKIP (https://nvbugs/5682551) full:H20/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_chunked_prefill[triton-auto] SKIP (https://nvbugs/6026676) full:RTX/accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype SKIP (https://nvbugs/5569696)