diff --git a/tests/integration/defs/accuracy/test_disaggregated_serving.py b/tests/integration/defs/accuracy/test_disaggregated_serving.py index 2d6b02897d..c52911fe00 100644 --- a/tests/integration/defs/accuracy/test_disaggregated_serving.py +++ b/tests/integration/defs/accuracy/test_disaggregated_serving.py @@ -1091,11 +1091,13 @@ class TestGPTOSS(LlmapiAccuracyTestHarness): "max_attention_window": [128, 32768], "enable_block_reuse": block_reuse, "enable_partial_reuse": False, + "free_gpu_memory_fraction": 0.5, } gen_server_config["kv_cache_config"] = { "max_attention_window": [128, 32768], "enable_block_reuse": block_reuse, "enable_partial_reuse": False, + "free_gpu_memory_fraction": 0.5, } disaggregated_server_config = { "hostname": "localhost", diff --git a/tests/integration/defs/accuracy/test_llm_api_pytorch.py b/tests/integration/defs/accuracy/test_llm_api_pytorch.py index ab9c1591c1..66b07ebf7b 100644 --- a/tests/integration/defs/accuracy/test_llm_api_pytorch.py +++ b/tests/integration/defs/accuracy/test_llm_api_pytorch.py @@ -4369,6 +4369,11 @@ class TestGPTOSS(LlmapiAccuracyTestHarness): "https://nvbugs/5636916: Remaining Hopper Eagle Accuracy Issue for only TP=4" ) + if not one_model and overlap_scheduler: + pytest.skip( + "https://nvbugs/5745152: two_model + overlap_scheduler can sometimes time out." + ) + MAX_OUTPUT_LEN = 128179 MAX_INPUT_LEN = 32768 diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index 6de1fa6b55..935e7be832 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -320,8 +320,6 @@ accuracy/test_llm_api_pytorch.py::TestLlama3_1NemotronNano8Bv1::test_fp8_prequan accuracy/test_llm_api_pytorch.py::TestNemotronH_47B_Base::test_auto_dtype[tp8ep4-cuda_graph=True] SKIP (https://nvbugs/5640697) accuracy/test_llm_api_pytorch.py::TestNemotronH_47B_Base::test_reasoning_fp8_prequantized[tp8ep8-cuda_graph=True] SKIP (https://nvbugs/5640697) accuracy/test_llm_api_pytorch.py::TestQwQ_32B::test_auto_dtype_tp4 SKIP (https://nvbugs/5640697) -accuracy/test_disaggregated_serving.py::TestGPTOSS::test_auto_dtype[True] SKIP (https://nvbugs/5644632) -accuracy/test_disaggregated_serving.py::TestGPTOSS::test_auto_dtype[False] SKIP (https://nvbugs/5644632) test_e2e.py::test_ptp_quickstart_multimodal[mistral-small-3.1-24b-instruct-Mistral-Small-3.1-24B-Instruct-2503-image-True] SKIP (https://nvbugs/5648560) test_e2e.py::test_ptp_quickstart_multimodal[mistral-small-3.1-24b-instruct-Mistral-Small-3.1-24B-Instruct-2503-image-False] SKIP (https://nvbugs/5648560) accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_multi_gpus[latency_trtllmgen_adp_lmtp] SKIP (https://nvbugs/5629136)