From 9a97f0a3b7529e229de54e1a86942a527e9ee26e Mon Sep 17 00:00:00 2001 From: dominicshanshan <30051912+dominicshanshan@users.noreply.github.com> Date: Sat, 6 Sep 2025 21:29:16 +0800 Subject: [PATCH] [None][ci] Waive qwen3 test for accuracy bug in https://nvbugs/5505402 (#7585) Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com> --- tests/integration/defs/accuracy/test_llm_api_pytorch.py | 1 + tests/integration/test_lists/test-db/l0_b200.yml | 1 + 2 files changed, 2 insertions(+) diff --git a/tests/integration/defs/accuracy/test_llm_api_pytorch.py b/tests/integration/defs/accuracy/test_llm_api_pytorch.py index 2b8190e4ad..05fe064c50 100644 --- a/tests/integration/defs/accuracy/test_llm_api_pytorch.py +++ b/tests/integration/defs/accuracy/test_llm_api_pytorch.py @@ -2317,6 +2317,7 @@ class TestQwen3_8B(LlmapiAccuracyTestHarness): MODEL_NAME = "Qwen3/Qwen3-8B" @skip_pre_hopper + @pytest.mark.skip(reason="https://nvbugs/5505402") @pytest.mark.parametrize( "tp_size,pp_size,ep_size,attention_dp,cuda_graph,overlap_scheduler", [(1, 1, 1, False, True, True)], diff --git a/tests/integration/test_lists/test-db/l0_b200.yml b/tests/integration/test_lists/test-db/l0_b200.yml index 7d53b90373..031548955b 100644 --- a/tests/integration/test_lists/test-db/l0_b200.yml +++ b/tests/integration/test_lists/test-db/l0_b200.yml @@ -37,6 +37,7 @@ l0_b200: - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-cutlass] - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-trtllm] - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[True-True-triton] + - accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_fp8_block_scales[latency] # nvbugs 5505402 - disaggregated/test_workers.py::test_workers_kv_cache_aware_router_eviction[TinyLlama-1.1B-Chat-v1.0] # nvbugs 5300551 - test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-NVFP4-nvfp4-quantized/Meta-Llama-3.1-8B] - test_e2e.py::test_ptp_quickstart_advanced[Llama3.1-8B-FP8-llama-3.1-model/Llama-3.1-8B-Instruct-FP8]