From 592988ebdb091e9d5c82dd8168054218c40f9dde Mon Sep 17 00:00:00 2001 From: Pengyun Lin <81065165+LinPoly@users.noreply.github.com> Date: Mon, 2 Feb 2026 16:18:41 +0800 Subject: [PATCH] [https://nvbugs/5819444][fix] Unwaive gpt-oss test (#10927) Signed-off-by: Pengyun Lin <81065165+LinPoly@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com> --- tests/integration/test_lists/waives.txt | 1 - tests/unittest/llmapi/apps/_test_openai_chat_harmony.py | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index cb4257cf17..5d1bfaa36e 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -301,7 +301,6 @@ accuracy/test_llm_api_pytorch.py::TestNemotronV3Super::test_auto_dtype_4gpus[4-4 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[dp2-cutlass-auto] SKIP (https://nvbugs/5836828) accuracy/test_llm_api_pytorch.py::TestNemotronV3Super::test_auto_dtype_4gpus[4-4-True-True-True] SKIP (https://nvbugs/5823587) accuracy/test_llm_api_pytorch.py::TestQwen3_4B::test_eagle3 SKIP (https://nvbugs/5836592) -test_e2e.py::test_openai_chat_harmony SKIP (https://nvbugs/5819444) accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_4gpus[ep4-mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False] SKIP (https://nvbugs/5800646) accuracy/test_disaggregated_serving.py::TestQwen3_30B_A3B::test_mixed_ctx_gen_model[ctxpp2gentp2] SKIP (https://nvbugs/5748664) examples/test_llama.py::test_llama_3_x_with_bf16_lora_torch[llama-3.2-1b-instruct] SKIP (https://nvbugs/5838178) diff --git a/tests/unittest/llmapi/apps/_test_openai_chat_harmony.py b/tests/unittest/llmapi/apps/_test_openai_chat_harmony.py index 5eadaf88ae..e247cb21d9 100644 --- a/tests/unittest/llmapi/apps/_test_openai_chat_harmony.py +++ b/tests/unittest/llmapi/apps/_test_openai_chat_harmony.py @@ -160,6 +160,7 @@ async def test_streaming(client: openai.AsyncOpenAI, model: str): "content": "Explain the theory of relativity in brief." }], stream=True, + extra_body={"top_k": 1}, ) collected_messages = [] first_iteration = True