From 814e74733195fe3f4915705844166b2bf9c25e24 Mon Sep 17 00:00:00 2001
From: Yiyun Lu <55233584+luyiyun1021@users.noreply.github.com>
Date: Fri, 4 Sep 2026 05:29:39 +0000
Subject: [PATCH] [https://nvbugs/6720250][test] Waive
 test_openai_completion_list_prompt_stream_reuses_stream_metadata

The test builds its server with object.__new__(OpenAIServer), bypassing
__init__, and hand-sets only the attributes the code path needed when it was
written. PR #17491 moved the openai_completion streaming path from the
module-level get_steady_clock_now_in_seconds() to
self._adjusted_steady_clock.now(), so the stub now raises AttributeError.

Waived under the same NVBug as the VisualGen timing breakage, which has the
same root cause. This is a stopgap; the fix is proposed on PR #18686.

Signed-off-by: Yiyun Lu <55233584+luyiyun1021@users.noreply.github.com>
---
 tests/integration/test_lists/waives.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt
index 4a0987b5a47e..858751553e54 100644
--- a/tests/integration/test_lists/waives.txt
+++ b/tests/integration/test_lists/waives.txt
@@ -341,6 +341,7 @@ unittest/executor/test_rpc.py::TestRpcCorrectness::test_incremental_task_async S
 unittest/executor/test_rpc_proxy.py SKIP (https://nvbugs/5605741)
 unittest/executor/test_rpc_worker.py SKIP (https://nvbugs/5605741)
 unittest/llmapi/test_llm.py::test_generate_with_detokenization_stop_words_streaming[/scratch.trt_llm_data/llm-models/gemma/gemma-3-1b-it] SKIP (https://nvbugs/6566772)
+unittest/llmapi/test_llm.py::test_openai_completion_list_prompt_stream_reuses_stream_metadata SKIP (https://nvbugs/6720250)
 unittest/llmapi/test_llm_multi_gpu_pytorch.py -m "gpu2" SKIP (https://nvbugs/6428092)
 unittest/llmapi/test_llm_multi_gpu_pytorch.py::test_llm_get_stats_pp2[False-False-True] SKIP (https://nvbugs/6432826)
 unittest/llmapi/test_llm_pytorch.py::test_gqa_nemo_lora[None] SKIP (https://nvbugs/6162504)