A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 11, 07:30 UTC
[CI][Bugfix] Fix flaky `tests/entrypoints/openai/test_audio.py::test_chat_streaming_audio` (#30878)
Signed-off-by: NickLucche <nlucches@redhat.com>
Nicolò Lucchesi committed
Dec 17, 2025 at 18:49 UTC
9ca8cb38fd68142627c9649756f1ddc5432c8b19
1 file changed
+3
-1
tests/entrypoints/openai/test_audio.py
+3
-1
@@ -254,7 +254,9 @@ async def test_single_chat_session_input_audio(
254
async def test_chat_streaming_audio(
255
client: openai.AsyncOpenAI, model_name: str, audio_url: str
256
):
257
- messages = dummy_messages_from_audio_url(audio_url)
257
+ messages = dummy_messages_from_audio_url(
258
+ audio_url, "What's a short title for this audio?"
259
+ )
260
261
# test single completion
262
chat_completion = await client.chat.completions.create(