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, 01:15 UTC
[CI][Bugfix] Fix `entrypoints/openai/test_audio.py` (#31151)
Signed-off-by: NickLucche <nlucches@redhat.com>
Nicolò Lucchesi committed
Dec 22, 2025 at 16:21 UTC
b1c3f96ae3874cc3b5a6bc7e55f43339b81da183
1 file changed
+1
-1
tests/entrypoints/openai/test_audio.py
+1
-1
@@ -313,7 +313,7 @@ async def test_chat_streaming_input_audio(
313
"format": "wav",
314
},
315
},
316
- {"type": "text", "text": "What's happening in this audio?"},
316
+ {"type": "text", "text": "What's a short title for this audio?"},
317
],
318
}
319
]