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 14, 05:30 UTC
[CI] Re-enable transcriptions `test_long_audio_request` (#22890)
Signed-off-by: NickLucche <nlucches@redhat.com>
Nicolò Lucchesi committed
Aug 14, 2025 at 13:34 UTC
540d54ca8d38633b69cc5a2ba99641e6304a7564
1 file changed
-3
tests/entrypoints/openai/test_transcription_validation.py
-3
@@ -80,9 +80,6 @@ async def test_bad_requests(mary_had_lamb):
80
async def test_long_audio_request(mary_had_lamb, model_name):
81
server_args = ["--enforce-eager"]
82
83
- if model_name.startswith("openai"):
84
- return
85
-
83
mary_had_lamb.seek(0)
84
audio, sr = librosa.load(mary_had_lamb)
85
# Add small silence after each audio for repeatability in the split process