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 13, 22:00 UTC
[CI/Build] Fix flaky test_transcription_validation.py::test_basic_audio_gemma (#27924)
Signed-off-by: Ben Browning <bbrownin@redhat.com>
Ben Browning committed
Nov 1, 2025 at 23:45 UTC
758ea2e980a1eeacec6097bfd98bd0a7c8fb864a
1 file changed
+3
-1
tests/entrypoints/openai/test_transcription_validation.py
+3
-1
@@ -72,7 +72,9 @@ async def test_basic_audio_gemma(foscolo):
72
model_name = "google/gemma-3n-E2B-it"
73
server_args = ["--enforce-eager"]
74
75
- with RemoteOpenAIServer(model_name, server_args) as remote_server:
75
+ with RemoteOpenAIServer(
76
+ model_name, server_args, max_wait_seconds=480
77
+ ) as remote_server:
78
client = remote_server.get_async_client()
79
transcription = await client.audio.transcriptions.create(
80
model=model_name,