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 9, 11:15 UTC
[CI] Whisper tests `enforce_eager=False` (#33098)
Signed-off-by: NickLucche <nlucches@redhat.com>
Nicolò Lucchesi committed
Jan 28, 2026 at 18:36 UTC
8ebf372e9d612a325f54aadf5c0c3c6588b6afa3
1 file changed
+1
-2
tests/entrypoints/openai/test_transcription_validation_whisper.py
+1
-2
@@ -16,12 +16,11 @@ import soundfile as sf
16
from ...utils import RemoteOpenAIServer
17
18
MODEL_NAME = "openai/whisper-large-v3-turbo"
19
-SERVER_ARGS = ["--enforce-eager"]
19
20
21
@pytest.fixture(scope="module")
22
def server():
24
- with RemoteOpenAIServer(MODEL_NAME, SERVER_ARGS) as remote_server:
23
+ with RemoteOpenAIServer(MODEL_NAME, []) as remote_server:
24
yield remote_server
25
26