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 Failure] Use float32 for tests/entrypoints/openai/test_audio.py (#22686)
Signed-off-by: mgoin <mgoin64@gmail.com>
Michael Goin committed
Aug 11, 2025 at 23:20 UTC
ea1292ad3ee724e44b3dfec2a26778cd614729f9
1 file changed
+2
tests/entrypoints/openai/test_audio.py
+2
@@ -23,6 +23,8 @@ MAXIMUM_AUDIOS = 2
23
@pytest.fixture(scope="module")
24
def server():
25
args = [
26
+ "--dtype",
27
+ "float32",
28
"--max-model-len",
29
"2048",
30
"--max-num-seqs",