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 8, 05:00 UTC
Fixed whisper CPU test that does not spawn properly. (#34324)
Signed-off-by: Anna Mayne <anna.mayne@arm.com> Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
almayne committed
Feb 17, 2026 at 14:46 UTC
6bd6d0c3c1195e007925b8c3c5ee214745f721d9
1 file changed
-1
tests/models/multimodal/generation/test_whisper.py
-1
@@ -117,7 +117,6 @@ def check_model_available(model: str) -> None:
117
@pytest.mark.parametrize("dtype", ["half", "float"])
118
@pytest.mark.parametrize("num_logprobs", [5])
119
@pytest.mark.parametrize("enforce_eager", [True, False])
120
-@create_new_process_for_each_test("spawn")
120
def test_models(
121
hf_runner,
122
vllm_runner,