Limit concurrency on test_transcription_api_correctness.py (#41478)

Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
This commit is contained in:
Ekagra Ranjan
2026-05-02 03:19:07 +00:00
committed by GitHub
parent 964a4bc2a5
commit 3e49479c4b
@@ -26,6 +26,9 @@ from vllm.tokenizers import get_tokenizer
from ....models.registry import HF_EXAMPLE_MODELS
from ....utils import RemoteOpenAIServer
# Tuned to prevent OOM on 18GB GPUs in transcription correctness tests.
MAX_SEQS_FOR_TRANSCRIPTION_TEST = 32
def to_bytes(y, sr):
buffer = io.BytesIO()
@@ -184,6 +187,7 @@ def test_wer_correctness(
server_args = [
"--enforce-eager",
f"--tokenizer_mode={model_info.tokenizer_mode}",
f"--max_num_seqs={MAX_SEQS_FOR_TRANSCRIPTION_TEST}",
]
if model_info.trust_remote_code:
server_args.append("--trust-remote-code")