Limit gpu utils and lower max BS on test_transcription_api_correctness.py (#41649)

Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
This commit is contained in:
Ekagra Ranjan
2026-05-04 10:30:02 -07:00
committed by GitHub
parent 3e1ad4435f
commit 321fa2d6d1
@@ -27,7 +27,8 @@ 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
MAX_SEQS_FOR_TRANSCRIPTION_TEST = 8
GPU_UTIL_FOR_TRANSCRIPTION_TEST = 0.5
def to_bytes(y, sr):
@@ -188,6 +189,7 @@ def test_wer_correctness(
"--enforce-eager",
f"--tokenizer_mode={model_info.tokenizer_mode}",
f"--max_num_seqs={MAX_SEQS_FOR_TRANSCRIPTION_TEST}",
f"--gpu_memory_utilization={GPU_UTIL_FOR_TRANSCRIPTION_TEST}",
]
if model_info.trust_remote_code:
server_args.append("--trust-remote-code")