[Benchmark] Do not save detailed info to json by default (#14879)

Signed-off-by: simon-mo <simon.mo@hey.com>
This commit is contained in:
Simon Mo 2025-03-16 21:48:11 -07:00 committed by GitHub
parent a73e183e36
commit 583a9778e0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 19 additions and 1 deletions

View File

@ -14,7 +14,8 @@ from tqdm.asyncio import tqdm
from transformers import (AutoTokenizer, PreTrainedTokenizer,
PreTrainedTokenizerFast)
from vllm.model_executor.model_loader.weight_utils import get_lock
# NOTE(simon): do not import vLLM here so the benchmark script
# can run without vLLM installed.
AIOHTTP_TIMEOUT = aiohttp.ClientTimeout(total=6 * 60 * 60)
@ -427,6 +428,8 @@ def get_model(pretrained_model_name_or_path: str) -> str:
if os.getenv('VLLM_USE_MODELSCOPE', 'False').lower() == 'true':
from modelscope import snapshot_download
from vllm.model_executor.model_loader.weight_utils import get_lock
# Use file lock to prevent multiple processes from
# downloading the same model weights at the same time.
with get_lock(pretrained_model_name_or_path):

View File

@ -684,6 +684,15 @@ def main(args: argparse.Namespace):
"Invalid metadata format. Please use KEY=VALUE format."
)
if not args.save_detailed:
# Remove fields with too many data points
for field in [
"input_lens", "output_lens", "ttfts", "itls",
"generated_texts", "errors"
]:
if field in result_json:
del result_json[field]
# Traffic
result_json["request_rate"] = (args.request_rate if args.request_rate
< float("inf") else "inf")
@ -828,6 +837,12 @@ if __name__ == "__main__":
action="store_true",
help="Specify to save benchmark results to a json file",
)
parser.add_argument(
"--save-detailed",
action="store_true",
help="When saving the results, whether to include per request "
"information such as response, error, ttfs, tpots, etc.",
)
parser.add_argument(
"--metadata",
metavar="KEY=VALUE",