frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Add penalties sampling parameters to serve tool (#25974)

Browse Source 
Signed-off-by: Sergei Skvortsov <sergeyskv@nebius.com>
Co-authored-by: Sergei Skvortsov <sergeyskv@nebius.com>
This commit is contained in:
Sergei Skvortsov
2025-10-03 23:43:14 +01:00
committed by GitHub
parent 75003f34e8
commit b71fcd4905
1 changed files with 24 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
vllm/benchmarks/serve.py
View File

@ -1077,6 +1077,27 @@ def add_cli_args(parser: argparse.ArgumentParser):
"openai-compatible backends. If not specified, default to greedy "
"decoding (i.e. temperature==0.0).",
)
sampling_group.add_argument(
"--frequency-penalty",
type=float,
default=None,
help="Frequency penalty sampling parameter. Only has effect on "
"openai-compatible backends.",
)
sampling_group.add_argument(
"--presence-penalty",
type=float,
default=None,
help="Presence penalty sampling parameter. Only has effect on "
"openai-compatible backends.",
)
sampling_group.add_argument(
"--repetition-penalty",
type=float,
default=None,
help="Repetition penalty sampling parameter. Only has effect on "
"openai-compatible backends.",
)
parser.add_argument(
'--tokenizer-mode',
@ -1211,6 +1232,9 @@ async def main_async(args: argparse.Namespace) -> dict[str, Any]:
"top_k": args.top_k,
"min_p": args.min_p,
"temperature": args.temperature,
"frequency_penalty": args.frequency_penalty,
"presence_penalty": args.presence_penalty,
"repetition_penalty": args.repetition_penalty,
}.items() if v is not None
}