xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-24 16:15:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

[bench] Support common prefix len config (for decode-only bench) (#29934)

Browse Source 
Signed-off-by: Ming Yang <minos.future@gmail.com>
This commit is contained in:
Ming Yang 2025-12-05 02:26:52 -08:00 committed by GitHub
parent 65ee97288a
commit f16356fe36
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 7 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/benchmarks/datasets.py
View File

@ -1842,6 +1842,7 @@ def get_samples(args, tokenizer) -> list[SampleRequest]:
random_seed=args.seed,
dataset_path=args.dataset_path,
disable_shuffle=args.disable_shuffle,
prefix_len=args.common_prefix_len,
).sample(
tokenizer=tokenizer,
num_requests=args.num_prompts,

6
vllm/benchmarks/serve.py
View File

@ -1221,6 +1221,12 @@ def add_cli_args(parser: argparse.ArgumentParser):
help="Repetition penalty sampling parameter. Only has effect on "
"openai-compatible backends.",
)
sampling_group.add_argument(
"--common-prefix-len",
type=int,
default=None,
help="Common prefix length shared by all prompts (used by random dataset)",
)
parser.add_argument(
"--tokenizer-mode",