xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-11 13:05:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Add random seed for prefix cache benchmark (#9081)

Browse Source
This commit is contained in:
Andy Dai 2024-10-04 14:58:57 -07:00 committed by GitHub
parent 05c531be47
commit 0cc566ca8f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
benchmarks/benchmark_prefix_caching.py
View File

@ -113,7 +113,7 @@ def repeat_and_sort_requests(requests: List[Tuple[str, int, int]],
def main(args): def main(args):
tokenizer = get_tokenizer(args.model, trust_remote_code=True) tokenizer = get_tokenizer(args.model, trust_remote_code=True)
input_length_range = tuple(map(int, args.input_length_range.split(':'))) input_length_range = tuple(map(int, args.input_length_range.split(':')))
random.seed(args.seed)
if args.dataset_path is not None: if args.dataset_path is not None:
print(f"Start to sample {args.num_prompts} prompts" print(f"Start to sample {args.num_prompts} prompts"
"from {args.dataset_path}") "from {args.dataset_path}")
@ -194,5 +194,7 @@ if __name__ == "__main__":
default='128:256', default='128:256',
help='Range of input lengths for sampling prompts,' help='Range of input lengths for sampling prompts,'
'specified as "min:max" (e.g., "128:256").') 'specified as "min:max" (e.g., "128:256").')
parser.add_argument("--seed", type=int, default=0,
help='Random seed for reproducibility')
args = parser.parse_args() args = parser.parse_args()
main(args) main(args)