20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Bugfix] Add random_seed to sample_hf_requests in benchmark_serving script (#9013)

Browse Source 
Co-authored-by: Isotr0py <2037008807@qq.com>
This commit is contained in:
Kai Wu 2024-10-17 14:11:11 -07:00 committed by GitHub
parent eca2c5f7c0
commit d65049daab
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
benchmarks/benchmark_serving.py
View File

@ -202,6 +202,7 @@ def sample_hf_requests(
dataset_split: str,
num_requests: int,
tokenizer: PreTrainedTokenizerBase,
random_seed: int,
fixed_output_len: Optional[int] = None,
) -> List[Tuple[str, str, int, Optional[Dict[str, Collection[str]]]]]:
dataset = load_dataset(dataset_path,
@ -210,8 +211,8 @@ def sample_hf_requests(
streaming=True)
assert "conversations" in dataset.features, (
"HF Dataset must have 'conversations' column.")
filtered_dataset = dataset.shuffle().filter(
lambda x: len(x["conversations"]) >= 2)
filter_func = lambda x: len(x["conversations"]) >= 2
filtered_dataset = dataset.shuffle(seed=random_seed).filter(filter_func)
sampled_requests: List[Tuple[str, int, int, Dict[str,
Collection[str]]]] = []
for data in filtered_dataset:
@ -646,6 +647,7 @@ def main(args: argparse.Namespace):
dataset_split=args.hf_split,
num_requests=args.num_prompts,
tokenizer=tokenizer,
random_seed=args.seed,
fixed_output_len=args.hf_output_len,
)